Spaces:
Paused
Paused
v0.6: Arrangement Studio, Demucs htdemucs (CPU), bucket persistence
Browse files- Dockerfile +17 -3
- README.md +323 -220
- app/bass.py +284 -0
- app/guardian.py +145 -0
- app/mini_model.py +280 -0
- app/mixer.py +160 -0
- app/models/omega_tag_mini_v1.npz +3 -0
- app/noise.py +253 -0
- app/server.py +467 -5
- app/static/app.js +353 -5
- app/static/arrangement.css +171 -0
- app/static/arrangement.js +382 -0
- app/static/index.html +189 -2
- app/static/style.css +56 -0
- app/virtualbass.py +88 -0
- docs/ARRANGEMENT_STUDIO.md +42 -0
- docs/BASS_CORE_DESIGN.md +64 -0
- docs/NOISE_CORE_DESIGN.md +74 -0
- docs/RELEASE_0.6.md +27 -0
- pyproject.toml +3 -3
- tests/test_arrangement.py +158 -0
- tests/test_bass.py +168 -0
- tests/test_noise.py +198 -0
Dockerfile
CHANGED
|
@@ -1,12 +1,26 @@
|
|
| 1 |
FROM python:3.11-slim
|
| 2 |
-
RUN apt-get update && apt-get install -y --no-install-recommends libsndfile1
|
|
|
|
| 3 |
RUN useradd -m -u 1000 user
|
| 4 |
USER user
|
| 5 |
ENV HOME=/home/user PATH=/home/user/.local/bin:$PATH \
|
| 6 |
-
ABSOLUTION_DATA_DIR=/tmp/omega_data
|
|
|
|
|
|
|
|
|
|
| 7 |
WORKDIR /home/user/app
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
COPY --chown=user pyproject.toml requirements.txt ./
|
| 9 |
COPY --chown=user app ./app
|
| 10 |
-
RUN pip install --no-cache-dir --user .
|
| 11 |
EXPOSE 7860
|
| 12 |
CMD ["uvicorn", "app.server:app", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
|
| 1 |
FROM python:3.11-slim
|
| 2 |
+
RUN apt-get update && apt-get install -y --no-install-recommends libsndfile1 ffmpeg git curl ca-certificates \
|
| 3 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 4 |
RUN useradd -m -u 1000 user
|
| 5 |
USER user
|
| 6 |
ENV HOME=/home/user PATH=/home/user/.local/bin:$PATH \
|
| 7 |
+
ABSOLUTION_DATA_DIR=/data ABSOLUTION_FALLBACK_DIR=/tmp/omega_data \
|
| 8 |
+
ABSOLUTION_MAX_UPLOAD_MIB=200 \
|
| 9 |
+
ABSOLUTION_DEMUCS_REPO=/home/user/demucs_models ABSOLUTION_DEMUCS_MAX_SECONDS=120 \
|
| 10 |
+
OMP_NUM_THREADS=2 TORCH_HOME=/home/user/.cache/torch
|
| 11 |
WORKDIR /home/user/app
|
| 12 |
+
# CPU-only PyTorch + Demucs (demucs.api lives on the upstream main branch, not in PyPI 4.0.1)
|
| 13 |
+
RUN pip install --no-cache-dir --user --index-url https://download.pytorch.org/whl/cpu \
|
| 14 |
+
torch==2.1.2 torchaudio==2.1.2 \
|
| 15 |
+
&& pip install --no-cache-dir --user "numpy<2" \
|
| 16 |
+
"demucs @ git+https://github.com/adefossez/demucs@2883f3db65617d6d178c6ed10d869dc14e44e59b"
|
| 17 |
+
# Official htdemucs v4 checkpoint, verified by SHA-256 at build time
|
| 18 |
+
RUN mkdir -p $ABSOLUTION_DEMUCS_REPO && cd $ABSOLUTION_DEMUCS_REPO \
|
| 19 |
+
&& curl -fsSL -o 955717e8-8726e21a.th https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/955717e8-8726e21a.th \
|
| 20 |
+
&& echo "8726e21a993978c7ba086d3872e7608d7d5bfca646ca4aca459ffda844faa8b4 955717e8-8726e21a.th" | sha256sum -c - \
|
| 21 |
+
&& printf "models: ['955717e8']\n" > htdemucs.yaml
|
| 22 |
COPY --chown=user pyproject.toml requirements.txt ./
|
| 23 |
COPY --chown=user app ./app
|
| 24 |
+
RUN pip install --no-cache-dir --user . "numpy<2"
|
| 25 |
EXPOSE 7860
|
| 26 |
CMD ["uvicorn", "app.server:app", "--host", "0.0.0.0", "--port", "7860"]
|
README.md
CHANGED
|
@@ -6,257 +6,360 @@ colorTo: purple
|
|
| 6 |
sdk: docker
|
| 7 |
app_port: 7860
|
| 8 |
pinned: false
|
| 9 |
-
short_description: Forensic audio lab – HPSS
|
| 10 |
---
|
| 11 |
|
| 12 |
-
> **Hugging Face Space note:** Public demo instance
|
| 13 |
|
| 14 |
-
# ABSOLUTION Ω —
|
| 15 |
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
separation (HPSS), source-aligned residual, audio previews, quality report, and export.
|
| 19 |
|
| 20 |
-
|
| 21 |
-
> The optional Demucs adapter is neural but needs trusted model weights installed manually.
|
| 22 |
-
> Neither method can guarantee perfectly pure or "quantum-exact" source extraction.
|
| 23 |
-
> No Zero-Day AI breakthrough is claimed.
|
| 24 |
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
## Full German audio website
|
| 37 |
-
|
| 38 |
-
The web experience includes a guided import flow, a bundled synthetic demo
|
| 39 |
-
(`GET /api/v1/demo`), an interactive waveform/seek control, persistent local
|
| 40 |
-
project recall, a four-section workspace, a global playback dock, single-stem
|
| 41 |
-
masters, batch ZIP export and a provenance dashboard.
|
| 42 |
-
|
| 43 |
-
**Run the included site:** `bash start.sh` on macOS/Linux,
|
| 44 |
-
`start_windows.bat` on Windows, or `docker compose up --build`.
|
| 45 |
-
Then open **http://127.0.0.1:8000**.
|
| 46 |
-
|
| 47 |
-
For installation details, user guide, security and actual feature scope,
|
| 48 |
-
see **[docs/WEBSITE.md](docs/WEBSITE.md)**.
|
| 49 |
-
|
| 50 |
-
**Public @sites deployment is not part of this deliverable.**
|
| 51 |
-
The FastAPI server does not have authentication: do not expose it publicly.
|
| 52 |
-
|
| 53 |
-
## Quickstart (Linux / macOS / Windows)
|
| 54 |
-
|
| 55 |
-
Requires Python **3.11+**, recommended virtual environment; tested with Python 3.13.
|
| 56 |
|
|
|
|
| 57 |
```bash
|
| 58 |
python -m venv .venv
|
| 59 |
-
# Linux/macOS:
|
| 60 |
-
|
| 61 |
-
# Windows PowerShell:
|
| 62 |
-
# .venv\Scripts\Activate.ps1
|
| 63 |
-
|
| 64 |
python -m pip install -e ".[dev]"
|
| 65 |
-
python tools/generate_demo.py
|
| 66 |
python -m pytest -q
|
| 67 |
python -m uvicorn app.server:app --host 127.0.0.1 --port 8000
|
| 68 |
```
|
| 69 |
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
```bash
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
Docker image enables DSP; it does **not** include trained neural checkpoints.
|
| 84 |
-
|
| 85 |
-
## Architecture and flow
|
| 86 |
-
|
| 87 |
-
```text
|
| 88 |
-
Browser (HTML/CSS/JS; fully offline-compatible)
|
| 89 |
-
|
|
| 90 |
-
| HTTP (FastAPI 0.1 REST / OpenAPI)
|
| 91 |
-
v
|
| 92 |
-
Audio Upload --- sanitize/check extension -> configurable upload size quota (default 1024 MiB)
|
| 93 |
-
| |
|
| 94 |
-
v v
|
| 95 |
-
Immutable Original SHA-256 + manifest.json
|
| 96 |
-
|
|
| 97 |
-
v
|
| 98 |
-
libsndfile streaming decoder -> metadata/peak waveform -> in-process queued job
|
| 99 |
-
|
|
| 100 |
-
+--> chunked STFT -> median harmonic/percussive masks -> inverse STFT
|
| 101 |
-
| |
|
| 102 |
-
| v
|
| 103 |
-
| Harmonic + Percussive
|
| 104 |
-
| |
|
| 105 |
-
| Original - both = Residual
|
| 106 |
-
| |
|
| 107 |
-
| v
|
| 108 |
-
| Mixture consistency report
|
| 109 |
-
| |
|
| 110 |
-
+--> [optional trusted Demucs local repo] |
|
| 111 |
-
trained four-source neural model |
|
| 112 |
-
| |
|
| 113 |
-
+------> residual calculation --------------+
|
| 114 |
-
|
|
| 115 |
-
v
|
| 116 |
-
WAV FLOAT master + PCM16 preview
|
| 117 |
-
|
|
| 118 |
-
v
|
| 119 |
-
Per-stem WAV / ZIP export
|
| 120 |
```
|
| 121 |
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
For the full hybrid roadmap, replace this with persistent Redis/RQ/Celery plus
|
| 125 |
-
PostgreSQL metadata and an optional S3-compatible artifact store. The browser
|
| 126 |
-
client remains usable without any external web service or CDN.
|
| 127 |
-
|
| 128 |
-
## Model setup (optional, experimental)
|
| 129 |
-
|
| 130 |
-
The model list advertises **HPSS READY** by default. It advertises Demucs
|
| 131 |
-
as configured only if `ABSOLUTION_DEMUCS_REPO` points to a directory containing
|
| 132 |
-
a `.th` file. Configuration alone does **not** guarantee the model loads.
|
| 133 |
-
|
| 134 |
-
1. Install `python -m pip install -e ".[neural]"` with a compatible PyTorch
|
| 135 |
-
and torchaudio environment. Confirm your CPU/GPU installation.
|
| 136 |
-
2. Manually obtain compatible **trusted** Demucs v4 `htdemucs` model files,
|
| 137 |
-
model definition YAML, and any required reference files in a local repository.
|
| 138 |
-
Review all model and dataset licenses first.
|
| 139 |
-
3. `export ABSOLUTION_DEMUCS_REPO=/absolute/path/to/release_models` (on Windows
|
| 140 |
-
set an equivalent environment variable), then restart the server.
|
| 141 |
-
4. Run a short file first; Demucs will process on CPU if CUDA is unavailable.
|
| 142 |
|
| 143 |
-
|
| 144 |
-
remote checkpoint fetching. Only load model weights from trusted sources,
|
| 145 |
-
because some checkpoint formats can execute code during deserialization.
|
| 146 |
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
|
| 152 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
|
| 154 |
-
|
| 155 |
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
| POST | `/api/v1/projects` | Create project `{"name":"..."}` |
|
| 161 |
-
| GET | `/api/v1/projects/{id}` | Get manifest and analysis |
|
| 162 |
-
| POST | `/api/v1/assets` | Multipart `project_id` and `file` |
|
| 163 |
-
| POST | `/api/v1/jobs/separate` | `{"project_id":"...", "model":"hpss"}` |
|
| 164 |
-
| GET | `/api/v1/jobs/{id}` | Poll queued/running/done/failed |
|
| 165 |
-
| GET | `/api/v1/projects/{id}/stems` | Stem metadata and reconstruction report |
|
| 166 |
-
| GET | `/api/v1/projects/{id}/audio/{stem}` | Master audio; `?preview=true` for PCM16 |
|
| 167 |
-
| GET | `/api/v1/projects/{id}/export` | ZIP source + stems + manifest |
|
| 168 |
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
The separate 16-bit PCM listening files are intentionally not master exports.
|
| 172 |
|
| 173 |
-
|
| 174 |
|
| 175 |
-
|
| 176 |
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
|
| 213 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 214 |
|
| 215 |
```bash
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
python -m pytest -q
|
| 217 |
-
|
| 218 |
-
```
|
| 219 |
-
|
| 220 |
-
The eleven automated tests cover reconstruction, stereo, silence, malformed
|
| 221 |
-
files, >180-second import and separation, streamed chunk boundaries,
|
| 222 |
-
API project/upload/separation/export and refusal of unsupported
|
| 223 |
-
prompt-based operations. Additional model-weight, browser
|
| 224 |
-
interaction, stress and security tests are needed before production use.
|
| 225 |
-
|
| 226 |
-
## File layout
|
| 227 |
-
|
| 228 |
-
```text
|
| 229 |
-
app/
|
| 230 |
-
audio.py - file decode and signal processing
|
| 231 |
-
server.py - FastAPI, project store, jobs and export
|
| 232 |
-
static/ - responsive browser workstation
|
| 233 |
-
tests/
|
| 234 |
-
test_audio.py - DSP, format and limit checks
|
| 235 |
-
test_api.py - HTTP end-to-end and negative cases
|
| 236 |
-
tools/
|
| 237 |
-
generate_demo.py - creates entirely synthetic demo.wav
|
| 238 |
-
Dockerfile
|
| 239 |
-
compose.yaml
|
| 240 |
-
pyproject.toml
|
| 241 |
-
requirements.txt
|
| 242 |
-
.env.example
|
| 243 |
-
docs/ARCHITECTURE.md
|
| 244 |
-
docs/LICENSE_AND_SECURITY.md
|
| 245 |
```
|
| 246 |
|
| 247 |
-
##
|
| 248 |
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
| 259 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 260 |
|
| 261 |
-
|
| 262 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
sdk: docker
|
| 7 |
app_port: 7860
|
| 8 |
pinned: false
|
| 9 |
+
short_description: Forensic audio lab – HPSS + Demucs stems, arrangement mixer
|
| 10 |
---
|
| 11 |
|
| 12 |
+
> **Hugging Face Space note:** Public demo instance, no authentication. Demucs htdemucs v4 runs on CPU (max. 120 s audio per job); HPSS has no duration limit. Upload limit 200 MiB. Projects are stored in an attached HF Storage Bucket at `/data` if mounted, otherwise in `/tmp` (lost on restart). Do not upload private/confidential audio.
|
| 13 |
|
| 14 |
+
# ABSOLUTION Ω — v0.6 · Arrangement Studio + OMEGA-TAG Mini
|
| 15 |
|
| 16 |
+
**Lokales Fullstack-Audiostudio.** Enthält alle Funktionen aus v0.4 (BASS-CORE, NOISE-CORE,
|
| 17 |
+
Virtual Bass, HPSS, optional Demucs) und zusätzlich ein farbiges Mehrspur-Arrangement.
|
|
|
|
| 18 |
|
| 19 |
+
## Schnellstart
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
+
1. ZIP entpacken. **Python 3.11+** muss installiert sein.
|
| 22 |
+
2. Windows: `start_windows.bat` ausführen. macOS/Linux: `bash start.sh`.
|
| 23 |
+
3. Browser: **http://127.0.0.1:8000**.
|
| 24 |
+
4. `Studio` → eigene Musik laden oder **Demo-Sound laden**.
|
| 25 |
+
5. Sidebar: **Arrangement** → **Mini-KI analysieren**.
|
| 26 |
+
6. Automatische *Klangtextur-Hypothesen* prüfen, ändern und **Plan speichern**.
|
| 27 |
+
7. **Separation starten**: HPSS (harmonisch/perkussiv/Residuum) ist sofort verfügbar;
|
| 28 |
+
Demucs nur mit separat zugänglichen lokalen Gewichten und Neural Dependencies.
|
| 29 |
+
8. Im Arrangement vorhandene Stems durch **M** (Mute), **S** (Solo), Gain, Stereo-
|
| 30 |
+
Panorama, Effekte bearbeiten. Oben die farbige Mixübersicht und Timeline nutzen.
|
| 31 |
+
9. **Mix berechnen** → **Mix anhören** → **WAV exportieren**.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
+
**Beispiel direkt starten, ohne Startskript:**
|
| 34 |
```bash
|
| 35 |
python -m venv .venv
|
| 36 |
+
# Linux/macOS: source .venv/bin/activate
|
| 37 |
+
# Windows PowerShell: .venv\Scripts\Activate.ps1
|
|
|
|
|
|
|
|
|
|
| 38 |
python -m pip install -e ".[dev]"
|
|
|
|
| 39 |
python -m pytest -q
|
| 40 |
python -m uvicorn app.server:app --host 127.0.0.1 --port 8000
|
| 41 |
```
|
| 42 |
|
| 43 |
+
### Neue Funktionen
|
| 44 |
+
|
| 45 |
+
- Mehrspur-Arrangement mit einzelnen Instrumenten-/Signalstems je nach verfügbarem Modell.
|
| 46 |
+
- Jedes *tatsächlich* verfügbare Audio-Stem erhält eigene Farbe und samplebasierte
|
| 47 |
+
Waveform-Visualisierung, links Lautstärke/Mute/Solo, mittig L/C/R-Pan, rechts
|
| 48 |
+
ausklappbare Effekte (Low-Cut, High-Cut, Sättigung, Stereobreite).
|
| 49 |
+
- Farbig überlagerte Gesamtübersicht, klickbare Zeitleiste und Scroll/Zoom.
|
| 50 |
+
- **OMEGA-TAG Mini**: Offline-MLP (35 Features → 32 tanh Neuronen → 6 Sigmoid-Ausgaben).
|
| 51 |
+
Mitgeliefertes `.npz`-Checkpoint wurde zweistufig auf **synthetischen Signalen**
|
| 52 |
+
trainiert und anschließend auf **synthetischen Mischungen feinjustiert**.
|
| 53 |
+
Es erkennt *nur* Klangtexturen: Bass-ähnlich, Kick-ähnlich, Snare-ähnlich,
|
| 54 |
+
Hi-Hat-ähnlich, harmonische Mitten und rauschähnliche Anteile.
|
| 55 |
+
**Keine trainierte oder validierte Instrumentenerkennung auf echter Musik.**
|
| 56 |
+
- Editable Trennziele (bis 128 aus Ressourcen-/Sicherheitsgründen).
|
| 57 |
+
Das Speichern eines Ziels separiert **keine** zusätzliche Audiospur.
|
| 58 |
+
- Nichtdestruktiver, chunkweiser Stereo-Float32-Mix mit Gain, Mute, Solo,
|
| 59 |
+
Panorama, Hoch-/Tiefpass, Stereo Width und harmonischer Sättigung.
|
| 60 |
+
- Optional von 50–200 % unabhängiges Tempo und ±12 Halbtöne transponieren
|
| 61 |
+
mittels **FFmpeg mit Rubber Band Filter**.
|
| 62 |
+
Der Button wird ohne Rubber Band deaktiviert, nicht simuliert.
|
| 63 |
+
- WAV-Float32-Export und messbarer Pegelbericht einschließlich möglicher
|
| 64 |
+
Überschreitung von 0 dBFS.
|
| 65 |
+
|
| 66 |
+
### Integritätsregeln
|
| 67 |
+
|
| 68 |
+
- Original wird niemals in-place überschrieben. Quellen und Export werden
|
| 69 |
+
in getrennten Projektordnern gespeichert.
|
| 70 |
+
- Kein Eingriff und kein Sound Processing ohne explizites **Mix berechnen**.
|
| 71 |
+
- Gespeicherte KI-Trennplan-Hypothesen sind ausdrücklich nicht als isolierte
|
| 72 |
+
Instrumentenspuren bezeichnet.
|
| 73 |
+
- HPSS ist **kein Instrumentenerkennungsmodell**, sondern strukturelle Trennung.
|
| 74 |
+
Demucs v4 ist optional und bietet vier Grobkategorien; es zerlegt nicht beliebig
|
| 75 |
+
viele benannte Instrumente.
|
| 76 |
+
- Waveforms werden für rasche Anzeige sparsam gesampelt; sie sind **keine**
|
| 77 |
+
vollständige Peak- oder Forensikmessung.
|
| 78 |
+
- Synthetisch generierte Oberwellen, Tontranspositionen und FX sind
|
| 79 |
+
Klangänderungen, **keine** Rekonstruktion physisch nachweisbarer fehlender Daten.
|
| 80 |
+
- Kein automatisches Mastering, kein pauschales Denoising oder 0-dB-Normalisieren.
|
| 81 |
+
|
| 82 |
+
### Tooling und Deployment
|
| 83 |
+
|
| 84 |
+
- Python / FastAPI / NumPy / SciPy / SoundFile.
|
| 85 |
+
- Frontend: eigenständiges HTML/CSS/JavaScript, kein CDN, keine fremde Cloud.
|
| 86 |
+
- Startet als lokaler Browser-Webserver; optional Docker Compose (nicht
|
| 87 |
+
als produktionsbereite Public-Cloud-Anwendung absichern).
|
| 88 |
+
- FFmpeg ist für Grundfunktionen nicht erforderlich, für spezielle Dateiformate,
|
| 89 |
+
Virtual Bass und unabhängige Pitch/Tempo-Transformation hingegen erforderlich.
|
| 90 |
+
- `start.sh`/`.bat` installieren Python-Abhängigkeiten über pip und benötigen bei
|
| 91 |
+
Erstinstallation Netzwerkzugang; die Anwendung selbst ruft danach keine
|
| 92 |
+
externen Server auf.
|
| 93 |
+
- Keine Benutzeranmeldung, keine öffentliche Mehrnutzer-Bereitstellung.
|
| 94 |
+
- Datenspeicherung in `omega_data/`, falls nicht über `ABSOLUTION_DATA_DIR` geändert.
|
| 95 |
+
|
| 96 |
+
### Tests
|
| 97 |
|
| 98 |
```bash
|
| 99 |
+
python -m pip install -e ".[dev]"
|
| 100 |
+
python -m pytest -q
|
| 101 |
+
node --check app/static/app.js
|
| 102 |
+
node --check app/static/arrangement.js
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
```
|
| 104 |
|
| 105 |
+
Neue Tests: neutrale Summierung, Solo/Mute, Panorama, FX, Wellenform-API,
|
| 106 |
+
synthetisches Mini-Modell, Plan-Persistenz, tatsächliche Mix-Jobs und WAV-Export.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
|
| 108 |
+
### Neue API
|
|
|
|
|
|
|
| 109 |
|
| 110 |
+
```
|
| 111 |
+
POST /api/v1/projects/{id}/inventory Mini-Tagging, synchron (lokal)
|
| 112 |
+
PUT /api/v1/projects/{id}/plan editierbare Zielhypothesen
|
| 113 |
+
GET /api/v1/projects/{id}/wave/{stem} sparsames Wellenform-Sampling
|
| 114 |
+
POST /api/v1/jobs/mix Offline-Mix-Job
|
| 115 |
+
GET /api/v1/jobs/{job_id} Fortschritt
|
| 116 |
+
GET /api/v1/projects/{id}/mixer Mix-Report und gespeicherte Parameter
|
| 117 |
+
GET /api/v1/projects/{id}/mixer/audio WAV-Export
|
| 118 |
+
```
|
| 119 |
|
| 120 |
+
Request-Body für Mix-Jobs:
|
| 121 |
+
```json
|
| 122 |
+
{
|
| 123 |
+
"project_id": "<PROJECT_UUID>",
|
| 124 |
+
"tracks": {
|
| 125 |
+
"harmonic": {"gain_db": -2.0, "pan": -0.2, "mute": false, "solo": false,
|
| 126 |
+
"highpass_hz": 25, "lowpass_hz": 0, "drive": 0.1, "width": 1.0}
|
| 127 |
+
},
|
| 128 |
+
"tempo": 1.0,
|
| 129 |
+
"pitch_semitones": 0
|
| 130 |
+
}
|
| 131 |
+
```
|
| 132 |
+
Nicht spezifizierte Stems sind ohne Effekte und bei 0 dB enthalten. Solo-Modus
|
| 133 |
+
spielt ausschließlich Solo-markierte, nicht stumm geschaltete Stems.
|
| 134 |
|
| 135 |
+
### Forschungsstatus
|
| 136 |
|
| 137 |
+
Weitere getrennte Instrumente benötigen leistungsfähige bedingte oder
|
| 138 |
+
hierarchische KI-Separatoren plus realistisch evaluiertes Modellrouting.
|
| 139 |
+
Das integrierte Mini-Modell ist hierfür nur eine Vorinventur, kein universelles
|
| 140 |
+
Separationsmodell. Das Projekt bleibt eine lokale Forschungs-/Prototyp-Version.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
|
| 142 |
+
Weitere Details: `docs/ARRANGEMENT_STUDIO.md` sowie das historische
|
| 143 |
+
NOISE-/BASS-CORE-Material unten.
|
|
|
|
| 144 |
|
| 145 |
+
---
|
| 146 |
|
| 147 |
+
# ABSOLUTION Ω — v0.4.0 · NOISE-CORE + BASS-CORE
|
| 148 |
|
| 149 |
+
> Local-first audio-forensics workbench with BASS-CORE (experimental DSP-derived kick/bassline
|
| 150 |
+
> estimates, non-destructive bass processing and optional use of pre-separated HPSS/Demucs stems).
|
| 151 |
+
|
| 152 |
+
## Starten
|
| 153 |
+
|
| 154 |
+
1. Das ZIP entpacken.
|
| 155 |
+
2. `start_windows.bat` (Windows) oder `bash start.sh` (macOS/Linux) im Projektordner starten.
|
| 156 |
+
3. `http://127.0.0.1:8000` im Browser öffnen.
|
| 157 |
+
4. Unter **Studio** WAV/FLAC/AIFF/OGG/unterstütztes MP3 importieren oder Demo laden.
|
| 158 |
+
5. Den Bereich **BASS-CORE** öffnen, Preset/Regler wählen und **Bass analysieren & optimieren** drücken.
|
| 159 |
+
6. **Bassband vorher/nachher**, Kick-/Bassline-Schätzung, erzeugte Obertöne und Vollmix anhören.
|
| 160 |
+
7. Einzel-WAVs oder **Alle Bass-Tracks herunterladen** (ZIP) exportieren.
|
| 161 |
+
|
| 162 |
+
Mit vorhandenem HPSS-Ergebnis kann BASS-CORE die harmonischen/perkussiven Stems als
|
| 163 |
+
Quellenhypothese verwenden. Bei korrekt konfiguriertem Demucs und vorab generierten
|
| 164 |
+
`bass`/`drums`-Stems nutzt die Engine diese als Ausgangspunkt. Ein manueller Modus
|
| 165 |
+
erzwingt entsprechende Quellen und wird mit HTTP 409 abgelehnt, falls sie fehlen.
|
| 166 |
+
|
| 167 |
+
## Neu: NOISE-CORE Ω — PRESERVE FIRST (v0.4)
|
| 168 |
+
|
| 169 |
+
**Hauptregel:** Erhaltung von Musik, Luft, Hall, feinen Transienten und dem
|
| 170 |
+
Original hat Vorrang vor der Störminderung. Es gibt **keine Garantie**,
|
| 171 |
+
dass eine Reparatur bei Überlagerungen ausschließlich Störgeräusche ändert.
|
| 172 |
+
Daher setzt diese Version die Reparatur nicht automatisch ein.
|
| 173 |
+
|
| 174 |
+
**Bedienung**
|
| 175 |
+
|
| 176 |
+
1. Importiere eine Audiodatei im Studio.
|
| 177 |
+
2. Öffne **NOISE-CORE** und wähle **Störspur analysieren**.
|
| 178 |
+
3. Überprüfe einzelne Klick-Verdachtsfälle durch Anhören des Originals.
|
| 179 |
+
Kein Ereignis ist vorab ausgewählt; die Klick-Erkennung ist nur eine
|
| 180 |
+
Heuristik, **kein KI-Detektor** und kein Beweis für eine Störung.
|
| 181 |
+
4. Wähle einzelne geprüfte Ereignisse und die Reparaturstärke aus.
|
| 182 |
+
5. Bestätige die Reparatur. Es werden **nur die ausgewählten einzelnen
|
| 183 |
+
Samples** interpoliert; keine sonstigen Samples gezielt verändert.
|
| 184 |
+
6. Höre **Clean** und insbesondere **Differenzspur** an und exportiere
|
| 185 |
+
beide als WAV 32-bit Float plus JSON-Bericht.
|
| 186 |
+
|
| 187 |
+
Die Differenzspur ist exakt als `Original - Clean` berechnet (vor
|
| 188 |
+
Float32-Dateiquantisierung). Sie kann echte musikalische Inhalte enthalten.
|
| 189 |
+
Ein kleiner numerischer Rekonstruktionsfehler beweist **nicht**, dass die
|
| 190 |
+
Veränderung hörpsychologisch unbedenklich ist.
|
| 191 |
+
|
| 192 |
+
**Was absichtlich NICHT automatisiert ist**
|
| 193 |
+
|
| 194 |
+
- Keine pauschale Broadband-Noise-Reduction und kein Spectral-Gate.
|
| 195 |
+
- Keine 50/60-Hz-Notches ohne Prüfung, da Bassnoten oder Obertöne betroffen sein können.
|
| 196 |
+
- Keine generative Resynthese verlorener Musik.
|
| 197 |
+
- Keine selbständige Klassifikation als „sicheres Störgeräusch“.
|
| 198 |
+
- Keine angebliche KI-Qualität, wo nur Heuristiken vorliegen.
|
| 199 |
+
|
| 200 |
+
Tonal-Indikatoren bei 50/60/100/120 Hz sind ausschließlich **mehrdeutige
|
| 201 |
+
Spektralspitzen**, die ohne automatischen Eingriff angezeigt werden.
|
| 202 |
+
Ein Scan unterstützt auch Audiodateien von mehr als 180 Sekunden; RAM
|
| 203 |
+
bleibt durch blockweise Verarbeitung begrenzt. Die Dateigrößen-
|
| 204 |
+
und Speicherplatzgrenzen bleiben bestehen.
|
| 205 |
+
|
| 206 |
+
**API:**
|
| 207 |
+
|
| 208 |
+
- `POST /api/v1/jobs/noise/scan` mit `{"project_id": "[UUID]"}`;
|
| 209 |
+
- `POST /api/v1/jobs/noise/repair` mit `{"project_id":"[UUID]", "approved_samples":[4321], "strength":0.8}`;
|
| 210 |
+
- `GET /api/v1/projects/{id}/noise` für Scan/Repair-Bericht;
|
| 211 |
+
- `GET /api/v1/projects/{id}/noise/audio/{clean|difference}`;
|
| 212 |
+
- `GET /api/v1/projects/{id}/noise/export`.
|
| 213 |
+
|
| 214 |
+
## Neu: Kdenlive-kompatibler Virtual-Bass-Export (optional)
|
| 215 |
+
|
| 216 |
+
BASS-CORE bietet einen **separaten FFmpeg-Virtualbass-Adapter** (nur falls
|
| 217 |
+
`ffmpeg` mit Filter `virtualbass` lokal verfügbar ist). Dieser Filter
|
| 218 |
+
konvertiert **2-Kanal-Stereo → 2.1**. Die ursprünglichen Stereo-Kanäle werden
|
| 219 |
+
vom Filter unverändert weitergegeben; der dritte Kanal ist ein künstlich
|
| 220 |
+
generierter LFE-Kanal. Ein neuer Bass-Ton wird **nicht zurückgewonnen**.
|
| 221 |
+
|
| 222 |
+
Wähle in BASS-CORE `Cutoff` 100–500 Hz, `Strength` 0.5–3, starte den Export
|
| 223 |
+
und lade `ABSOLUTION_VIRTUAL_BASS_2_1.wav` herunter (WAV Float32).
|
| 224 |
+
Nur für echte Stereoquellen. Eine echte 2.1-Wiedergabekette wird empfohlen;
|
| 225 |
+
Browser-Audio unterstützt dreikanalige WAV-Dateien nicht zuverlässig.
|
| 226 |
+
Die LFE-Amplitude kann 0 dBFS überschreiten und muss im Zielsystem geprüft werden.
|
| 227 |
+
|
| 228 |
+
Offizielle Filterbeschreibung: https://ffmpeg.org/ffmpeg-filters.html#virtualbass
|
| 229 |
+
|
| 230 |
+
**API:**
|
| 231 |
+
|
| 232 |
+
- `POST /api/v1/jobs/bass/virtual` (`project_id`, `cutoff_hz`, `strength`);
|
| 233 |
+
- `GET /api/v1/projects/{id}/virtualbass`;
|
| 234 |
+
- `GET /api/v1/projects/{id}/virtualbass/audio` (2.1-WAV).
|
| 235 |
+
|
| 236 |
+
### Warum keine Normalisierung auf −0,01 dB vor Analyse/Trennung?
|
| 237 |
+
|
| 238 |
+
Weil Verstärkung keine fehlende Information wiederherstellt und spätere
|
| 239 |
+
Bearbeitung bei nahezu Vollaussteuerung leichter übersteuert. Originalpegel
|
| 240 |
+
unverändert halten; falls ein Modell Normalisierung braucht, nur reversible
|
| 241 |
+
temporäre Kopien mit dokumentiertem Verstärkungsfaktor verwenden.
|
| 242 |
+
Output-True-Peak-Messung nach der Bearbeitung, nicht aggressives
|
| 243 |
+
Pre-Normalizing. **−0,01 dBFS Sample-Peak ist keine Garantie für
|
| 244 |
+
−0,01 dBTP (True Peak).**
|
| 245 |
+
|
| 246 |
+
## Verarbeitung: BASS-CORE v0.3
|
| 247 |
+
|
| 248 |
+
- **DSP-Modus:** 45–350-Hz Tiefband mittels Zero-Phase-Crossover. Ein
|
| 249 |
+
transientenbasierter Maskierungsansatz schätzt Kick vs. Bassline.
|
| 250 |
+
Dies ist **keine** unabhängige Instrumentenquellentrennung.
|
| 251 |
+
- **HPSS-Modus:** Tiefband der vorab separierten `percussive`- und `harmonic`-Spuren.
|
| 252 |
+
Harmonische Instrumente außer Bass und tiefe Schlagzeuganteile können überlappen.
|
| 253 |
+
- **Demucs-Modus:** Tiefband der vorab geschätzten `drums`- und `bass`-Spuren.
|
| 254 |
+
Erfordert lokale Demucs-Gewichte und erfolgreiche Separation; automatische Downloads AUS.
|
| 255 |
+
- **Processing:** Pegelregler für Kick/Bassline, Bass-Subgain, Rumpelfilter,
|
| 256 |
+
symmetrische nichtlineare Obertongenerierung, Stereo-zu-Mono unter Grenzfrequenz,
|
| 257 |
+
Dry/Wet-Mischung.
|
| 258 |
+
- **Output-Ceiling:** nach dem Rendern wird *der optimierte Mix* bei Bedarf
|
| 259 |
+
global abgesenkt. Das ist **kein True-Peak-Limiter**. Einzelstems bleiben
|
| 260 |
+
unverändert und dürfen Peaks > 0 dBFS enthalten (WAV 32-bit Float).
|
| 261 |
+
- **Export:** `bass_band`, `kick_estimate`, `bassline_estimate`, `other_unprocessed`,
|
| 262 |
+
`harmonics_added`, `bass_optimized`, `mix_optimized`, jeweils WAV Float32 plus
|
| 263 |
+
separate PCM16-Hörvorschauen. ZIP enthält `bass_report.json`.
|
| 264 |
+
- **Consistency:** Die Zerlegung `kick_estimate + bassline_estimate +
|
| 265 |
+
other_unprocessed` entspricht dem eingelesenen Mix innerhalb einer numerischen
|
| 266 |
+
Toleranz. Das beweist nicht die semantische Reinheit.
|
| 267 |
+
|
| 268 |
+
Der Inspector zeigt Energien für Frequenzbänder von 20–1280 Hz aus dem ersten
|
| 269 |
+
Audio-Chunk. Er stellt keine Tonhöhen oder einzelnen Instrumente fest.
|
| 270 |
+
|
| 271 |
+
## Grenzen und Sicherheit
|
| 272 |
+
|
| 273 |
+
- Originaldateien bleiben unverändert gespeichert, inklusive SHA-256.
|
| 274 |
+
- Keine feste 180-Sekunden-Grenze. Maximalgröße standardmäßig 1024 MiB
|
| 275 |
+
(konfigurierbar über `ABSOLUTION_MAX_UPLOAD_MIB` bis 4096).
|
| 276 |
+
- Chunkweise/offline Verarbeitung vermindert, **eliminiert aber nicht** mögliche
|
| 277 |
+
Artefakte an Blockgrenzen. Sie kann erhebliche Diskkapazität erfordern
|
| 278 |
+
(sieben Float32-WAVs plus Vorschauen).
|
| 279 |
+
- Kein echtes Deep-Learning für die DSP-Schätzung. Keine Noten-/F0-Reparatur,
|
| 280 |
+
keine intelligenten Sub-Oszillatoren, kein echtes De-Clip, kein vollautomatisches KI-De-Noise, kein Echtzeit-Audio,
|
| 281 |
+
kein VST3-/AU-Hosting in v0.3. Diese Funktionen sind auf der Roadmap.
|
| 282 |
+
- Nicht für öffentliche Mehrbenutzer-Deployments geeignet:
|
| 283 |
+
Benutzeranmeldung, Job-Persistenz, Rate Limiting und Plugin-Sandbox fehlen.
|
| 284 |
+
- Keine Telemetrie und keine externen Modell-Downloads durch diese Anwendung.
|
| 285 |
+
- Für optionale Bibliotheken wie Demucs, Pedalboard/Surge XT und kommerzielle
|
| 286 |
+
VST-Plugins gelten jeweils eigene Lizenz-/Checkpoints-/Nutzungsbedingungen.
|
| 287 |
+
|
| 288 |
+
## Entwickler: API und Tests
|
| 289 |
|
| 290 |
```bash
|
| 291 |
+
python -m venv .venv
|
| 292 |
+
# Linux/macOS:
|
| 293 |
+
source .venv/bin/activate
|
| 294 |
+
# Windows PowerShell:
|
| 295 |
+
# .venv\\Scripts\\Activate.ps1
|
| 296 |
+
pip install -e ".[dev]"
|
| 297 |
python -m pytest -q
|
| 298 |
+
python -m uvicorn app.server:app --host 127.0.0.1 --port 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 299 |
```
|
| 300 |
|
| 301 |
+
### Wichtige API-Pfade
|
| 302 |
|
| 303 |
+
| HTTP | Pfad | Beschreibung |
|
| 304 |
+
|---|---|---|
|
| 305 |
+
| POST | `/api/v1/projects` | Projekt anlegen |
|
| 306 |
+
| POST | `/api/v1/assets` | WAV/FLAC/etc. importieren |
|
| 307 |
+
| POST | `/api/v1/jobs/separate` | HPSS oder optional Demucs |
|
| 308 |
+
| POST | `/api/v1/jobs/bass` | Neuer BASS-CORE-Job |
|
| 309 |
+
| GET | `/api/v1/jobs/{job_id}` | Status/Fortschritt |
|
| 310 |
+
| GET | `/api/v1/projects/{id}/bass` | Quelle, Report, Outputs |
|
| 311 |
+
| GET | `/api/v1/projects/{id}/bass/audio/{track}` | Master; `?preview=true` für Player |
|
| 312 |
+
| GET | `/api/v1/projects/{id}/bass/export` | ZIP aller Bass-Stems |
|
| 313 |
+
| GET | `/docs` | Interaktive OpenAPI-Dokumentation |
|
| 314 |
+
|
| 315 |
+
Beispiel-JSON für `/api/v1/jobs/bass`:
|
| 316 |
+
|
| 317 |
+
```json
|
| 318 |
+
{
|
| 319 |
+
"project_id": "[UUID-AUS-DER-PROJEKT-ANLAGE]",
|
| 320 |
+
"source_mode": "auto",
|
| 321 |
+
"crossover_hz": 220,
|
| 322 |
+
"kick_focus": 0.75,
|
| 323 |
+
"kick_gain_db": 2.0,
|
| 324 |
+
"bass_gain_db": 1.0,
|
| 325 |
+
"sub_gain_db": 1.5,
|
| 326 |
+
"harmonics": 0.35,
|
| 327 |
+
"lowcut_hz": 22,
|
| 328 |
+
"mono_below_hz": 100,
|
| 329 |
+
"wet": 1.0,
|
| 330 |
+
"ceiling_dbfs": -1.0
|
| 331 |
+
}
|
| 332 |
+
```
|
| 333 |
|
| 334 |
+
## KI-Roadmap nach Erhaltungs-Priorität
|
| 335 |
+
|
| 336 |
+
1. **AI Noise Event Triage:** Click-vs-Instrumenten-Transient-Klassifikator
|
| 337 |
+
auf echten musikalischen Negativbeispielen, mit Unsicherheits-Gating/
|
| 338 |
+
Abstention; keine automatische Massenreparatur.
|
| 339 |
+
2. **Source-aware Noise:** Zwischen Bass, Schlagzeug, Stimmen und Rest
|
| 340 |
+
separieren; Störhypothese gezielt im betreffenden Stem prüfen.
|
| 341 |
+
3. **Harmonic Preservation:** Zeit-Frequenz-Masken mit Erhaltung von
|
| 342 |
+
Noten, Harmonischen, Atemgeräuschen, Hallfahnen und Transienten.
|
| 343 |
+
Nicht sicher unterscheidbare Energie bleibt im Original.
|
| 344 |
+
4. **Independent Repair Judge:** Automatische Vorher-/Nachher-Prüfung,
|
| 345 |
+
Difference-Stem, Nulltests, Blindhörtest und Leckage-/Transientmetriken.
|
| 346 |
+
5. Echte Bass-/Drum-Separation durch modellbasierte Quellenzerlegung und
|
| 347 |
+
mehrstufige Kick-/Bassline-/808-Klassifikation.
|
| 348 |
+
6. Semantischer Low-End-Eventgraph mit validiertem F0- und Transienten-Tracking.
|
| 349 |
+
7. Optionaler phase-/pitch-locked Sub-Synthesizer unter Unsicherheits-Gating.
|
| 350 |
+
8. Selektive Event-Reparatur (z. B. Clicks und Dropouts) mit Provenance.
|
| 351 |
+
9. Geschützter, separat betriebener VST3-/AU-Host und kommerzielle Lizenzprüfung;
|
| 352 |
+
externe Plugins dürfen niemals ungeprüft im API-Prozess laufen.
|
| 353 |
+
10. True-Peak-Meter/Limiter, Oversampling, A/B-Loudness-Matching, Listening Benchmarks
|
| 354 |
+
und getrennte quantitative Benchmarks mit Ground Truth.
|
| 355 |
+
|
| 356 |
+
Alle Forschungsstufen sind noch nicht implementiert. Eine mathematisch
|
| 357 |
+
saubere Restmischung ist nicht gleichbedeutend mit perfekten Original-Stems.
|
| 358 |
+
|
| 359 |
+
## Weitere Dokumentation
|
| 360 |
+
|
| 361 |
+
Siehe `docs/ARCHITECTURE.md`, `docs/LICENSE_AND_SECURITY.md`, `docs/WEBSITE.md`.
|
| 362 |
+
|
| 363 |
+
## Dokumentation NOISE-CORE
|
| 364 |
+
|
| 365 |
+
Siehe `docs/NOISE_CORE_DESIGN.md` für Schutzprinzipien, Grenzen und Teststrategie.
|
app/bass.py
ADDED
|
@@ -0,0 +1,284 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""BASS-CORE Ω: local, deterministic, non-destructive low-frequency laboratory.
|
| 2 |
+
|
| 3 |
+
No semantic separation or restoration of absent information is claimed.
|
| 4 |
+
- DSP mode: transient-gated sub-band approximation.
|
| 5 |
+
- HPSS mode: HPSS-derived sub-band estimates.
|
| 6 |
+
- Demucs mode: licensed/precomputed bass and drums stems.
|
| 7 |
+
All modes retain a mathematically explicit unprocessed remainder.
|
| 8 |
+
"""
|
| 9 |
+
from __future__ import annotations
|
| 10 |
+
|
| 11 |
+
import math
|
| 12 |
+
from contextlib import ExitStack
|
| 13 |
+
from dataclasses import asdict, dataclass
|
| 14 |
+
from pathlib import Path
|
| 15 |
+
from typing import Callable
|
| 16 |
+
|
| 17 |
+
import numpy as np
|
| 18 |
+
import soundfile as sf
|
| 19 |
+
from scipy.ndimage import uniform_filter1d
|
| 20 |
+
from scipy.integrate import trapezoid
|
| 21 |
+
from scipy.signal import butter, sosfiltfilt, welch
|
| 22 |
+
|
| 23 |
+
from .audio import AudioError, audio_info
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
@dataclass(frozen=True)
|
| 27 |
+
class BassParams:
|
| 28 |
+
crossover_hz: float = 220.0
|
| 29 |
+
kick_focus: float = 0.75
|
| 30 |
+
kick_gain_db: float = 0.0
|
| 31 |
+
bass_gain_db: float = 0.0
|
| 32 |
+
sub_gain_db: float = 0.0
|
| 33 |
+
harmonics: float = 0.20
|
| 34 |
+
lowcut_hz: float = 22.0
|
| 35 |
+
mono_below_hz: float = 100.0
|
| 36 |
+
wet: float = 1.0
|
| 37 |
+
ceiling_dbfs: float = -1.0
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
TRACKS = {
|
| 41 |
+
"bass_band": "Original low-frequency estimate",
|
| 42 |
+
"kick_estimate": "Low-frequency kick hypothesis (not instrument truth)",
|
| 43 |
+
"bassline_estimate": "Low-frequency bassline hypothesis (not instrument truth)",
|
| 44 |
+
"other_unprocessed": "Original minus estimated bass band",
|
| 45 |
+
"harmonics_added": "Synthesized harmonics only (not recovered information)",
|
| 46 |
+
"bass_optimized": "Edited low-frequency estimate",
|
| 47 |
+
"mix_optimized": "Reconstructed mix, with global ceiling gain",
|
| 48 |
+
}
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
def _lp(signal: np.ndarray, sr: int, hz: float, order: int = 4) -> np.ndarray:
|
| 52 |
+
hz = max(4.0, min(float(hz), sr * .46))
|
| 53 |
+
return sosfiltfilt(butter(order, hz, btype="low", fs=sr, output="sos"), signal, axis=0)
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
def _hp(signal: np.ndarray, sr: int, hz: float, order: int = 3) -> np.ndarray:
|
| 57 |
+
hz = max(4.0, min(float(hz), sr * .46))
|
| 58 |
+
return sosfiltfilt(butter(order, hz, btype="high", fs=sr, output="sos"), signal, axis=0)
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def _level(samples: np.ndarray) -> dict:
|
| 62 |
+
peak = float(np.max(np.abs(samples))) if samples.size else 0.0
|
| 63 |
+
rms = float(np.sqrt(np.mean(np.square(samples)))) if samples.size else 0.0
|
| 64 |
+
return {"peak_dbfs": round(20 * math.log10(max(peak, 1e-12)), 3),
|
| 65 |
+
"rms_dbfs": round(20 * math.log10(max(rms, 1e-12)), 3)}
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def _kick_mask(low: np.ndarray, sr: int, amount: float) -> np.ndarray:
|
| 69 |
+
"""Transient emphasis, NOT an instrument classifier."""
|
| 70 |
+
mono = np.mean(low, axis=1)
|
| 71 |
+
energy = np.square(mono)
|
| 72 |
+
fast = np.sqrt(np.maximum(0, uniform_filter1d(energy, size=max(3, int(sr*.008)))))
|
| 73 |
+
slow = np.sqrt(np.maximum(0, uniform_filter1d(energy, size=max(7, int(sr*.110)))))
|
| 74 |
+
ratio = np.maximum(0.0, fast / np.maximum(slow, 1e-5) - 0.96)
|
| 75 |
+
transients = np.clip(ratio * 1.15, 0.0, 1.0)
|
| 76 |
+
# Smooth short spikes; use context to avoid abrupt gates.
|
| 77 |
+
activation = uniform_filter1d(transients, size=max(3, int(sr*.024)))
|
| 78 |
+
return np.clip(activation * amount, 0, 1)[:, None]
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
def _transform(samples: np.ndarray, sr: int, cfg: BassParams,
|
| 82 |
+
mode: str, harmonic=None, percussive=None, bass=None, drums=None) -> dict[str, np.ndarray]:
|
| 83 |
+
if mode == "demucs":
|
| 84 |
+
if bass is None or drums is None:
|
| 85 |
+
raise AudioError("Demucs bass and drums stems are required.")
|
| 86 |
+
kick = _lp(drums, sr, cfg.crossover_hz)
|
| 87 |
+
bassline = _lp(bass, sr, cfg.crossover_hz)
|
| 88 |
+
band = kick + bassline
|
| 89 |
+
elif mode == "hpss":
|
| 90 |
+
if harmonic is None or percussive is None:
|
| 91 |
+
raise AudioError("HPSS harmonic and percussive stems are required.")
|
| 92 |
+
kick = _lp(percussive, sr, cfg.crossover_hz)
|
| 93 |
+
bassline = _lp(harmonic, sr, cfg.crossover_hz)
|
| 94 |
+
band = kick + bassline
|
| 95 |
+
else:
|
| 96 |
+
band = _lp(samples, sr, cfg.crossover_hz)
|
| 97 |
+
mask = _kick_mask(band, sr, cfg.kick_focus)
|
| 98 |
+
kick = band * mask
|
| 99 |
+
bassline = band - kick
|
| 100 |
+
|
| 101 |
+
other = samples - band
|
| 102 |
+
# A DC/sub-rumble cut is a *change* to the original, never hidden.
|
| 103 |
+
edited_kick = _hp(kick, sr, cfg.lowcut_hz) * 10 ** (cfg.kick_gain_db / 20)
|
| 104 |
+
edited_line = _hp(bassline, sr, cfg.lowcut_hz) * 10 ** (cfg.bass_gain_db / 20)
|
| 105 |
+
if abs(cfg.sub_gain_db) > 1e-8:
|
| 106 |
+
low_sub = _lp(edited_line, sr, min(65.0, cfg.crossover_hz*.65))
|
| 107 |
+
edited_line = edited_line + low_sub * (10 ** (cfg.sub_gain_db/20) - 1)
|
| 108 |
+
# Odd harmonic synthesis through symmetric soft saturation.
|
| 109 |
+
drive = np.clip(edited_line * 3.5, -12, 12)
|
| 110 |
+
synthesized = np.tanh(drive) - drive
|
| 111 |
+
synthesized = _hp(synthesized, sr, min(100.0, cfg.crossover_hz * .6))
|
| 112 |
+
synthesized = _lp(synthesized, sr, min(1500.0, sr*.42))
|
| 113 |
+
synthesized *= cfg.harmonics * .6
|
| 114 |
+
optimized = edited_kick + edited_line + synthesized
|
| 115 |
+
if samples.shape[1] == 2 and cfg.mono_below_hz > 0:
|
| 116 |
+
centered_low = _lp(optimized, sr, cfg.mono_below_hz)
|
| 117 |
+
optimized = optimized - centered_low + np.mean(centered_low, axis=1, keepdims=True)
|
| 118 |
+
optimized = cfg.wet * optimized + (1-cfg.wet) * band
|
| 119 |
+
mix = other + optimized
|
| 120 |
+
return {
|
| 121 |
+
"bass_band": band, "kick_estimate": kick,
|
| 122 |
+
"bassline_estimate": bassline, "other_unprocessed": other,
|
| 123 |
+
"harmonics_added": synthesized * cfg.wet,
|
| 124 |
+
"bass_optimized": optimized, "mix_optimized": mix,
|
| 125 |
+
}
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
def _bands(signal: np.ndarray, sr: int) -> list[dict]:
|
| 129 |
+
mono = np.mean(signal, axis=1)
|
| 130 |
+
n = min(8192, len(mono))
|
| 131 |
+
frequencies, power = welch(mono, fs=sr, nperseg=n, noverlap=n//2)
|
| 132 |
+
output = []
|
| 133 |
+
for lower, upper in [(20,40), (40,80), (80,160), (160,320), (320,640), (640,1280)]:
|
| 134 |
+
selection = (frequencies >= lower) & (frequencies < upper)
|
| 135 |
+
energy = float(trapezoid(power[selection], frequencies[selection])) if np.count_nonzero(selection) >= 2 else 0
|
| 136 |
+
output.append({"range_hz": [lower,upper], "estimated_rms_dbfs": round(
|
| 137 |
+
10 * math.log10(max(energy, 1e-24)), 2)})
|
| 138 |
+
return output
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def process_bass_file(input_path: Path, output_dir: Path, cfg: BassParams,
|
| 142 |
+
mode: str = "dsp", refs: dict[str, Path] | None = None,
|
| 143 |
+
progress: Callable[[float], None] | None = None,
|
| 144 |
+
chunk_frames: int = 262144,
|
| 145 |
+
context_frames: int | None = None) -> tuple[dict, dict]:
|
| 146 |
+
"""Bounded-memory offline editing; symmetric context reduces boundary artifacts.
|
| 147 |
+
|
| 148 |
+
Stems are WAV 32-bit float. Preview copies are PCM16 for browser playback.
|
| 149 |
+
A final global ceiling gain is applied to optimized MIX only.
|
| 150 |
+
"""
|
| 151 |
+
info = audio_info(input_path)
|
| 152 |
+
if mode not in ("dsp","hpss","demucs"):
|
| 153 |
+
raise AudioError("Unknown bass extraction mode.")
|
| 154 |
+
if not (45 <= cfg.crossover_hz <= min(350.0, info.samplerate*.42)):
|
| 155 |
+
raise AudioError("Crossover must be between 45 and 350 Hz.")
|
| 156 |
+
if context_frames is None:
|
| 157 |
+
context_frames = max(8192, int(info.samplerate * .32))
|
| 158 |
+
if chunk_frames < 4096 or context_frames < 1024:
|
| 159 |
+
raise AudioError("Processing chunks/context too small.")
|
| 160 |
+
required = {"hpss":("harmonic","percussive"),"demucs":("bass","drums"),"dsp":()}[mode]
|
| 161 |
+
refs = refs or {}
|
| 162 |
+
for name in required:
|
| 163 |
+
if name not in refs:
|
| 164 |
+
raise AudioError(f"Missing reference stem: {name}")
|
| 165 |
+
ref = audio_info(refs[name])
|
| 166 |
+
if ref.samplerate != info.samplerate or ref.frames != info.frames or ref.channels != info.channels:
|
| 167 |
+
raise AudioError("Stem must match source sample rate, length and channels.")
|
| 168 |
+
|
| 169 |
+
output_dir.mkdir(parents=True, exist_ok=True)
|
| 170 |
+
measured_peak = 0.0
|
| 171 |
+
max_reconstruction_error = 0.0
|
| 172 |
+
first = None
|
| 173 |
+
rms_accum = {key:0.0 for key in TRACKS}
|
| 174 |
+
peaks = {key:0.0 for key in TRACKS}
|
| 175 |
+
metadata = {}
|
| 176 |
+
try:
|
| 177 |
+
with ExitStack() as stack:
|
| 178 |
+
input_file = stack.enter_context(sf.SoundFile(str(input_path), "r"))
|
| 179 |
+
input_refs = {name:stack.enter_context(sf.SoundFile(str(refs[name]),"r")) for name in required}
|
| 180 |
+
writers = {name:stack.enter_context(sf.SoundFile(
|
| 181 |
+
str(output_dir / f"{name}.wav"), "w", format="WAV", subtype="FLOAT",
|
| 182 |
+
samplerate=info.samplerate, channels=info.channels,
|
| 183 |
+
)) for name in TRACKS}
|
| 184 |
+
previews = {name:stack.enter_context(sf.SoundFile(
|
| 185 |
+
str(output_dir / f"{name}_preview.wav"),"w", format="WAV", subtype="PCM_16",
|
| 186 |
+
samplerate=info.samplerate,channels=info.channels,
|
| 187 |
+
)) for name in TRACKS}
|
| 188 |
+
for pos in range(0, info.frames, chunk_frames):
|
| 189 |
+
target_end = min(info.frames, pos + chunk_frames)
|
| 190 |
+
start = max(0, pos - context_frames)
|
| 191 |
+
end = min(info.frames, target_end + context_frames)
|
| 192 |
+
input_file.seek(start)
|
| 193 |
+
x = input_file.read(end-start, dtype="float64", always_2d=True)
|
| 194 |
+
if len(x) != end-start or not np.isfinite(x).all():
|
| 195 |
+
raise AudioError("Audio contains unreadable or non-finite samples.")
|
| 196 |
+
extra = {}
|
| 197 |
+
for name, inp in input_refs.items():
|
| 198 |
+
inp.seek(start)
|
| 199 |
+
extra[name] = inp.read(end-start,dtype="float64",always_2d=True)
|
| 200 |
+
if len(extra[name]) != len(x) or not np.isfinite(extra[name]).all():
|
| 201 |
+
raise AudioError("Reference stem contains invalid samples.")
|
| 202 |
+
tracks = _transform(x,info.samplerate,cfg,mode,**extra)
|
| 203 |
+
sel = slice(pos-start, pos-start + target_end-pos)
|
| 204 |
+
inner = {name:arr[sel] for name,arr in tracks.items()}
|
| 205 |
+
err = np.max(np.abs((inner["kick_estimate"]+inner["bassline_estimate"]+
|
| 206 |
+
inner["other_unprocessed"]) - x[sel]))
|
| 207 |
+
max_reconstruction_error = max(max_reconstruction_error,float(err))
|
| 208 |
+
measured_peak = max(measured_peak,float(np.max(np.abs(inner["mix_optimized"]))))
|
| 209 |
+
if first is None:
|
| 210 |
+
first = {"before": _bands(inner["bass_band"],info.samplerate),
|
| 211 |
+
"after": _bands(inner["bass_optimized"],info.samplerate)}
|
| 212 |
+
for name, signal in inner.items():
|
| 213 |
+
writers[name].write(signal)
|
| 214 |
+
previews[name].write(np.clip(signal,-1,1))
|
| 215 |
+
rms_accum[name] += float(np.sum(np.square(signal)))
|
| 216 |
+
peaks[name] = max(peaks[name], float(np.max(np.abs(signal))))
|
| 217 |
+
if progress:
|
| 218 |
+
progress((target_end / info.frames)*.90)
|
| 219 |
+
# A global, non-clipping gain for MIX output; individual stems remain unaltered.
|
| 220 |
+
ceiling = 10 ** (cfg.ceiling_dbfs/20)
|
| 221 |
+
gain = min(1.0, ceiling / max(measured_peak, 1e-12))
|
| 222 |
+
if gain < 1:
|
| 223 |
+
from tempfile import NamedTemporaryFile
|
| 224 |
+
with NamedTemporaryFile(prefix="omega_mix_",suffix=".wav",dir=output_dir,delete=False) as target:
|
| 225 |
+
temporary = Path(target.name)
|
| 226 |
+
try:
|
| 227 |
+
with sf.SoundFile(str(output_dir / "mix_optimized.wav"), "r") as inp, \
|
| 228 |
+
sf.SoundFile(str(temporary),"w",samplerate=info.samplerate,
|
| 229 |
+
channels=info.channels,subtype="FLOAT", format="WAV") as out:
|
| 230 |
+
while True:
|
| 231 |
+
block = inp.read(131072,dtype="float64",always_2d=True)
|
| 232 |
+
if not len(block): break
|
| 233 |
+
out.write(block*gain)
|
| 234 |
+
temporary.replace(output_dir / "mix_optimized.wav")
|
| 235 |
+
with sf.SoundFile(str(output_dir/"mix_optimized_preview.wav"),"w",
|
| 236 |
+
samplerate=info.samplerate,channels=info.channels,
|
| 237 |
+
format="WAV",subtype="PCM_16") as preview, \
|
| 238 |
+
sf.SoundFile(str(output_dir/"mix_optimized.wav"),"r") as mixed:
|
| 239 |
+
while True:
|
| 240 |
+
block=mixed.read(131072, dtype="float64", always_2d=True)
|
| 241 |
+
if not len(block): break
|
| 242 |
+
preview.write(np.clip(block,-1,1))
|
| 243 |
+
finally:
|
| 244 |
+
temporary.unlink(missing_ok=True)
|
| 245 |
+
for name in TRACKS:
|
| 246 |
+
value = math.sqrt(rms_accum[name] / (info.frames * info.channels))
|
| 247 |
+
metadata[name] = {
|
| 248 |
+
"name": name, "label": TRACKS[name], "master": f"{name}.wav",
|
| 249 |
+
"preview": f"{name}_preview.wav",
|
| 250 |
+
"duration_seconds": round(info.frames/info.samplerate,4),
|
| 251 |
+
"peak_dbfs": round(20 * math.log10(max(peaks[name] * (
|
| 252 |
+
gain if name=="mix_optimized" else 1),1e-12)),3),
|
| 253 |
+
"rms_dbfs": round(20 * math.log10(max(value * (gain if name=="mix_optimized" else 1),1e-12)),3),
|
| 254 |
+
}
|
| 255 |
+
report = {
|
| 256 |
+
"mode": mode, "source_quality": ("AI stem estimate" if mode=="demucs" else
|
| 257 |
+
"HPSS low-band estimate" if mode=="hpss" else
|
| 258 |
+
"DSP transient estimate; not instrument isolation"),
|
| 259 |
+
"created_harmonics_are_synthetic": True,
|
| 260 |
+
"reconstruction_check": {
|
| 261 |
+
"max_abs_error": float(max_reconstruction_error),
|
| 262 |
+
"tolerance": 2e-6,
|
| 263 |
+
"consistent": max_reconstruction_error < 2e-6,
|
| 264 |
+
"scope": "Kick estimate + bassline estimate + unprocessed other = internal input",
|
| 265 |
+
},
|
| 266 |
+
"params": asdict(cfg),
|
| 267 |
+
"first_chunk_spectrum": first,
|
| 268 |
+
"output_ceiling_gain_db": round(20 * math.log10(max(gain, 1e-12)), 3),
|
| 269 |
+
"output_peak_dbfs": round(20 * math.log10(max(measured_peak*gain, 1e-12)), 3),
|
| 270 |
+
"warnings": [
|
| 271 |
+
"Instrument identities are estimates; isolation quality requires listening tests.",
|
| 272 |
+
"Added overtones are synthesized, not restored originals.",
|
| 273 |
+
"The ceiling operates on the optimized MIX; exported individual stems are not peak-limited.",
|
| 274 |
+
"Per-chunk zero-phase filtering can produce low-level boundary artifacts.",
|
| 275 |
+
],
|
| 276 |
+
}
|
| 277 |
+
if progress: progress(1.0)
|
| 278 |
+
return metadata, report
|
| 279 |
+
except Exception:
|
| 280 |
+
# Never leave a partial result mistaken for a completed edit.
|
| 281 |
+
for name in TRACKS:
|
| 282 |
+
for suffix in (".wav","_preview.wav"):
|
| 283 |
+
(output_dir / f"{name}{suffix}").unlink(missing_ok=True)
|
| 284 |
+
raise
|
app/guardian.py
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Preservation Guardian v0.5: interpretable transient protection and independent repair audit.
|
| 2 |
+
|
| 3 |
+
This is classical DSP signal heuristics, NOT a pretrained neural classifier.
|
| 4 |
+
Neither its risk labels nor the original click detector establish ground truth.
|
| 5 |
+
Default operation is fail-closed: protected candidate events cannot be repaired.
|
| 6 |
+
"""
|
| 7 |
+
from __future__ import annotations
|
| 8 |
+
|
| 9 |
+
import hashlib
|
| 10 |
+
import math
|
| 11 |
+
from pathlib import Path
|
| 12 |
+
|
| 13 |
+
import numpy as np
|
| 14 |
+
import soundfile as sf
|
| 15 |
+
|
| 16 |
+
from .audio import audio_info
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def label_event(x: np.ndarray, i: int, sr: int) -> dict:
|
| 20 |
+
"""Provide explainable evidence and a conservative protection decision.
|
| 21 |
+
|
| 22 |
+
x: frames x channels. i must have 35 ms of neighboring context where
|
| 23 |
+
available. No model-inferred probabilities or 'musical certainty' implied.
|
| 24 |
+
"""
|
| 25 |
+
if i < 2 or i >= len(x) - 2:
|
| 26 |
+
return {
|
| 27 |
+
"guardian_verdict": "protect_boundary",
|
| 28 |
+
"repair_allowed": False,
|
| 29 |
+
"guardian_reasons": ["Insufficient samples for local contextual review."],
|
| 30 |
+
}
|
| 31 |
+
width = max(16, round(0.025 * sr))
|
| 32 |
+
before = x[max(0, i-width):i]
|
| 33 |
+
after = x[i+1:min(len(x), i+1+width)]
|
| 34 |
+
# Insufficient context occurs near file boundaries, not chunk boundaries
|
| 35 |
+
# because the scanner reads overlap on both sides.
|
| 36 |
+
if len(before) < max(8, width // 2) or len(after) < max(8, width // 2):
|
| 37 |
+
return {
|
| 38 |
+
"guardian_verdict": "protect_boundary",
|
| 39 |
+
"repair_allowed": False,
|
| 40 |
+
"guardian_reasons": ["Not enough surrounding audio to assess onset structure."],
|
| 41 |
+
}
|
| 42 |
+
innovation = np.abs(x[i] - (x[i-1] + x[i+1]) * 0.5)
|
| 43 |
+
high = float(np.max(innovation))
|
| 44 |
+
active = int(np.count_nonzero(innovation >= max(0.035, high * 0.38)))
|
| 45 |
+
pre_rms = float(np.sqrt(np.mean(before * before)))
|
| 46 |
+
post_rms = float(np.sqrt(np.mean(after * after)))
|
| 47 |
+
attack_ratio = post_rms / max(pre_rms, 1e-7)
|
| 48 |
+
# A musical onset usually has continuation energy; impulsive digital damage
|
| 49 |
+
# isolated to one sample does not reliably create such continuation.
|
| 50 |
+
sustained_onset = bool(
|
| 51 |
+
post_rms > 0.012 and post_rms > pre_rms * 2.5
|
| 52 |
+
and (post_rms - pre_rms) > 0.009
|
| 53 |
+
)
|
| 54 |
+
# A simultaneous stereo impulse might be a drum transient OR a stereo
|
| 55 |
+
# corruption: protect by default rather than guessing.
|
| 56 |
+
multichannel = bool(x.shape[1] >= 2 and active >= 2)
|
| 57 |
+
reasons = []
|
| 58 |
+
if sustained_onset:
|
| 59 |
+
reasons.append("Sustained energy rises after the event; possible musical attack.")
|
| 60 |
+
if multichannel:
|
| 61 |
+
reasons.append("Impulse appears across channels; possible correlated musical transient.")
|
| 62 |
+
if not reasons:
|
| 63 |
+
reasons.append("Isolated candidate, not proof of a non-musical defect. Listening required.")
|
| 64 |
+
blocked = sustained_onset or multichannel
|
| 65 |
+
return {
|
| 66 |
+
"guardian_verdict": "protect_possible_music" if blocked else "review_isolated_candidate",
|
| 67 |
+
"repair_allowed": not blocked,
|
| 68 |
+
"guardian_reasons": reasons,
|
| 69 |
+
"evidence": {
|
| 70 |
+
"channels_with_impulse": active,
|
| 71 |
+
"energy_after_before_ratio": round(min(attack_ratio, 99999), 3),
|
| 72 |
+
"before_rms": round(pre_rms, 6),
|
| 73 |
+
"after_rms": round(post_rms, 6),
|
| 74 |
+
},
|
| 75 |
+
}
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
def file_sha256(path: Path) -> str:
|
| 79 |
+
h = hashlib.sha256()
|
| 80 |
+
with open(path, "rb") as source:
|
| 81 |
+
for block in iter(lambda: source.read(1024 * 1024), b""):
|
| 82 |
+
h.update(block)
|
| 83 |
+
return h.hexdigest()
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
def audit_repair(
|
| 87 |
+
original: Path,
|
| 88 |
+
clean: Path,
|
| 89 |
+
difference: Path,
|
| 90 |
+
approved_samples: list[int],
|
| 91 |
+
original_hash_before: str,
|
| 92 |
+
chunk_frames: int = 131072,
|
| 93 |
+
) -> dict:
|
| 94 |
+
"""Independent readback, samplewise preservation check and mix consistency.
|
| 95 |
+
|
| 96 |
+
'Pass' means changes outside selected sample indices are within the declared
|
| 97 |
+
float32 conversion tolerance; it does NOT prove edits are musically correct.
|
| 98 |
+
"""
|
| 99 |
+
info = audio_info(original)
|
| 100 |
+
changed_outside_max = 0.0
|
| 101 |
+
recon_error_max = 0.0
|
| 102 |
+
selected = set(int(i) for i in approved_samples)
|
| 103 |
+
modified_indices = set()
|
| 104 |
+
selected_delta_peak = 0.0
|
| 105 |
+
with sf.SoundFile(str(original)) as a, sf.SoundFile(str(clean)) as b, sf.SoundFile(str(difference)) as d:
|
| 106 |
+
if ((a.frames, a.samplerate, a.channels) != (b.frames, b.samplerate, b.channels)
|
| 107 |
+
or (a.frames, a.samplerate, a.channels) != (d.frames, d.samplerate, d.channels)):
|
| 108 |
+
raise ValueError("Guardian audit failed: mismatched audio dimensions.")
|
| 109 |
+
for start in range(0, info.frames, chunk_frames):
|
| 110 |
+
end = min(info.frames, start + chunk_frames)
|
| 111 |
+
x = a.read(end-start,dtype="float64",always_2d=True)
|
| 112 |
+
y = b.read(end-start,dtype="float64",always_2d=True)
|
| 113 |
+
z = d.read(end-start,dtype="float64",always_2d=True)
|
| 114 |
+
if not all(np.isfinite(k).all() for k in (x,y,z)):
|
| 115 |
+
raise ValueError("Guardian audit failed: non-finite output.")
|
| 116 |
+
delta = np.max(np.abs(x-y),axis=1)
|
| 117 |
+
unselected = np.ones(len(delta), dtype=bool)
|
| 118 |
+
for loc in selected:
|
| 119 |
+
if start <= loc < end:
|
| 120 |
+
unselected[loc-start] = False
|
| 121 |
+
if np.any(unselected):
|
| 122 |
+
changed_outside_max = max(changed_outside_max, float(np.max(delta[unselected])))
|
| 123 |
+
if np.any(~unselected):
|
| 124 |
+
selected_delta_peak = max(selected_delta_peak, float(np.max(delta[~unselected])))
|
| 125 |
+
modified_indices.update(int(start + j) for j in np.flatnonzero((delta > 2e-7) & ~unselected))
|
| 126 |
+
recon_error_max = max(recon_error_max, float(np.max(np.abs(x-y-z))))
|
| 127 |
+
hash_after = file_sha256(original)
|
| 128 |
+
original_untouched = original_hash_before == hash_after
|
| 129 |
+
# Float32 WAV stores ~7 significant digits; PCM32 inputs can quantize.
|
| 130 |
+
# 2e-7 absolute is an explicit tolerance, not bit-identical representation.
|
| 131 |
+
tolerance = 2.0e-7
|
| 132 |
+
passed = original_untouched and changed_outside_max <= tolerance and recon_error_max <= tolerance
|
| 133 |
+
return {
|
| 134 |
+
"engine": "independent_samplewise_guardian_audit_v0.5",
|
| 135 |
+
"result": "PASS" if passed else "BLOCK",
|
| 136 |
+
"original_hash_unchanged": original_untouched,
|
| 137 |
+
"approved_sample_count": len(selected),
|
| 138 |
+
"changed_approved_sample_count": len(modified_indices),
|
| 139 |
+
"unapproved_max_absolute_change": changed_outside_max,
|
| 140 |
+
"selected_peak_absolute_change": selected_delta_peak,
|
| 141 |
+
"reconstruction_max_absolute_error": recon_error_max,
|
| 142 |
+
"absolute_float32_tolerance": tolerance,
|
| 143 |
+
"interpretation": "Numerical preservation outside approved sample frames, not perceptual proof.",
|
| 144 |
+
"air_and_reverb": "Samples outside approved indices preserved to float32 tolerance; edited samples remain uncertain.",
|
| 145 |
+
}
|
app/mini_model.py
ADDED
|
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""OMEGA-TAG Mini v0.5: tiny, OFFLINE multilabel spectral-event model.
|
| 2 |
+
|
| 3 |
+
Model shipped with project uses *synthetic* two-stage training: isolated/pair
|
| 4 |
+
pretraining, then overlapping-mixture fine-tuning. It has NEVER been trained
|
| 5 |
+
on real labelled music, so it must not claim reliable instrument identities.
|
| 6 |
+
All scores are uncalibrated classifier activations, not probabilities.
|
| 7 |
+
No remote downloads or unsafe pickle deserialization.
|
| 8 |
+
"""
|
| 9 |
+
from __future__ import annotations
|
| 10 |
+
|
| 11 |
+
from pathlib import Path
|
| 12 |
+
import hashlib
|
| 13 |
+
import json
|
| 14 |
+
import math
|
| 15 |
+
|
| 16 |
+
import numpy as np
|
| 17 |
+
import soundfile as sf
|
| 18 |
+
from scipy.signal import resample_poly
|
| 19 |
+
|
| 20 |
+
LABELS = ("bass_sustain", "kick_like", "snare_like", "hi_hat_like",
|
| 21 |
+
"harmonic_mid", "noise_texture")
|
| 22 |
+
FRIENDLY = {
|
| 23 |
+
"bass_sustain": "Tieffrequente, anhaltende Töne / Bass-Verdacht",
|
| 24 |
+
"kick_like": "Tieffrequente Impulse / Kick-Verdacht",
|
| 25 |
+
"snare_like": "Breitbandige Mitten-Impulse / Snare-Verdacht",
|
| 26 |
+
"hi_hat_like": "Helle, kurze Impulse / Hi-Hat-Verdacht",
|
| 27 |
+
"harmonic_mid": "Harmonische Mitten / Melodie-Verdacht",
|
| 28 |
+
"noise_texture": "Rauschähnliche Textur (kann musikalisch sein)",
|
| 29 |
+
}
|
| 30 |
+
SR = 8000
|
| 31 |
+
N = 4096
|
| 32 |
+
MODEL_FILE = Path(__file__).resolve().parent / "models" / "omega_tag_mini_v1.npz"
|
| 33 |
+
BANDS = ((25,80),(80,180),(180,400),(400,900),(900,1900),(1900,3500),(3500,3950))
|
| 34 |
+
|
| 35 |
+
def features(x: np.ndarray) -> np.ndarray:
|
| 36 |
+
"""32 stable feature components from 0.512s mono resampled audio.
|
| 37 |
+
|
| 38 |
+
Features are descriptive and deliberately do not identify instruments
|
| 39 |
+
through semantic embedding / pretrained audio foundation features.
|
| 40 |
+
"""
|
| 41 |
+
x = np.asarray(x, dtype=np.float64).reshape(-1)
|
| 42 |
+
if len(x) != N:
|
| 43 |
+
raise ValueError(f"Expected {N} samples, got {len(x)}")
|
| 44 |
+
if not np.isfinite(x).all():
|
| 45 |
+
raise ValueError("Non-finite features input")
|
| 46 |
+
# Fixed frames. Use per-frame relative energies for spectral activity.
|
| 47 |
+
windows = np.stack([x[i:i+1024] for i in range(0, N-1024+1, 384)], axis=0)
|
| 48 |
+
fft = np.abs(np.fft.rfft(windows*np.hanning(1024), axis=-1))**2+1e-15
|
| 49 |
+
hz = np.fft.rfftfreq(1024, 1./SR)
|
| 50 |
+
bands=np.stack([fft[:,(hz>=lo)&(hz<hi)].sum(axis=1) for lo,hi in BANDS],axis=1)
|
| 51 |
+
frame_energy = fft.sum(axis=1,keepdims=True)
|
| 52 |
+
proportion=bands/frame_energy
|
| 53 |
+
avg=proportion.mean(axis=0)
|
| 54 |
+
variability=proportion.std(axis=0)
|
| 55 |
+
logenergy=np.log10(np.maximum(bands.mean(axis=0),1e-10))
|
| 56 |
+
logtotal=np.log10(max(float(np.mean(x*x)),1e-10))
|
| 57 |
+
flatness=(np.exp(np.mean(np.log(fft),axis=1))/np.mean(fft,axis=1)).mean()
|
| 58 |
+
zcr=np.mean(np.signbit(x[1:])!=np.signbit(x[:-1]))
|
| 59 |
+
power=np.mean(windows*windows,axis=1)
|
| 60 |
+
onset=np.maximum(np.diff(power),0)
|
| 61 |
+
novelty=float(np.max(onset)/(np.mean(power)+1e-12))
|
| 62 |
+
fluctuation=float(np.std(power)/(np.mean(power)+1e-12))
|
| 63 |
+
crest=float(np.max(np.abs(x))/(math.sqrt(float(np.mean(x*x)))+1e-10))
|
| 64 |
+
spectral_flux=np.maximum(np.diff(np.sqrt(fft),axis=0),0).sum()/np.sqrt(fft).sum()
|
| 65 |
+
# 7+7+7+7 = 28, then 7 metadata => 35
|
| 66 |
+
result=np.r_[avg,variability,np.clip(logenergy,-10,7),
|
| 67 |
+
np.clip(logenergy-logenergy.mean(),-12,12),
|
| 68 |
+
logtotal, flatness,zcr,np.log1p(novelty),
|
| 69 |
+
np.log1p(fluctuation), np.log1p(crest),spectral_flux]
|
| 70 |
+
return np.asarray(result,dtype=np.float32)
|
| 71 |
+
|
| 72 |
+
FEATURE_COUNT = len(features(np.zeros(N,dtype=np.float32)))
|
| 73 |
+
|
| 74 |
+
def synthetic_signal(label: str, rng: np.random.Generator) -> np.ndarray:
|
| 75 |
+
"""Generated test/training signals, NOT copyrighted music nor real stems."""
|
| 76 |
+
t=np.arange(N)/SR
|
| 77 |
+
x=np.zeros(N,dtype=np.float64)
|
| 78 |
+
if label=="bass_sustain":
|
| 79 |
+
freq=rng.uniform(46,160)
|
| 80 |
+
for harmonic in (1,2,3):
|
| 81 |
+
x+=np.sin(2*np.pi*(harmonic*freq*t+rng.uniform(0,1)))*(.6/harmonic**1.3)
|
| 82 |
+
x*=.4+.6*np.sin(2*np.pi*rng.uniform(.3,2)*t+rng.uniform(0,6))**2
|
| 83 |
+
elif label=="kick_like":
|
| 84 |
+
for loc in rng.choice(np.arange(0,N-850,300),size=int(rng.integers(1,4)),replace=False):
|
| 85 |
+
k=np.arange(min(1500,N-loc)); time=k/SR
|
| 86 |
+
phase=2*np.pi*(50*time+90*(1-np.exp(-time*32))/32)
|
| 87 |
+
env=np.exp(-time*rng.uniform(17,35))
|
| 88 |
+
x[loc:loc+len(k)] += np.sin(phase)*env
|
| 89 |
+
elif label=="snare_like":
|
| 90 |
+
for loc in rng.choice(np.arange(0,N-450,280),size=int(rng.integers(1,4)),replace=False):
|
| 91 |
+
k=np.arange(min(850,N-loc)); time=k/SR
|
| 92 |
+
pulse=rng.standard_normal(len(k))
|
| 93 |
+
pulse=np.r_[0,np.diff(pulse)]
|
| 94 |
+
x[loc:loc+len(k)] += pulse*np.exp(-time*27)*.3
|
| 95 |
+
elif label=="hi_hat_like":
|
| 96 |
+
for loc in rng.choice(np.arange(0,N-150,170),size=int(rng.integers(2,7)),replace=False):
|
| 97 |
+
k=np.arange(min(380,N-loc));time=k/SR
|
| 98 |
+
noise=rng.standard_normal(len(k))
|
| 99 |
+
noise=np.r_[0,np.diff(noise)]
|
| 100 |
+
x[loc:loc+len(k)]+=noise*np.exp(-time*85)*.35
|
| 101 |
+
elif label=="harmonic_mid":
|
| 102 |
+
for freq in rng.uniform(200,900,size=int(rng.integers(1,4))):
|
| 103 |
+
x+=np.sin(2*np.pi*(freq*t+rng.uniform(0,1)))*.4
|
| 104 |
+
x*=.3+.7*(np.sin(np.pi*np.clip(t/rng.uniform(.25,.85),0,1))**2)
|
| 105 |
+
elif label=="noise_texture":
|
| 106 |
+
noise=rng.standard_normal(N)
|
| 107 |
+
if rng.random()<.6:
|
| 108 |
+
noise=np.convolve(noise,np.ones(37)/37,mode='same')
|
| 109 |
+
x += noise*.3
|
| 110 |
+
return x.astype(np.float32)
|
| 111 |
+
|
| 112 |
+
def synthetic_case(rng:np.random.Generator, phase: str) -> tuple[np.ndarray,np.ndarray]:
|
| 113 |
+
max_sources=2 if phase=="pretrain" else 5
|
| 114 |
+
count=int(rng.integers(1,max_sources+1))
|
| 115 |
+
indices=rng.choice(len(LABELS),size=count,replace=False)
|
| 116 |
+
y=np.zeros(len(LABELS),dtype=np.float32)
|
| 117 |
+
x=np.zeros(N,dtype=np.float32)
|
| 118 |
+
for idx in indices:
|
| 119 |
+
y[idx]=1.
|
| 120 |
+
x+=synthetic_signal(LABELS[idx],rng)*rng.uniform(.2,1.0)
|
| 121 |
+
# Apply nonstationary gain, external hum/noise and polarity changes to test
|
| 122 |
+
# robustness; all remain synthetic.
|
| 123 |
+
if rng.random()<.4:x*=np.linspace(rng.uniform(.35,1),rng.uniform(.35,1),N)
|
| 124 |
+
if rng.random()<.5:x+=rng.standard_normal(N).astype(np.float32)*rng.uniform(0,.016)
|
| 125 |
+
if rng.random()<.5:x*=-1
|
| 126 |
+
peak=max(float(np.max(np.abs(x))),1e-8)
|
| 127 |
+
x*=float(rng.uniform(.15,.8))/peak
|
| 128 |
+
return x,y
|
| 129 |
+
|
| 130 |
+
def generate_training(n:int,seed:int,phase:str):
|
| 131 |
+
rng=np.random.default_rng(seed)
|
| 132 |
+
X=np.empty((n,FEATURE_COUNT),np.float32)
|
| 133 |
+
Y=np.empty((n,len(LABELS)),np.float32)
|
| 134 |
+
for i in range(n):
|
| 135 |
+
x,y=synthetic_case(rng,phase)
|
| 136 |
+
X[i]=features(x);Y[i]=y
|
| 137 |
+
return X,Y
|
| 138 |
+
|
| 139 |
+
def _sigmoid(z): return 1/(1+np.exp(-np.clip(z,-35,35)))
|
| 140 |
+
|
| 141 |
+
def _net(X,W1,b1,W2,b2):
|
| 142 |
+
h=np.tanh(X@W1+b1)
|
| 143 |
+
return h,_sigmoid(h@W2+b2)
|
| 144 |
+
|
| 145 |
+
def train_model(destination:Path=MODEL_FILE,seed:int=25,epochs1:int=90,epochs2:int=105,
|
| 146 |
+
pretrain_count:int=650,finetune_count:int=1100) -> dict:
|
| 147 |
+
"""Offline reproducible 2-stage neural training, using only synthetic audio.
|
| 148 |
+
|
| 149 |
+
Stage 2 is real parameter fine-tuning of stage 1 weights but NOT transfer
|
| 150 |
+
learning from a commercial foundation model or real instrument recordings.
|
| 151 |
+
"""
|
| 152 |
+
rng=np.random.default_rng(seed)
|
| 153 |
+
xp,yp=generate_training(pretrain_count,seed,"pretrain")
|
| 154 |
+
xf,yf=generate_training(finetune_count,seed+1,"finetune")
|
| 155 |
+
xt,yt=generate_training(300,seed+2,"finetune")
|
| 156 |
+
mu=xp.mean(axis=0)
|
| 157 |
+
sigma=np.maximum(xp.std(axis=0),.08)
|
| 158 |
+
xp=np.clip((xp-mu)/sigma,-8,8)
|
| 159 |
+
xf=np.clip((xf-mu)/sigma,-8,8)
|
| 160 |
+
xt=np.clip((xt-mu)/sigma,-8,8)
|
| 161 |
+
hidden=32
|
| 162 |
+
W1=(rng.standard_normal((FEATURE_COUNT,hidden))*.15).astype(np.float64)
|
| 163 |
+
b1=np.zeros(hidden)
|
| 164 |
+
W2=(rng.standard_normal((hidden,len(LABELS)))*.15).astype(np.float64)
|
| 165 |
+
b2=np.zeros(len(LABELS))
|
| 166 |
+
params=[W1,b1,W2,b2]
|
| 167 |
+
mt=[np.zeros_like(p) for p in params]
|
| 168 |
+
vt=[np.zeros_like(p) for p in params]
|
| 169 |
+
step=0
|
| 170 |
+
def loop(X,Y,epochs,lr):
|
| 171 |
+
nonlocal step
|
| 172 |
+
for epoch in range(epochs):
|
| 173 |
+
for batchidx in np.array_split(rng.permutation(len(X)),max(1,len(X)//96)):
|
| 174 |
+
data,labels=X[batchidx],Y[batchidx]
|
| 175 |
+
h,prob=_net(data,*params)
|
| 176 |
+
grad=(prob-labels)/len(batchidx)
|
| 177 |
+
g2=h.T@grad
|
| 178 |
+
gb2=grad.sum(axis=0)
|
| 179 |
+
gh=(grad@W2.T)*(1-h*h)
|
| 180 |
+
g1=data.T@gh
|
| 181 |
+
gb1=gh.sum(axis=0)
|
| 182 |
+
for idx, g in enumerate((g1,gb1,g2,gb2)):
|
| 183 |
+
step+=1 if idx==0 else 0
|
| 184 |
+
mt[idx][:]=.9*mt[idx]+.1*g
|
| 185 |
+
vt[idx][:]=.999*vt[idx]+.001*g*g
|
| 186 |
+
mhat=mt[idx]/(1-.9**step)
|
| 187 |
+
vhat=vt[idx]/(1-.999**step)
|
| 188 |
+
params[idx]-=lr*mhat/(np.sqrt(vhat)+1e-8)
|
| 189 |
+
loop(xp,yp,epochs1,.012)
|
| 190 |
+
loop(xf,yf,epochs2,.006)
|
| 191 |
+
h,pred=_net(xt,*params)
|
| 192 |
+
estimates=pred>=.5
|
| 193 |
+
precision=float(np.sum((estimates==1)&(yt==1))/max(1,np.sum(estimates==1)))
|
| 194 |
+
recall=float(np.sum((estimates==1)&(yt==1))/max(1,np.sum(yt==1)))
|
| 195 |
+
acc=float(np.mean(estimates==yt))
|
| 196 |
+
destination.parent.mkdir(parents=True,exist_ok=True)
|
| 197 |
+
np.savez_compressed(destination,
|
| 198 |
+
W1=W1.astype(np.float32),b1=b1.astype(np.float32),
|
| 199 |
+
W2=W2.astype(np.float32),b2=b2.astype(np.float32),
|
| 200 |
+
mu=mu.astype(np.float32),sigma=sigma.astype(np.float32),
|
| 201 |
+
model_schema=np.array("omega_mini_synthetic_v1"),
|
| 202 |
+
labels=np.asarray(LABELS))
|
| 203 |
+
return {"stage1":"synthetic isolated/pair pretraining",
|
| 204 |
+
"stage2":"fine-tuning on synthetic overlapping mixtures",
|
| 205 |
+
"heldout_synthetic_precision":round(precision,3),
|
| 206 |
+
"heldout_synthetic_recall":round(recall,3),
|
| 207 |
+
"heldout_synthetic_label_accuracy":round(acc,3),
|
| 208 |
+
"validation_dataset":"300 held-out synthetic mixtures, NOT real-world benchmark",
|
| 209 |
+
"checkpoint":str(destination),
|
| 210 |
+
"checkpoint_sha256":hashlib.sha256(destination.read_bytes()).hexdigest(),
|
| 211 |
+
"architecture":f"feature({FEATURE_COUNT}) -> tanh(32) -> sigmoid({len(LABELS)})",
|
| 212 |
+
"train_examples":pretrain_count+finetune_count}
|
| 213 |
+
|
| 214 |
+
def load_model(path:Path=MODEL_FILE)->dict:
|
| 215 |
+
if not path.is_file():
|
| 216 |
+
raise FileNotFoundError("Mini model missing. Run python -m app.mini_model --train")
|
| 217 |
+
with np.load(path,allow_pickle=False) as f:
|
| 218 |
+
params={k:f[k].copy() for k in ("W1","b1","W2","b2","mu","sigma")}
|
| 219 |
+
schema=str(f["model_schema"].item())
|
| 220 |
+
labels=tuple(str(x) for x in f["labels"])
|
| 221 |
+
if schema!="omega_mini_synthetic_v1" or labels!=LABELS:
|
| 222 |
+
raise ValueError("Unsupported/incompatible mini model weights")
|
| 223 |
+
if params["W1"].shape!=(FEATURE_COUNT,32) or params["W2"].shape!=(32,len(LABELS)):
|
| 224 |
+
raise ValueError("Corrupt mini model dimensions")
|
| 225 |
+
if not all(np.isfinite(v).all() for v in params.values()):
|
| 226 |
+
raise ValueError("Non-finite model weights")
|
| 227 |
+
return params
|
| 228 |
+
|
| 229 |
+
def predict_features(x:np.ndarray,model:dict)->np.ndarray:
|
| 230 |
+
scaled=np.clip((x-model["mu"])/model["sigma"],-8,8)
|
| 231 |
+
return _net(scaled,model["W1"],model["b1"],model["W2"],model["b2"])[1]
|
| 232 |
+
|
| 233 |
+
def inspect_file(path:Path,max_windows:int=12, model_path:Path=MODEL_FILE)->dict:
|
| 234 |
+
"""Inspect strategically sampled 0.512s segments; bounded RAM, any duration."""
|
| 235 |
+
model=load_model(model_path)
|
| 236 |
+
scores=[]
|
| 237 |
+
with sf.SoundFile(str(path)) as source:
|
| 238 |
+
if source.frames<=0:
|
| 239 |
+
raise ValueError("Empty audio")
|
| 240 |
+
count=min(max_windows,max(1,math.ceil(source.frames/source.samplerate/.65)))
|
| 241 |
+
positions=np.linspace(0,max(0,source.frames-int(.55*source.samplerate)),count,dtype=int)
|
| 242 |
+
for pos in positions:
|
| 243 |
+
source.seek(int(pos))
|
| 244 |
+
block=source.read(min(source.frames-int(pos),int(.65*source.samplerate)),
|
| 245 |
+
dtype="float32",always_2d=True)
|
| 246 |
+
if not np.isfinite(block).all():raise ValueError("Invalid audio samples")
|
| 247 |
+
mono=block.mean(axis=1)
|
| 248 |
+
if len(mono)>0:
|
| 249 |
+
g=math.gcd(source.samplerate,SR)
|
| 250 |
+
mono=resample_poly(mono,SR//g,source.samplerate//g)
|
| 251 |
+
if len(mono)<N:mono=np.pad(mono,(0,N-len(mono)))
|
| 252 |
+
mono=mono[:N]
|
| 253 |
+
scores.append(predict_features(features(mono),model))
|
| 254 |
+
pred=np.stack(scores)
|
| 255 |
+
score=np.mean(pred,axis=0)*.6+np.max(pred,axis=0)*.4
|
| 256 |
+
return {
|
| 257 |
+
"model":"OMEGA-TAG Mini v1",
|
| 258 |
+
"model_kind":"tiny_neural_network__synthetic_pretrained_and_finetuned",
|
| 259 |
+
"checkpoint_sha256":hashlib.sha256(Path(model_path).read_bytes()).hexdigest(),
|
| 260 |
+
"input_sha256":hashlib.sha256(Path(path).read_bytes()).hexdigest(),
|
| 261 |
+
"sampled_windows":len(scores),
|
| 262 |
+
"scope":"SYNTHETIC SIGNAL TEXTURE TAGGING; no verified instrument identification",
|
| 263 |
+
"score_definition":"uncalibrated neural activation; NOT real-world probability",
|
| 264 |
+
"detections":[{"id":label,"label":FRIENDLY[label],"score":round(float(prob),4),
|
| 265 |
+
"suggested":bool(prob>=.55),
|
| 266 |
+
"note":"Hypothesis only. May be wrong for real recordings."}
|
| 267 |
+
for label,prob in zip(LABELS,score)],
|
| 268 |
+
"limitations":["No pretrained music foundation model",
|
| 269 |
+
"No isolated real music-stem training data",
|
| 270 |
+
"Scores are not calibrated for real recordings",
|
| 271 |
+
"Short sampled windows may miss rare or late events"],
|
| 272 |
+
}
|
| 273 |
+
|
| 274 |
+
if __name__=="__main__":
|
| 275 |
+
import sys
|
| 276 |
+
if sys.argv[1:]==["--train"]:
|
| 277 |
+
details=train_model()
|
| 278 |
+
print(json.dumps(details,indent=2))
|
| 279 |
+
else:
|
| 280 |
+
print("Use: python -m app.mini_model --train")
|
app/mixer.py
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""ABSOLUTION Ω arrangement mixer: offline stem mix with non-destructive gain/pan/FX.
|
| 2 |
+
|
| 3 |
+
Only real stem files issued by separation can be mixed. Planning hypotheses
|
| 4 |
+
never become audible tracks. No mastering / denoising is implicit.
|
| 5 |
+
"""
|
| 6 |
+
from __future__ import annotations
|
| 7 |
+
|
| 8 |
+
import json
|
| 9 |
+
import math
|
| 10 |
+
import shutil
|
| 11 |
+
import subprocess
|
| 12 |
+
import tempfile
|
| 13 |
+
from pathlib import Path
|
| 14 |
+
|
| 15 |
+
import numpy as np
|
| 16 |
+
import soundfile as sf
|
| 17 |
+
from scipy.signal import butter, sosfilt, sosfilt_zi
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
def rubberband_available() -> bool:
|
| 21 |
+
exe=shutil.which("ffmpeg")
|
| 22 |
+
if not exe:return False
|
| 23 |
+
try:
|
| 24 |
+
out=subprocess.run([exe,"-hide_banner","-filters"],capture_output=True,text=True,timeout=8)
|
| 25 |
+
return "rubberband" in out.stdout
|
| 26 |
+
except (OSError,subprocess.TimeoutExpired):
|
| 27 |
+
return False
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
def render_mix(sources:dict[str,Path], settings:dict, destination:Path,
|
| 31 |
+
progress=None) -> dict:
|
| 32 |
+
"""Chunked deterministic float32 WAV mixer. Returns audited peak and metadata.
|
| 33 |
+
|
| 34 |
+
Source files must be sample-aligned, with identical sample rate and frame
|
| 35 |
+
count. Effects are independent per stem and maintain filter state.
|
| 36 |
+
"""
|
| 37 |
+
if not sources:raise ValueError("No real separated stems are available")
|
| 38 |
+
if len(sources)>128:raise ValueError("Maximum 128 simultaneously mixed stems for resource safety")
|
| 39 |
+
desired=settings.get("tracks") or {}
|
| 40 |
+
if set(desired)-set(sources):
|
| 41 |
+
raise ValueError("Unknown track names in mixer settings")
|
| 42 |
+
infos={name:sf.info(str(path)) for name,path in sources.items()}
|
| 43 |
+
sr=next(iter(infos.values())).samplerate
|
| 44 |
+
frames=next(iter(infos.values())).frames
|
| 45 |
+
if any(i.samplerate!=sr or i.frames!=frames or i.channels not in (1,2) for i in infos.values()):
|
| 46 |
+
raise ValueError("Stem sample rates, lengths or channels are incompatible")
|
| 47 |
+
# Preserve channel topology for original stereo recordings.
|
| 48 |
+
channels=max(i.channels for i in infos.values())
|
| 49 |
+
is_solo=any(bool(desired.get(n,{}).get("solo",False)) for n in sources)
|
| 50 |
+
track_state={}
|
| 51 |
+
for name in sources:
|
| 52 |
+
p=desired.get(name,{})
|
| 53 |
+
gain=float(p.get("gain_db",0));pan=float(p.get("pan",0))
|
| 54 |
+
hp=float(p.get("highpass_hz",0));lp=float(p.get("lowpass_hz",0))
|
| 55 |
+
width=float(p.get("width",1));drive=float(p.get("drive",0))
|
| 56 |
+
if not (-48<=gain<=12 and -1<=pan<=1 and 0<=hp<=400 and
|
| 57 |
+
0<=lp<=min(18000,sr*.47) and 0<=drive<=1 and 0<=width<=2):
|
| 58 |
+
raise ValueError("Mixer parameter outside supported range")
|
| 59 |
+
if hp and lp and hp>=lp:raise ValueError("Highpass must be below lowpass")
|
| 60 |
+
chain=[]
|
| 61 |
+
for typ,freq in (("highpass",hp),("lowpass",lp)):
|
| 62 |
+
if freq:
|
| 63 |
+
sos=butter(2,freq,btype=typ,fs=sr,output="sos")
|
| 64 |
+
zi=np.zeros((len(sos),2,channels),np.float64)
|
| 65 |
+
chain.append([sos,zi])
|
| 66 |
+
track_state[name]=(p,10**(gain/20),pan,drive,width,chain)
|
| 67 |
+
destination.parent.mkdir(parents=True,exist_ok=True)
|
| 68 |
+
tmp=destination.with_name(f".{destination.stem}.tmp.wav")
|
| 69 |
+
peak=0.;rms_sq=0.;n=0
|
| 70 |
+
try:
|
| 71 |
+
from contextlib import ExitStack
|
| 72 |
+
with ExitStack() as stack:
|
| 73 |
+
readers={k:stack.enter_context(sf.SoundFile(str(v),"r")) for k,v in sources.items()}
|
| 74 |
+
out=stack.enter_context(sf.SoundFile(str(tmp),"w",samplerate=sr,
|
| 75 |
+
channels=channels,subtype="FLOAT",format="WAV"))
|
| 76 |
+
blocksize=32768
|
| 77 |
+
for start in range(0,frames,blocksize):
|
| 78 |
+
count=min(blocksize,frames-start)
|
| 79 |
+
mixed=np.zeros((count,channels),dtype=np.float64)
|
| 80 |
+
for name,src in readers.items():
|
| 81 |
+
x=src.read(count,dtype="float64",always_2d=True)
|
| 82 |
+
if len(x)!=count:raise ValueError(f"Incomplete stem {name}")
|
| 83 |
+
p,gain,pan,drive,width,chain=track_state[name]
|
| 84 |
+
if bool(p.get("mute",False)) or (is_solo and not p.get("solo",False)):
|
| 85 |
+
continue
|
| 86 |
+
if x.shape[1]==1 and channels==2:x=np.repeat(x,2,axis=1)
|
| 87 |
+
if x.shape[1]!=channels:raise ValueError("Channel mismatch")
|
| 88 |
+
for entry in chain:
|
| 89 |
+
# One persistent state per channel, chunk boundary safe.
|
| 90 |
+
sos,zi=entry
|
| 91 |
+
for c in range(channels):
|
| 92 |
+
x[:,c],zi[:,:,c]=sosfilt(sos,x[:,c],zi=zi[:,:,c])
|
| 93 |
+
if drive:
|
| 94 |
+
amount=1+drive*5
|
| 95 |
+
x=np.tanh(x*amount)/amount
|
| 96 |
+
if channels==2:
|
| 97 |
+
mid=(x[:,0]+x[:,1])*.5
|
| 98 |
+
side=(x[:,0]-x[:,1])*.5*width
|
| 99 |
+
left=mid+side;right=mid-side
|
| 100 |
+
x=np.column_stack((left,right))
|
| 101 |
+
# Constant center gain and smoothly attenuate opposite side.
|
| 102 |
+
gl=math.cos((pan+1)*math.pi/4)*math.sqrt(2)
|
| 103 |
+
gr=math.sin((pan+1)*math.pi/4)*math.sqrt(2)
|
| 104 |
+
x*=np.array([gl,gr])
|
| 105 |
+
mixed+=x*gain
|
| 106 |
+
if not np.isfinite(mixed).all():raise ValueError("Non-finite mixer output")
|
| 107 |
+
peak=max(peak,float(np.max(np.abs(mixed))) if mixed.size else 0)
|
| 108 |
+
rms_sq+=float(np.sum(mixed*mixed));n+=mixed.size
|
| 109 |
+
out.write(mixed.astype(np.float32))
|
| 110 |
+
if progress:progress((start+count)/frames)
|
| 111 |
+
tmp.replace(destination)
|
| 112 |
+
finally:
|
| 113 |
+
tmp.unlink(missing_ok=True)
|
| 114 |
+
tempo=float(settings.get("tempo",1))
|
| 115 |
+
pitch=float(settings.get("pitch_semitones",0))
|
| 116 |
+
if not (0.5<=tempo<=2 and -12<=pitch<=12):raise ValueError("Invalid tempo/pitch")
|
| 117 |
+
if abs(tempo-1)>1e-5 or abs(pitch)>1e-5:
|
| 118 |
+
if not rubberband_available():
|
| 119 |
+
destination.unlink(missing_ok=True)
|
| 120 |
+
raise ValueError("Independent tempo/pitch needs FFmpeg with rubberband filter")
|
| 121 |
+
shifted=destination.with_name("render_transformed.wav")
|
| 122 |
+
try:
|
| 123 |
+
args=["ffmpeg","-nostdin","-hide_banner","-loglevel","error","-y","-i",str(destination),
|
| 124 |
+
"-af",f"rubberband=tempo={tempo:.6f}:pitch={2**(pitch/12):.8f}",
|
| 125 |
+
"-c:a","pcm_f32le",str(shifted)]
|
| 126 |
+
p=subprocess.run(args,capture_output=True,text=True)
|
| 127 |
+
if p.returncode!=0:raise ValueError("Rubberband processing failed: "+p.stderr[-300:])
|
| 128 |
+
shifted.replace(destination)
|
| 129 |
+
finally:
|
| 130 |
+
shifted.unlink(missing_ok=True)
|
| 131 |
+
with sf.SoundFile(destination) as f:
|
| 132 |
+
peak=0;rms_sq=0;n=0
|
| 133 |
+
while True:
|
| 134 |
+
b=f.read(32768,dtype="float32",always_2d=True)
|
| 135 |
+
if len(b)==0:break
|
| 136 |
+
peak=max(peak,float(np.max(np.abs(b))))
|
| 137 |
+
rms_sq+=float(np.sum(b.astype(np.float64)**2));n+=b.size
|
| 138 |
+
return {"samplerate":sr,"channels":channels,"source_frames":frames,
|
| 139 |
+
"output_frames":sf.info(str(destination)).frames,
|
| 140 |
+
"peak_dbfs":round(20*math.log10(max(peak,1e-12)),3),
|
| 141 |
+
"rms_dbfs":round(20*math.log10(max(math.sqrt(rms_sq/max(n,1)),1e-12)),3),
|
| 142 |
+
"float_wav":True,"clip_warning":peak>1,
|
| 143 |
+
"isolation":"Only actual separated stems; no proposed tracks",
|
| 144 |
+
"tempo":tempo,"pitch_semitones":pitch}
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
def sampled_peaks(path:Path, size:int=360)->dict:
|
| 148 |
+
"""Downsample visual amplitude envelope by sampling short blocks; not an exhaustive peak scan."""
|
| 149 |
+
info=sf.info(str(path))
|
| 150 |
+
if info.channels not in (1,2):raise ValueError("Only mono/stereo available")
|
| 151 |
+
size=max(64,min(size,1000))
|
| 152 |
+
points=[]
|
| 153 |
+
with sf.SoundFile(str(path)) as f:
|
| 154 |
+
for pos in np.linspace(0,max(0,info.frames-512),size,dtype=int):
|
| 155 |
+
f.seek(int(pos))
|
| 156 |
+
block=f.read(min(512,info.frames-int(pos)),dtype="float32",always_2d=True)
|
| 157 |
+
points.append(round(float(np.max(np.abs(block))) if block.size else 0,5))
|
| 158 |
+
return {"samples":points,"duration":round(info.duration,3),
|
| 159 |
+
"samplerate":info.samplerate,"sample_method":"sparse_windows_512frames",
|
| 160 |
+
"peak_reliability":"visualization only; not exhaustive"}
|
app/models/omega_tag_mini_v1.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd952daf742ab4c8e0fbf31b19b25f2e1baa124e304f04bd0a5f1641d90dfad
|
| 3 |
+
size 7030
|
app/noise.py
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""NOISE-CORE Ω — preservation-first detection and explicitly approved sample repairs.
|
| 2 |
+
|
| 3 |
+
Important: a click hypothesis is *not* proof that the sample is noise.
|
| 4 |
+
Nothing is modified during the scan. Repair needs indices explicitly
|
| 5 |
+
selected by a user and always produces an exact conceptual difference stem.
|
| 6 |
+
|
| 7 |
+
No network, pretrained model, or destructive replacement is performed.
|
| 8 |
+
"""
|
| 9 |
+
from __future__ import annotations
|
| 10 |
+
|
| 11 |
+
import math
|
| 12 |
+
from contextlib import ExitStack
|
| 13 |
+
from dataclasses import dataclass
|
| 14 |
+
from pathlib import Path
|
| 15 |
+
from typing import Callable
|
| 16 |
+
|
| 17 |
+
import numpy as np
|
| 18 |
+
import soundfile as sf
|
| 19 |
+
from scipy.signal import welch
|
| 20 |
+
|
| 21 |
+
from .audio import AudioError, audio_info
|
| 22 |
+
from .guardian import label_event
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
@dataclass(frozen=True)
|
| 26 |
+
class RepairParams:
|
| 27 |
+
strength: float = 0.8 # Blend factor for just the selected click sample
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
def _impulses(x: np.ndarray, absolute_start: int, sr: int) -> list[dict]:
|
| 31 |
+
"""Find high-salience isolated, single-sample discontinuities.
|
| 32 |
+
|
| 33 |
+
Detection deliberately has high thresholds to prioritize false-negative
|
| 34 |
+
rather than false-positive results. No score is a probability.
|
| 35 |
+
"""
|
| 36 |
+
if x.shape[0] < 9:
|
| 37 |
+
return []
|
| 38 |
+
# x has 2D shape: frames x channels
|
| 39 |
+
center = x[1:-1]
|
| 40 |
+
left = x[:-2]
|
| 41 |
+
right = x[2:]
|
| 42 |
+
innovation = np.max(np.abs(center - 0.5 * (left + right)), axis=1)
|
| 43 |
+
# Robust local background for this block. Frequency-rich content naturally
|
| 44 |
+
# has large second derivatives; it will not pass the sharp outlier threshold.
|
| 45 |
+
p995 = float(np.percentile(innovation, 99.5))
|
| 46 |
+
threshold = max(0.065, p995 * 6.0)
|
| 47 |
+
candidates = np.flatnonzero(innovation > threshold)
|
| 48 |
+
hits = []
|
| 49 |
+
for offset in candidates:
|
| 50 |
+
idx = int(offset) + 1
|
| 51 |
+
# Opposite slopes (a single-sample impulse) and comparatively similar
|
| 52 |
+
# neighbors. Music transients can still pass: user review is mandatory.
|
| 53 |
+
a = x[idx] - x[idx - 1]
|
| 54 |
+
b = x[idx + 1] - x[idx]
|
| 55 |
+
channel = int(np.argmax(np.abs(x[idx] - .5 * (x[idx-1] + x[idx+1]))))
|
| 56 |
+
if a[channel] * b[channel] >= 0:
|
| 57 |
+
continue
|
| 58 |
+
if abs(x[idx-1,channel]-x[idx+1,channel]) > 0.28 * max(
|
| 59 |
+
abs(a[channel]), abs(b[channel]), 1e-8):
|
| 60 |
+
continue
|
| 61 |
+
score = float(innovation[offset] / max(threshold,1e-12))
|
| 62 |
+
hits.append({
|
| 63 |
+
"sample": int(absolute_start + idx),
|
| 64 |
+
"time_seconds": round((absolute_start + idx)/sr, 6),
|
| 65 |
+
"salience": round(min(score, 999), 3),
|
| 66 |
+
"kind": "single_sample_impulse_hypothesis",
|
| 67 |
+
"warning": "May be a genuine musical transient. Manual approval required.",
|
| 68 |
+
})
|
| 69 |
+
return hits
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
def _tonal_indicators(source: sf.SoundFile, samplerate: int, total_frames: int) -> list[dict]:
|
| 73 |
+
"""Very rough hum-frequency indicators, never identified as certain noise."""
|
| 74 |
+
size = min(total_frames, max(2048, 4 * samplerate))
|
| 75 |
+
if size < max(512, samplerate // 4):
|
| 76 |
+
return []
|
| 77 |
+
positions = sorted(set([0, max(0,(total_frames-size)//2), max(0,total_frames-size)]))
|
| 78 |
+
powers = []
|
| 79 |
+
for pos in positions:
|
| 80 |
+
source.seek(pos)
|
| 81 |
+
sample = source.read(size,dtype="float64",always_2d=True)
|
| 82 |
+
mono = np.mean(sample,axis=1)
|
| 83 |
+
nperseg=min(len(mono),max(4096, samplerate))
|
| 84 |
+
freq, density=welch(mono,fs=samplerate,nperseg=nperseg)
|
| 85 |
+
powers.append(density)
|
| 86 |
+
values = np.mean(powers,axis=0)
|
| 87 |
+
indicators = []
|
| 88 |
+
for hz in (50.0,60.0,100.0,120.0):
|
| 89 |
+
if hz >= samplerate*.48:
|
| 90 |
+
continue
|
| 91 |
+
idx=int(np.argmin(abs(freq-hz)))
|
| 92 |
+
floor = np.median(values[(freq>=hz-12)&(freq<=hz+12)])
|
| 93 |
+
ratio = float(values[idx] / max(floor, 1e-16))
|
| 94 |
+
if ratio>12.0 and values[idx]>1e-12:
|
| 95 |
+
indicators.append({
|
| 96 |
+
"frequency_hz": hz,
|
| 97 |
+
"peak_to_local_median_db": round(10*math.log10(ratio),2),
|
| 98 |
+
"classification": "ambiguous_tonal_peak",
|
| 99 |
+
"warning": "A bass note or musical harmonic can cause this peak. No notch applied."
|
| 100 |
+
})
|
| 101 |
+
return indicators
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
def inspect_noise_file(
|
| 105 |
+
input_path: Path,
|
| 106 |
+
progress: Callable[[float],None] | None=None,
|
| 107 |
+
chunk_frames: int=131072,
|
| 108 |
+
max_events: int=400
|
| 109 |
+
) -> dict:
|
| 110 |
+
"""Bounded-memory scan. No original modification, no auto repair."""
|
| 111 |
+
info = audio_info(input_path)
|
| 112 |
+
total = info.frames
|
| 113 |
+
events = []
|
| 114 |
+
total_hits = 0
|
| 115 |
+
last_hit = -1000000
|
| 116 |
+
guard = max(4, int(round(info.samplerate * 0.04)))
|
| 117 |
+
with sf.SoundFile(str(input_path),"r") as source:
|
| 118 |
+
for start in range(0,total,chunk_frames):
|
| 119 |
+
end=min(total,start+chunk_frames)
|
| 120 |
+
left=max(0,start-guard)
|
| 121 |
+
right=min(total,end+guard)
|
| 122 |
+
source.seek(left)
|
| 123 |
+
block=source.read(right-left,dtype="float64",always_2d=True)
|
| 124 |
+
if not np.isfinite(block).all() or len(block)!=(right-left):
|
| 125 |
+
raise AudioError("Nonfinite or truncated input.")
|
| 126 |
+
for event in _impulses(block,left,info.samplerate):
|
| 127 |
+
loc=event["sample"]
|
| 128 |
+
if not (start<=loc<end):
|
| 129 |
+
continue
|
| 130 |
+
# Suppress clusters within 2 milliseconds, which are less
|
| 131 |
+
# safely modeled as isolated one-sample clicks.
|
| 132 |
+
if loc-last_hit <= max(2,int(info.samplerate*.002)):
|
| 133 |
+
continue
|
| 134 |
+
event.update(label_event(block, loc-left, info.samplerate))
|
| 135 |
+
last_hit=loc
|
| 136 |
+
total_hits+=1
|
| 137 |
+
if len(events)<max_events:
|
| 138 |
+
events.append(event)
|
| 139 |
+
if progress:
|
| 140 |
+
progress(.87*(end/total))
|
| 141 |
+
tonal=_tonal_indicators(source,info.samplerate,total)
|
| 142 |
+
if progress:
|
| 143 |
+
progress(1.)
|
| 144 |
+
return {
|
| 145 |
+
"mode":"inspect_only",
|
| 146 |
+
"guardian_engine":"explainable_signal_heuristics_v0.5_NOT_neural_AI",
|
| 147 |
+
"protected_event_count":sum(not x.get("repair_allowed",False) for x in events),
|
| 148 |
+
"reviewable_event_count":sum(x.get("repair_allowed",False) for x in events),
|
| 149 |
+
"auto_repair":False,
|
| 150 |
+
"input_frames":total,
|
| 151 |
+
"samplerate":info.samplerate,
|
| 152 |
+
"events":events,
|
| 153 |
+
"event_count":total_hits,
|
| 154 |
+
"event_limit_reached":total_hits>len(events),
|
| 155 |
+
"tonal_indicators":tonal,
|
| 156 |
+
"noise_profile_ready":False,
|
| 157 |
+
"broadband_denoise_available":False,
|
| 158 |
+
"reason":"No noise-only region verified; automatic denoising could erase air, reverberation and tones.",
|
| 159 |
+
"notes":[
|
| 160 |
+
"Click and hum proposals are uncertain: musical transients and bass notes may be mistaken for noise.",
|
| 161 |
+
"Guardian protects possible musical attacks and correlated stereo impulses from repair.",
|
| 162 |
+
"Inspection does not alter music. Manual sample selection is required for any repair.",
|
| 163 |
+
"This version does not remove continuous hiss or tonal hum automatically."
|
| 164 |
+
]
|
| 165 |
+
}
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
def repair_noise_file(
|
| 169 |
+
input_path:Path,
|
| 170 |
+
output_dir:Path,
|
| 171 |
+
approved_samples:list[int],
|
| 172 |
+
params:RepairParams=RepairParams(),
|
| 173 |
+
progress: Callable[[float],None]|None=None,
|
| 174 |
+
chunk_frames:int=131072,
|
| 175 |
+
) -> tuple[dict,dict]:
|
| 176 |
+
"""Apply only approved repairs; create (original = clean + difference).
|
| 177 |
+
|
| 178 |
+
Uses an isolated-sample linear interpolation as a *hypothesis* for a
|
| 179 |
+
click. It cannot mathematically guarantee that no music is affected.
|
| 180 |
+
"""
|
| 181 |
+
if not (0<=params.strength<=1):
|
| 182 |
+
raise ValueError("Repair strength must be between 0 and 1.")
|
| 183 |
+
info=audio_info(input_path)
|
| 184 |
+
unique=sorted(set(int(x) for x in approved_samples))
|
| 185 |
+
if len(unique)>400 or any(x<2 or x>=info.frames-2 for x in unique):
|
| 186 |
+
raise ValueError("Invalid or excessive approved sample indices.")
|
| 187 |
+
output_dir.mkdir(parents=True,exist_ok=True)
|
| 188 |
+
max_err=0.0
|
| 189 |
+
changed=0
|
| 190 |
+
peak_change=0.0
|
| 191 |
+
energy=0.0
|
| 192 |
+
with ExitStack() as stack:
|
| 193 |
+
input_file=stack.enter_context(sf.SoundFile(str(input_path),"r"))
|
| 194 |
+
outs={}
|
| 195 |
+
for name in ("clean","difference"):
|
| 196 |
+
outs[name]=stack.enter_context(sf.SoundFile(
|
| 197 |
+
str(output_dir/f"{name}.wav"),"w",samplerate=info.samplerate,
|
| 198 |
+
channels=info.channels,format="WAV",subtype="FLOAT"))
|
| 199 |
+
outs[name+"_preview"]=stack.enter_context(sf.SoundFile(
|
| 200 |
+
str(output_dir/f"{name}_preview.wav"),"w",samplerate=info.samplerate,
|
| 201 |
+
channels=info.channels,format="WAV",subtype="PCM_16"))
|
| 202 |
+
cursor=0
|
| 203 |
+
for start in range(0,info.frames,chunk_frames):
|
| 204 |
+
end=min(info.frames,start+chunk_frames)
|
| 205 |
+
left=max(0,start-2)
|
| 206 |
+
right=min(info.frames,end+2)
|
| 207 |
+
input_file.seek(left)
|
| 208 |
+
x=input_file.read(right-left,dtype="float64",always_2d=True)
|
| 209 |
+
if len(x)!=right-left or not np.isfinite(x).all():
|
| 210 |
+
raise AudioError("Invalid or truncated audio.")
|
| 211 |
+
i0=start-left
|
| 212 |
+
original=x[i0:i0+end-start].copy()
|
| 213 |
+
clean=original.copy()
|
| 214 |
+
while cursor<len(unique) and unique[cursor]<end:
|
| 215 |
+
loc=unique[cursor]
|
| 216 |
+
if loc>=start:
|
| 217 |
+
index=loc-left
|
| 218 |
+
interp=.5*(x[index-1]+x[index+1])
|
| 219 |
+
clean[loc-start]=(1-params.strength)*x[index]+params.strength*interp
|
| 220 |
+
changed+=1
|
| 221 |
+
cursor+=1
|
| 222 |
+
difference=original-clean
|
| 223 |
+
reconstruction=np.max(np.abs(original-(clean+difference)))
|
| 224 |
+
max_err=max(max_err,float(reconstruction))
|
| 225 |
+
peak_change=max(peak_change,float(np.max(np.abs(difference))))
|
| 226 |
+
energy+=float(np.sum(np.square(difference),dtype=np.float64))
|
| 227 |
+
outs["clean"].write(clean)
|
| 228 |
+
outs["difference"].write(difference)
|
| 229 |
+
outs["clean_preview"].write(np.clip(clean,-1,1))
|
| 230 |
+
outs["difference_preview"].write(np.clip(difference,-1,1))
|
| 231 |
+
if progress:
|
| 232 |
+
progress(end/info.frames)
|
| 233 |
+
tracks={
|
| 234 |
+
name: {"name":name,"master":f"{name}.wav",
|
| 235 |
+
"preview":f"{name}_preview.wav","duration_seconds":round(info.frames/info.samplerate,4)}
|
| 236 |
+
for name in ("clean","difference")
|
| 237 |
+
}
|
| 238 |
+
report={
|
| 239 |
+
"mode":"manual_selected_single_sample_interpolation",
|
| 240 |
+
"selected_sample_count":len(unique),
|
| 241 |
+
"changed_sample_frames":changed,
|
| 242 |
+
"repair_strength":params.strength,
|
| 243 |
+
"peak_absolute_change":peak_change,
|
| 244 |
+
"difference_rms":math.sqrt(energy/(info.frames*info.channels)),
|
| 245 |
+
"reconstruction_max_absolute_error":max_err,
|
| 246 |
+
"reconstruction_consistent":max_err<1e-10,
|
| 247 |
+
"no_auto_denoise":True,
|
| 248 |
+
"warning":"A removed signal may contain authentic music. Listen to the difference stem.",
|
| 249 |
+
"original_file_untouched":True,
|
| 250 |
+
"master_format":"WAV float32",
|
| 251 |
+
"preview_format":"WAV PCM16 (listening only)",
|
| 252 |
+
}
|
| 253 |
+
return tracks, report
|
app/server.py
CHANGED
|
@@ -22,6 +22,12 @@ from fastapi.responses import FileResponse, JSONResponse
|
|
| 22 |
from fastapi.staticfiles import StaticFiles
|
| 23 |
from pydantic import BaseModel, Field
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
from .audio import (
|
| 26 |
AudioError, align_and_resample, analyze_file, hpss_separate_file,
|
| 27 |
load_audio, mixture_report, save_stems, sha256_file,
|
|
@@ -31,6 +37,8 @@ from .audio import (
|
|
| 31 |
# Configure ABSOLUTION_MAX_UPLOAD_MIB to fit your available storage.
|
| 32 |
MAX_UPLOAD_MIB = max(1, min(4096, int(os.environ.get("ABSOLUTION_MAX_UPLOAD_MIB", "1024"))))
|
| 33 |
MAX_UPLOAD_BYTES = MAX_UPLOAD_MIB * 1024 * 1024
|
|
|
|
|
|
|
| 34 |
ALLOWED_EXTENSIONS = {".wav", ".flac", ".aif", ".aiff", ".mp3", ".ogg"}
|
| 35 |
|
| 36 |
|
|
@@ -55,6 +63,67 @@ class SeparationRequest(BaseModel):
|
|
| 55 |
target_description: str = Field(default="", max_length=300)
|
| 56 |
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
class Service:
|
| 59 |
def __init__(self, data_root: Path):
|
| 60 |
self.data_root = data_root.resolve()
|
|
@@ -88,11 +157,53 @@ class Service:
|
|
| 88 |
manifest = {
|
| 89 |
"id": project_id, "name": name, "created_at": timestamp(),
|
| 90 |
"asset": None, "analysis": None, "stems": {},
|
| 91 |
-
"separation": None, "report": None,
|
|
|
|
| 92 |
}
|
| 93 |
self.write_manifest(project_id, manifest)
|
| 94 |
return manifest
|
| 95 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
def model_info(self) -> list[dict]:
|
| 97 |
local = Path(self.model_repo).expanduser() if self.model_repo else None
|
| 98 |
configured = bool(local and local.is_dir() and
|
|
@@ -108,7 +219,7 @@ class Service:
|
|
| 108 |
"id": "demucs", "name": "Demucs HT v4 · neural (local weights)",
|
| 109 |
"ready": configured, "type": "neural_network",
|
| 110 |
"stems": ["drums", "bass", "other", "vocals", "residual"],
|
| 111 |
-
"limitations": ("Requires trusted local htdemucs weights/config
|
| 112 |
"demucs/torch dependencies. No automatic downloads."),
|
| 113 |
},
|
| 114 |
]
|
|
@@ -121,6 +232,12 @@ class Service:
|
|
| 121 |
raise HTTPException(status_code=409, detail="Import audio before separation.")
|
| 122 |
if request.model == "demucs" and not self.model_info()[1]["ready"]:
|
| 123 |
raise HTTPException(status_code=409, detail="Demucs not configured; local checkpoints required.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
if request.target_description.strip() and request.model == "hpss":
|
| 125 |
raise HTTPException(status_code=422, detail="HPSS cannot follow arbitrary text prompts.")
|
| 126 |
# Explicitly reject the unsupported "text conditioned" interpretation for neural.
|
|
@@ -137,6 +254,171 @@ class Service:
|
|
| 137 |
self.executor.submit(self.run_job, job["id"])
|
| 138 |
return dict(job)
|
| 139 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
def update_job(self, job_id: str, **kwargs) -> None:
|
| 141 |
with self.lock:
|
| 142 |
self.jobs[job_id].update(kwargs)
|
|
@@ -213,10 +495,24 @@ class Service:
|
|
| 213 |
return stems
|
| 214 |
|
| 215 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
def create_app(data_root: Path | None = None) -> FastAPI:
|
| 217 |
default = Path(os.environ.get("ABSOLUTION_DATA_DIR", "./omega_data"))
|
| 218 |
-
|
| 219 |
-
|
|
|
|
|
|
|
| 220 |
description="Local-first audio forensic vertical slice")
|
| 221 |
app.state.service = service
|
| 222 |
static_dir = Path(__file__).parent / "static"
|
|
@@ -236,7 +532,7 @@ def create_app(data_root: Path | None = None) -> FastAPI:
|
|
| 236 |
|
| 237 |
@app.get("/api/v1/health")
|
| 238 |
def health():
|
| 239 |
-
return {"status": "ok", "version": "0.
|
| 240 |
"network_downloads": False, "auth": False,
|
| 241 |
"max_upload_bytes": MAX_UPLOAD_BYTES,
|
| 242 |
"duration_limit_seconds": None, "streaming_hpss": True}
|
|
@@ -310,6 +606,172 @@ def create_app(data_root: Path | None = None) -> FastAPI:
|
|
| 310 |
except (ValueError, KeyError) as exc:
|
| 311 |
raise HTTPException(status_code=404, detail="Job not found.") from exc
|
| 312 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 313 |
@app.get("/api/v1/projects/{project_id}/stems")
|
| 314 |
def get_stems(project_id: str):
|
| 315 |
manifest = service.manifest(project_id)
|
|
|
|
| 22 |
from fastapi.staticfiles import StaticFiles
|
| 23 |
from pydantic import BaseModel, Field
|
| 24 |
|
| 25 |
+
from .bass import BassParams, TRACKS, process_bass_file
|
| 26 |
+
from .noise import RepairParams, inspect_noise_file, repair_noise_file
|
| 27 |
+
from .virtualbass import available as virtualbass_available, render_virtualbass
|
| 28 |
+
from .mini_model import inspect_file as inspect_mini, MODEL_FILE
|
| 29 |
+
from .mixer import render_mix, sampled_peaks, rubberband_available
|
| 30 |
+
|
| 31 |
from .audio import (
|
| 32 |
AudioError, align_and_resample, analyze_file, hpss_separate_file,
|
| 33 |
load_audio, mixture_report, save_stems, sha256_file,
|
|
|
|
| 37 |
# Configure ABSOLUTION_MAX_UPLOAD_MIB to fit your available storage.
|
| 38 |
MAX_UPLOAD_MIB = max(1, min(4096, int(os.environ.get("ABSOLUTION_MAX_UPLOAD_MIB", "1024"))))
|
| 39 |
MAX_UPLOAD_BYTES = MAX_UPLOAD_MIB * 1024 * 1024
|
| 40 |
+
# Demucs on shared CPU hardware: cap input duration (0 = unlimited).
|
| 41 |
+
DEMUCS_MAX_SECONDS = float(os.environ.get("ABSOLUTION_DEMUCS_MAX_SECONDS", "0"))
|
| 42 |
ALLOWED_EXTENSIONS = {".wav", ".flac", ".aif", ".aiff", ".mp3", ".ogg"}
|
| 43 |
|
| 44 |
|
|
|
|
| 63 |
target_description: str = Field(default="", max_length=300)
|
| 64 |
|
| 65 |
|
| 66 |
+
class BassRequest(BaseModel):
|
| 67 |
+
project_id: str
|
| 68 |
+
source_mode: Literal["auto", "dsp", "hpss", "demucs"] = "auto"
|
| 69 |
+
crossover_hz: float = Field(default=220, ge=45, le=350)
|
| 70 |
+
kick_focus: float = Field(default=0.75, ge=0, le=1)
|
| 71 |
+
kick_gain_db: float = Field(default=0, ge=-12, le=12)
|
| 72 |
+
bass_gain_db: float = Field(default=0, ge=-12, le=12)
|
| 73 |
+
sub_gain_db: float = Field(default=0, ge=-12, le=12)
|
| 74 |
+
harmonics: float = Field(default=0.20, ge=0, le=1)
|
| 75 |
+
lowcut_hz: float = Field(default=22, ge=10, le=45)
|
| 76 |
+
mono_below_hz: float = Field(default=100, ge=0, le=180)
|
| 77 |
+
wet: float = Field(default=1, ge=0, le=1)
|
| 78 |
+
ceiling_dbfs: float = Field(default=-1, ge=-6, le=-0.1)
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
class NoiseScanRequest(BaseModel):
|
| 82 |
+
project_id: str
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
class NoiseRepairRequest(BaseModel):
|
| 86 |
+
project_id: str
|
| 87 |
+
approved_samples: list[int] = Field(default_factory=list, max_length=400)
|
| 88 |
+
strength: float = Field(default=0.8, ge=0, le=1)
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
class VirtualBassRequest(BaseModel):
|
| 93 |
+
project_id: str
|
| 94 |
+
cutoff_hz: float = Field(default=250, ge=100, le=500)
|
| 95 |
+
strength: float = Field(default=1.0, ge=0.5, le=3.0)
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
class TrackMix(BaseModel):
|
| 100 |
+
gain_db: float = Field(default=0, ge=-48, le=12)
|
| 101 |
+
pan: float = Field(default=0, ge=-1, le=1)
|
| 102 |
+
mute: bool = False
|
| 103 |
+
solo: bool = False
|
| 104 |
+
highpass_hz: float = Field(default=0, ge=0, le=400)
|
| 105 |
+
lowpass_hz: float = Field(default=0, ge=0, le=18000)
|
| 106 |
+
width: float = Field(default=1, ge=0, le=2)
|
| 107 |
+
drive: float = Field(default=0, ge=0, le=1)
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
class MixerRequest(BaseModel):
|
| 111 |
+
project_id: str
|
| 112 |
+
tracks: dict[str, TrackMix] = Field(default_factory=dict)
|
| 113 |
+
tempo: float = Field(default=1, ge=0.5, le=2)
|
| 114 |
+
pitch_semitones: float = Field(default=0, ge=-12, le=12)
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
class PlannedTrack(BaseModel):
|
| 118 |
+
id: str = Field(min_length=1, max_length=60, pattern=r"^[a-z0-9_-]+$")
|
| 119 |
+
label: str = Field(min_length=1, max_length=100)
|
| 120 |
+
enabled: bool = True
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
class PlanRequest(BaseModel):
|
| 124 |
+
tracks: list[PlannedTrack] = Field(max_length=128)
|
| 125 |
+
|
| 126 |
+
|
| 127 |
class Service:
|
| 128 |
def __init__(self, data_root: Path):
|
| 129 |
self.data_root = data_root.resolve()
|
|
|
|
| 157 |
manifest = {
|
| 158 |
"id": project_id, "name": name, "created_at": timestamp(),
|
| 159 |
"asset": None, "analysis": None, "stems": {},
|
| 160 |
+
"separation": None, "report": None, "bass": None, "noise": None, "virtualbass": None,
|
| 161 |
+
"inventory": None, "plan": [], "mixer": None,
|
| 162 |
}
|
| 163 |
self.write_manifest(project_id, manifest)
|
| 164 |
return manifest
|
| 165 |
|
| 166 |
+
def create_mixer_job(self, request: MixerRequest) -> dict:
|
| 167 |
+
project_id=check_id(request.project_id)
|
| 168 |
+
with self.lock:
|
| 169 |
+
manifest=self.manifest(project_id)
|
| 170 |
+
if not manifest.get("stems"):
|
| 171 |
+
raise HTTPException(status_code=409,detail="Run actual separation first; planned labels are not audio.")
|
| 172 |
+
unknown=set(request.tracks)-set(manifest["stems"])
|
| 173 |
+
if unknown:
|
| 174 |
+
raise HTTPException(status_code=422,detail="Unknown real stems: "+", ".join(sorted(unknown)))
|
| 175 |
+
if len(manifest["stems"])>128:
|
| 176 |
+
raise HTTPException(status_code=422,detail="More than 128 stems not supported for one render.")
|
| 177 |
+
if (request.tempo!=1 or request.pitch_semitones!=0) and not rubberband_available():
|
| 178 |
+
raise HTTPException(status_code=422,detail="FFmpeg with rubberband is required for independent tempo/pitch.")
|
| 179 |
+
if any(j["project_id"]==project_id and j["status"] in ("queued","running")
|
| 180 |
+
for j in self.jobs.values()):
|
| 181 |
+
raise HTTPException(status_code=409,detail="Project already processing.")
|
| 182 |
+
job={"id":str(uuid.uuid4()),"project_id":project_id,
|
| 183 |
+
"model":"arrangement_mixer","kind":"mix","status":"queued",
|
| 184 |
+
"progress":0,"created_at":timestamp(),"error":None}
|
| 185 |
+
self.jobs[job["id"]]=job
|
| 186 |
+
self.executor.submit(self.run_mixer_job,job["id"],request.model_dump())
|
| 187 |
+
return dict(job)
|
| 188 |
+
|
| 189 |
+
def run_mixer_job(self, job_id: str, settings:dict):
|
| 190 |
+
job=self.jobs[job_id];project_id=job["project_id"]
|
| 191 |
+
try:
|
| 192 |
+
self.update_job(job_id,status="running",progress=3)
|
| 193 |
+
manifest=self.manifest(project_id);folder=self.folder(project_id)
|
| 194 |
+
sources={name:folder/"stems"/data["master"] for name,data in manifest["stems"].items()}
|
| 195 |
+
output=folder/"mixer"/(job_id+".wav")
|
| 196 |
+
result=render_mix(sources,settings,output,
|
| 197 |
+
progress=lambda r:self.update_job(job_id,progress=3+int(r*90)))
|
| 198 |
+
with self.lock:
|
| 199 |
+
newest=self.manifest(project_id)
|
| 200 |
+
newest["mixer"]={"id":job_id,"file":output.name,"settings":settings,
|
| 201 |
+
"result":result,"created_at":timestamp()}
|
| 202 |
+
self.write_manifest(project_id,newest)
|
| 203 |
+
self.update_job(job_id,status="done",progress=100)
|
| 204 |
+
except Exception as exc:
|
| 205 |
+
self.update_job(job_id,status="failed",error=f"{type(exc).__name__}: {exc}")
|
| 206 |
+
|
| 207 |
def model_info(self) -> list[dict]:
|
| 208 |
local = Path(self.model_repo).expanduser() if self.model_repo else None
|
| 209 |
configured = bool(local and local.is_dir() and
|
|
|
|
| 219 |
"id": "demucs", "name": "Demucs HT v4 · neural (local weights)",
|
| 220 |
"ready": configured, "type": "neural_network",
|
| 221 |
"stems": ["drums", "bass", "other", "vocals", "residual"],
|
| 222 |
+
"limitations": ("Requires trusted local htdemucs weights/config (official checkpoint 955717e8) and "
|
| 223 |
"demucs/torch dependencies. No automatic downloads."),
|
| 224 |
},
|
| 225 |
]
|
|
|
|
| 232 |
raise HTTPException(status_code=409, detail="Import audio before separation.")
|
| 233 |
if request.model == "demucs" and not self.model_info()[1]["ready"]:
|
| 234 |
raise HTTPException(status_code=409, detail="Demucs not configured; local checkpoints required.")
|
| 235 |
+
if request.model == "demucs" and DEMUCS_MAX_SECONDS > 0:
|
| 236 |
+
duration = float((manifest.get("analysis") or {}).get("duration_seconds") or 0)
|
| 237 |
+
if duration > DEMUCS_MAX_SECONDS:
|
| 238 |
+
raise HTTPException(status_code=413, detail=(
|
| 239 |
+
f"Demucs on this CPU instance is limited to {DEMUCS_MAX_SECONDS:g} s audio "
|
| 240 |
+
f"(file: {duration:.0f} s). Use HPSS or run locally."))
|
| 241 |
if request.target_description.strip() and request.model == "hpss":
|
| 242 |
raise HTTPException(status_code=422, detail="HPSS cannot follow arbitrary text prompts.")
|
| 243 |
# Explicitly reject the unsupported "text conditioned" interpretation for neural.
|
|
|
|
| 254 |
self.executor.submit(self.run_job, job["id"])
|
| 255 |
return dict(job)
|
| 256 |
|
| 257 |
+
def create_bass_job(self, request: BassRequest) -> dict:
|
| 258 |
+
project_id = check_id(request.project_id)
|
| 259 |
+
with self.lock:
|
| 260 |
+
manifest = self.manifest(project_id)
|
| 261 |
+
if not manifest["asset"]:
|
| 262 |
+
raise HTTPException(status_code=409, detail="Import audio before BASS-CORE.")
|
| 263 |
+
active = any(j["project_id"] == project_id and j["status"] in ("queued", "running")
|
| 264 |
+
for j in self.jobs.values())
|
| 265 |
+
if active:
|
| 266 |
+
raise HTTPException(status_code=409, detail="A project job is already running.")
|
| 267 |
+
stems = manifest.get("stems") or {}
|
| 268 |
+
separation = (manifest.get("separation") or {}).get("method")
|
| 269 |
+
valid_hpss = separation == "hpss" and all(k in stems for k in ("harmonic","percussive"))
|
| 270 |
+
valid_neural = separation == "demucs" and all(k in stems for k in ("bass","drums"))
|
| 271 |
+
mode = request.source_mode
|
| 272 |
+
if mode == "auto":
|
| 273 |
+
mode = "demucs" if valid_neural else "hpss" if valid_hpss else "dsp"
|
| 274 |
+
if mode == "hpss" and not valid_hpss:
|
| 275 |
+
raise HTTPException(status_code=409, detail="Run HPSS separation first.")
|
| 276 |
+
if mode == "demucs" and not valid_neural:
|
| 277 |
+
raise HTTPException(status_code=409, detail="Run Demucs bass/drums separation first.")
|
| 278 |
+
job = {
|
| 279 |
+
"id": str(uuid.uuid4()), "project_id": project_id, "model": "basscore",
|
| 280 |
+
"mode": mode, "kind": "bass", "status": "queued", "progress": 0,
|
| 281 |
+
"created_at": timestamp(), "error": None,
|
| 282 |
+
}
|
| 283 |
+
self.jobs[job["id"]] = job
|
| 284 |
+
self.executor.submit(self.run_bass_job, job["id"], request)
|
| 285 |
+
return dict(job)
|
| 286 |
+
|
| 287 |
+
def run_bass_job(self, job_id: str, request: BassRequest) -> None:
|
| 288 |
+
job = self.jobs[job_id]
|
| 289 |
+
project_id, mode = job["project_id"], job["mode"]
|
| 290 |
+
try:
|
| 291 |
+
self.update_job(job_id, status="running", progress=5)
|
| 292 |
+
manifest = self.manifest(project_id)
|
| 293 |
+
folder = self.folder(project_id)
|
| 294 |
+
refs = {}
|
| 295 |
+
wanted = {"dsp": (), "hpss": ("harmonic","percussive"),
|
| 296 |
+
"demucs": ("bass","drums")}[mode]
|
| 297 |
+
for name in wanted:
|
| 298 |
+
refs[name] = folder / "stems" / manifest["stems"][name]["master"]
|
| 299 |
+
settings = BassParams(**request.model_dump(exclude={"project_id","source_mode"}))
|
| 300 |
+
out = folder / "basscore" / job_id
|
| 301 |
+
stems, report = process_bass_file(
|
| 302 |
+
folder / manifest["asset"]["stored_name"], out, settings,
|
| 303 |
+
mode=mode, refs=refs,
|
| 304 |
+
progress=lambda ratio:self.update_job(job_id, progress=5 + int(90 * ratio)),
|
| 305 |
+
)
|
| 306 |
+
result = {"id": job_id, "completed_at": timestamp(), "mode": mode,
|
| 307 |
+
"source_sha256": manifest["asset"]["sha256"],
|
| 308 |
+
"stems": stems, "report": report}
|
| 309 |
+
with self.lock:
|
| 310 |
+
updated = self.manifest(project_id)
|
| 311 |
+
updated["bass"] = result
|
| 312 |
+
self.write_manifest(project_id, updated)
|
| 313 |
+
self.update_job(job_id, status="done", progress=100)
|
| 314 |
+
except Exception as exc:
|
| 315 |
+
self.update_job(job_id, status="failed", error=f"{type(exc).__name__}: {exc}")
|
| 316 |
+
|
| 317 |
+
def create_noise_job(self, project_id: str, action: str,
|
| 318 |
+
approved: list[int] | None=None, strength: float=0.8) -> dict:
|
| 319 |
+
project_id=check_id(project_id)
|
| 320 |
+
with self.lock:
|
| 321 |
+
manifest=self.manifest(project_id)
|
| 322 |
+
if not manifest.get("asset"):
|
| 323 |
+
raise HTTPException(status_code=409,detail="Import audio before NOISE-CORE.")
|
| 324 |
+
if any(j["project_id"]==project_id and j["status"] in ("queued","running")
|
| 325 |
+
for j in self.jobs.values()):
|
| 326 |
+
raise HTTPException(status_code=409,detail="A project job is already running.")
|
| 327 |
+
if action=="repair":
|
| 328 |
+
scan=(manifest.get("noise") or {}).get("scan")
|
| 329 |
+
if not scan:
|
| 330 |
+
raise HTTPException(status_code=409,detail="Scan for click hypotheses first.")
|
| 331 |
+
allowed={event["sample"] for event in scan["events"]}
|
| 332 |
+
if not set(approved or []).issubset(allowed):
|
| 333 |
+
raise HTTPException(status_code=422,detail="Repair only confirmed scan events.")
|
| 334 |
+
if not approved:
|
| 335 |
+
raise HTTPException(status_code=422,detail="Select at least one click candidate.")
|
| 336 |
+
job={
|
| 337 |
+
"id":str(uuid.uuid4()),"project_id":project_id,
|
| 338 |
+
"model":"noisecore","kind":"noise_"+action,
|
| 339 |
+
"status":"queued","progress":0,"created_at":timestamp(),"error":None,
|
| 340 |
+
}
|
| 341 |
+
self.jobs[job["id"]]=job
|
| 342 |
+
self.executor.submit(self.run_noise_job,job["id"],action,approved or [],strength)
|
| 343 |
+
return dict(job)
|
| 344 |
+
|
| 345 |
+
def run_noise_job(self, job_id:str, action:str, approved:list[int], strength:float)->None:
|
| 346 |
+
project_id=self.jobs[job_id]["project_id"]
|
| 347 |
+
try:
|
| 348 |
+
self.update_job(job_id,status="running",progress=3)
|
| 349 |
+
manifest=self.manifest(project_id)
|
| 350 |
+
folder=self.folder(project_id)
|
| 351 |
+
source=folder/manifest["asset"]["stored_name"]
|
| 352 |
+
callback=lambda ratio:self.update_job(job_id,progress=5+int(90*ratio))
|
| 353 |
+
if action=="scan":
|
| 354 |
+
scan=inspect_noise_file(source,progress=callback)
|
| 355 |
+
with self.lock:
|
| 356 |
+
updated=self.manifest(project_id)
|
| 357 |
+
# Old repair, if any, must not be attached to a new scan.
|
| 358 |
+
updated["noise"]={"scan":scan,"repair":None,
|
| 359 |
+
"source_sha256":manifest["asset"]["sha256"],
|
| 360 |
+
"scanned_at":timestamp()}
|
| 361 |
+
self.write_manifest(project_id,updated)
|
| 362 |
+
else:
|
| 363 |
+
root=folder/"noisecore"/job_id
|
| 364 |
+
tracks,report=repair_noise_file(
|
| 365 |
+
source,root,approved,RepairParams(strength),progress=callback)
|
| 366 |
+
with self.lock:
|
| 367 |
+
updated=self.manifest(project_id)
|
| 368 |
+
updated["noise"]["repair"]={
|
| 369 |
+
"id":job_id,"completed_at":timestamp(),
|
| 370 |
+
"source_sha256":manifest["asset"]["sha256"],
|
| 371 |
+
"tracks":tracks,"report":report,
|
| 372 |
+
}
|
| 373 |
+
self.write_manifest(project_id,updated)
|
| 374 |
+
self.update_job(job_id,status="done",progress=100)
|
| 375 |
+
except Exception as exc:
|
| 376 |
+
self.update_job(job_id,status="failed",error=f"{type(exc).__name__}: {exc}")
|
| 377 |
+
|
| 378 |
+
def create_virtualbass_job(self, request: VirtualBassRequest) -> dict:
|
| 379 |
+
pid=check_id(request.project_id)
|
| 380 |
+
with self.lock:
|
| 381 |
+
manifest=self.manifest(pid)
|
| 382 |
+
if not manifest.get("asset"):
|
| 383 |
+
raise HTTPException(status_code=409,detail="Import stereo audio first.")
|
| 384 |
+
if not virtualbass_available():
|
| 385 |
+
raise HTTPException(status_code=409,detail="FFmpeg virtualbass filter not available locally.")
|
| 386 |
+
if manifest["analysis"]["channels"]!=2:
|
| 387 |
+
raise HTTPException(status_code=422,detail="Virtualbass requires two-channel stereo.")
|
| 388 |
+
if any(j["project_id"]==pid and j["status"] in ("queued","running")
|
| 389 |
+
for j in self.jobs.values()):
|
| 390 |
+
raise HTTPException(status_code=409,detail="Project has a running job.")
|
| 391 |
+
job={"id":str(uuid.uuid4()),"project_id":pid,"model":"ffmpeg_virtualbass",
|
| 392 |
+
"kind":"virtualbass","status":"queued","progress":0,
|
| 393 |
+
"created_at":timestamp(),"error":None}
|
| 394 |
+
self.jobs[job["id"]]=job
|
| 395 |
+
self.executor.submit(self.run_virtualbass_job,job["id"],request)
|
| 396 |
+
return dict(job)
|
| 397 |
+
|
| 398 |
+
def run_virtualbass_job(self, job_id:str, request:VirtualBassRequest) -> None:
|
| 399 |
+
job=self.jobs[job_id]
|
| 400 |
+
pid=job["project_id"]
|
| 401 |
+
try:
|
| 402 |
+
self.update_job(job_id,status="running",progress=10)
|
| 403 |
+
manifest=self.manifest(pid)
|
| 404 |
+
folder=self.folder(pid)
|
| 405 |
+
target=folder/"virtualbass"/job_id/"virtualbass_2_1.wav"
|
| 406 |
+
report=render_virtualbass(
|
| 407 |
+
folder/manifest["asset"]["stored_name"],target,
|
| 408 |
+
cutoff_hz=request.cutoff_hz,strength=request.strength
|
| 409 |
+
)
|
| 410 |
+
self.update_job(job_id,progress=95)
|
| 411 |
+
with self.lock:
|
| 412 |
+
updated=self.manifest(pid)
|
| 413 |
+
updated["virtualbass"]={
|
| 414 |
+
"id":job_id,"source_sha256":manifest["asset"]["sha256"],
|
| 415 |
+
"completed_at":timestamp(),"report":report,
|
| 416 |
+
}
|
| 417 |
+
self.write_manifest(pid,updated)
|
| 418 |
+
self.update_job(job_id,status="done",progress=100)
|
| 419 |
+
except Exception as exc:
|
| 420 |
+
self.update_job(job_id,status="failed",error=f"{type(exc).__name__}: {exc}")
|
| 421 |
+
|
| 422 |
def update_job(self, job_id: str, **kwargs) -> None:
|
| 423 |
with self.lock:
|
| 424 |
self.jobs[job_id].update(kwargs)
|
|
|
|
| 495 |
return stems
|
| 496 |
|
| 497 |
|
| 498 |
+
def writable_dir(preferred: Path, fallback: Path) -> Path:
|
| 499 |
+
"""Use the persistent mount (e.g. HF bucket at /data) if writable, else fallback."""
|
| 500 |
+
try:
|
| 501 |
+
preferred.mkdir(parents=True, exist_ok=True)
|
| 502 |
+
probe = preferred / f".probe-{uuid.uuid4().hex}"
|
| 503 |
+
probe.write_text("ok"); probe.unlink()
|
| 504 |
+
return preferred
|
| 505 |
+
except OSError:
|
| 506 |
+
fallback.mkdir(parents=True, exist_ok=True)
|
| 507 |
+
return fallback
|
| 508 |
+
|
| 509 |
+
|
| 510 |
def create_app(data_root: Path | None = None) -> FastAPI:
|
| 511 |
default = Path(os.environ.get("ABSOLUTION_DATA_DIR", "./omega_data"))
|
| 512 |
+
if data_root is None:
|
| 513 |
+
data_root = writable_dir(default, Path(os.environ.get("ABSOLUTION_FALLBACK_DIR", "/tmp/omega_data")))
|
| 514 |
+
service = Service(data_root)
|
| 515 |
+
app = FastAPI(title="ABSOLUTION Ω", version="0.6.0",
|
| 516 |
description="Local-first audio forensic vertical slice")
|
| 517 |
app.state.service = service
|
| 518 |
static_dir = Path(__file__).parent / "static"
|
|
|
|
| 532 |
|
| 533 |
@app.get("/api/v1/health")
|
| 534 |
def health():
|
| 535 |
+
return {"status": "ok", "version": "0.6.0", "arrangement_studio": True, "mini_tag_model_ready": MODEL_FILE.is_file(), "rubberband_ready": rubberband_available(), "basscore": True, "noisecore": True, "virtualbass_ready": virtualbass_available(), "job_backend": "process-local", "data_dir": str(service.data_root), "persistent_storage": str(service.data_root).startswith("/data"), "demucs_max_seconds": DEMUCS_MAX_SECONDS or None,
|
| 536 |
"network_downloads": False, "auth": False,
|
| 537 |
"max_upload_bytes": MAX_UPLOAD_BYTES,
|
| 538 |
"duration_limit_seconds": None, "streaming_hpss": True}
|
|
|
|
| 606 |
except (ValueError, KeyError) as exc:
|
| 607 |
raise HTTPException(status_code=404, detail="Job not found.") from exc
|
| 608 |
|
| 609 |
+
@app.post("/api/v1/jobs/bass", status_code=202)
|
| 610 |
+
def bass_job(request: BassRequest):
|
| 611 |
+
return service.create_bass_job(request)
|
| 612 |
+
|
| 613 |
+
@app.get("/api/v1/projects/{project_id}/bass")
|
| 614 |
+
def bass_results(project_id: str):
|
| 615 |
+
result = service.manifest(project_id).get("bass")
|
| 616 |
+
return {"bass": result}
|
| 617 |
+
|
| 618 |
+
@app.get("/api/v1/projects/{project_id}/bass/audio/{track}")
|
| 619 |
+
def bass_audio(project_id: str, track: str, preview: bool = False):
|
| 620 |
+
manifest = service.manifest(project_id)
|
| 621 |
+
result = manifest.get("bass")
|
| 622 |
+
if not result or track not in TRACKS or track not in result["stems"]:
|
| 623 |
+
raise HTTPException(status_code=404, detail="Bass track not found.")
|
| 624 |
+
info = result["stems"][track]
|
| 625 |
+
key = "preview" if preview else "master"
|
| 626 |
+
path = service.folder(project_id) / "basscore" / result["id"] / info[key]
|
| 627 |
+
if not path.is_file():
|
| 628 |
+
raise HTTPException(status_code=404, detail="Bass track not found.")
|
| 629 |
+
return FileResponse(path, media_type="audio/wav", filename=path.name)
|
| 630 |
+
|
| 631 |
+
@app.get("/api/v1/projects/{project_id}/bass/export")
|
| 632 |
+
def bass_export(project_id: str):
|
| 633 |
+
manifest = service.manifest(project_id)
|
| 634 |
+
result = manifest.get("bass")
|
| 635 |
+
if not result:
|
| 636 |
+
raise HTTPException(status_code=409, detail="Run BASS-CORE before exporting.")
|
| 637 |
+
folder = service.folder(project_id)
|
| 638 |
+
root = folder / "basscore" / result["id"]
|
| 639 |
+
target = root / "BASS_CORE_EXPORT.zip"
|
| 640 |
+
tmp = root / f".{uuid.uuid4().hex}.zip"
|
| 641 |
+
with zipfile.ZipFile(tmp, "w", compression=zipfile.ZIP_STORED) as archive:
|
| 642 |
+
archive.writestr("bass_report.json", json.dumps(result,indent=2,ensure_ascii=False))
|
| 643 |
+
for name, entry in result["stems"].items():
|
| 644 |
+
archive.write(root / entry["master"], f"stems/{entry['master']}")
|
| 645 |
+
tmp.replace(target)
|
| 646 |
+
return FileResponse(target,media_type="application/zip",filename="ABSOLUTION_BASS_CORE.zip")
|
| 647 |
+
|
| 648 |
+
@app.post("/api/v1/jobs/noise/scan",status_code=202)
|
| 649 |
+
def noise_scan(request:NoiseScanRequest):
|
| 650 |
+
return service.create_noise_job(request.project_id,"scan")
|
| 651 |
+
|
| 652 |
+
@app.post("/api/v1/jobs/noise/repair",status_code=202)
|
| 653 |
+
def noise_repair(request:NoiseRepairRequest):
|
| 654 |
+
return service.create_noise_job(request.project_id,"repair",
|
| 655 |
+
request.approved_samples,request.strength)
|
| 656 |
+
|
| 657 |
+
@app.get("/api/v1/projects/{project_id}/noise")
|
| 658 |
+
def noise_results(project_id:str):
|
| 659 |
+
return {"noise":service.manifest(project_id).get("noise")}
|
| 660 |
+
|
| 661 |
+
@app.get("/api/v1/projects/{project_id}/noise/audio/{track}")
|
| 662 |
+
def noise_audio(project_id:str, track:str, preview:bool=False):
|
| 663 |
+
result=(service.manifest(project_id).get("noise") or {}).get("repair")
|
| 664 |
+
if not result or track not in ("clean","difference"):
|
| 665 |
+
raise HTTPException(status_code=404,detail="NOISE-CORE track not found.")
|
| 666 |
+
item=result["tracks"][track]
|
| 667 |
+
path=service.folder(project_id)/"noisecore"/result["id"]/item[
|
| 668 |
+
"preview" if preview else "master"]
|
| 669 |
+
if not path.is_file():
|
| 670 |
+
raise HTTPException(status_code=404,detail="NOISE-CORE file not found.")
|
| 671 |
+
return FileResponse(path,media_type="audio/wav",filename=path.name)
|
| 672 |
+
|
| 673 |
+
@app.get("/api/v1/projects/{project_id}/noise/export")
|
| 674 |
+
def noise_export(project_id:str):
|
| 675 |
+
result=(service.manifest(project_id).get("noise") or {}).get("repair")
|
| 676 |
+
if not result:
|
| 677 |
+
raise HTTPException(status_code=409,detail="Approve and render repairs first.")
|
| 678 |
+
folder=service.folder(project_id)/"noisecore"/result["id"]
|
| 679 |
+
tmp=folder/f".{uuid.uuid4().hex}.zip"
|
| 680 |
+
target=folder/"NOISE_CORE_EXPORT.zip"
|
| 681 |
+
with zipfile.ZipFile(tmp,"w",compression=zipfile.ZIP_STORED) as archive:
|
| 682 |
+
archive.writestr("report.json",json.dumps(result,indent=2,ensure_ascii=False))
|
| 683 |
+
for name,entry in result["tracks"].items():
|
| 684 |
+
archive.write(folder/entry["master"],f"tracks/{entry['master']}")
|
| 685 |
+
tmp.replace(target)
|
| 686 |
+
return FileResponse(target,media_type="application/zip",
|
| 687 |
+
filename="ABSOLUTION_NOISE_CORE.zip")
|
| 688 |
+
|
| 689 |
+
@app.post("/api/v1/jobs/bass/virtual",status_code=202)
|
| 690 |
+
def create_virtual(request:VirtualBassRequest):
|
| 691 |
+
return service.create_virtualbass_job(request)
|
| 692 |
+
|
| 693 |
+
@app.get("/api/v1/projects/{project_id}/virtualbass")
|
| 694 |
+
def virtual_result(project_id:str):
|
| 695 |
+
return {"virtualbass":service.manifest(project_id).get("virtualbass")}
|
| 696 |
+
|
| 697 |
+
@app.get("/api/v1/projects/{project_id}/virtualbass/audio")
|
| 698 |
+
def virtual_audio(project_id:str):
|
| 699 |
+
result=service.manifest(project_id).get("virtualbass")
|
| 700 |
+
if not result:
|
| 701 |
+
raise HTTPException(status_code=404,detail="No Virtual Bass result.")
|
| 702 |
+
path=service.folder(project_id)/"virtualbass"/result["id"]/"virtualbass_2_1.wav"
|
| 703 |
+
if not path.is_file():
|
| 704 |
+
raise HTTPException(status_code=404,detail="Virtual Bass file not found.")
|
| 705 |
+
return FileResponse(path,media_type="audio/wav",filename="ABSOLUTION_VIRTUAL_BASS_2_1.wav")
|
| 706 |
+
|
| 707 |
+
@app.post("/api/v1/projects/{project_id}/inventory")
|
| 708 |
+
def run_inventory(project_id:str):
|
| 709 |
+
project_id=check_id(project_id)
|
| 710 |
+
with service.lock:
|
| 711 |
+
manifest=service.manifest(project_id)
|
| 712 |
+
if not manifest.get("asset"):
|
| 713 |
+
raise HTTPException(status_code=409,detail="Audio import required.")
|
| 714 |
+
path=service.folder(project_id)/manifest["asset"]["stored_name"]
|
| 715 |
+
try:
|
| 716 |
+
inventory=inspect_mini(path)
|
| 717 |
+
except (ValueError,FileNotFoundError) as exc:
|
| 718 |
+
raise HTTPException(status_code=422,detail=str(exc)) from exc
|
| 719 |
+
# Editable suggestions are hypotheses, NOT separated audio.
|
| 720 |
+
suggested=[{"id":d["id"],"label":d["label"],"enabled":True}
|
| 721 |
+
for d in inventory["detections"] if d["suggested"]]
|
| 722 |
+
manifest["inventory"]=inventory
|
| 723 |
+
if not manifest.get("plan"):manifest["plan"]=suggested
|
| 724 |
+
service.write_manifest(project_id,manifest)
|
| 725 |
+
return {"inventory":inventory,"plan":manifest["plan"],
|
| 726 |
+
"actual_stems":list(manifest.get("stems",{}))}
|
| 727 |
+
|
| 728 |
+
@app.put("/api/v1/projects/{project_id}/plan")
|
| 729 |
+
def update_plan(project_id:str,req:PlanRequest):
|
| 730 |
+
ids=[x.id for x in req.tracks]
|
| 731 |
+
if len(ids)!=len(set(ids)):
|
| 732 |
+
raise HTTPException(status_code=422,detail="Duplicate planned IDs.")
|
| 733 |
+
with service.lock:
|
| 734 |
+
manifest=service.manifest(project_id)
|
| 735 |
+
if not manifest.get("asset"):
|
| 736 |
+
raise HTTPException(status_code=409,detail="Import audio first.")
|
| 737 |
+
manifest["plan"]=[x.model_dump() for x in req.tracks]
|
| 738 |
+
service.write_manifest(project_id,manifest)
|
| 739 |
+
return {"plan":manifest["plan"],"status":"hypotheses_only",
|
| 740 |
+
"notice":"A saved plan does not separate or generate new stems."}
|
| 741 |
+
|
| 742 |
+
@app.get("/api/v1/projects/{project_id}/wave/{stem}")
|
| 743 |
+
def get_wave(project_id:str,stem:str,points:int=360):
|
| 744 |
+
manifest=service.manifest(project_id);folder=service.folder(project_id)
|
| 745 |
+
if stem=="original":
|
| 746 |
+
if not manifest.get("asset"):raise HTTPException(status_code=404,detail="No audio")
|
| 747 |
+
path=folder/manifest["asset"]["stored_name"]
|
| 748 |
+
else:
|
| 749 |
+
if stem not in manifest.get("stems",{}):
|
| 750 |
+
raise HTTPException(status_code=404,detail="Unknown stem")
|
| 751 |
+
path=folder/"stems"/manifest["stems"][stem]["master"]
|
| 752 |
+
if points<64 or points>1000:
|
| 753 |
+
raise HTTPException(status_code=422,detail="points must be 64..1000")
|
| 754 |
+
try:return sampled_peaks(path,points)
|
| 755 |
+
except (ValueError,RuntimeError) as exc:
|
| 756 |
+
raise HTTPException(status_code=422,detail=str(exc)) from exc
|
| 757 |
+
|
| 758 |
+
@app.post("/api/v1/jobs/mix",status_code=202)
|
| 759 |
+
def start_mix(request:MixerRequest):
|
| 760 |
+
return service.create_mixer_job(request)
|
| 761 |
+
|
| 762 |
+
@app.get("/api/v1/projects/{project_id}/mixer")
|
| 763 |
+
def mixer_status(project_id:str):
|
| 764 |
+
return {"mixer":service.manifest(project_id).get("mixer")}
|
| 765 |
+
|
| 766 |
+
@app.get("/api/v1/projects/{project_id}/mixer/audio")
|
| 767 |
+
def mixer_audio(project_id:str):
|
| 768 |
+
manifest=service.manifest(project_id)
|
| 769 |
+
mixer=manifest.get("mixer")
|
| 770 |
+
if not mixer:raise HTTPException(status_code=404,detail="Render a mix first.")
|
| 771 |
+
path=service.folder(project_id)/"mixer"/mixer["file"]
|
| 772 |
+
if not path.is_file():raise HTTPException(status_code=404,detail="Rendered mix missing")
|
| 773 |
+
return FileResponse(path,media_type="audio/wav",filename="ABSOLUTION_ARRANGEMENT_MIX.wav")
|
| 774 |
+
|
| 775 |
@app.get("/api/v1/projects/{project_id}/stems")
|
| 776 |
def get_stems(project_id: str):
|
| 777 |
manifest = service.manifest(project_id)
|
app/static/app.js
CHANGED
|
@@ -7,7 +7,7 @@ const BASE = "/api/v1";
|
|
| 7 |
const STORAGE = "absolution_omega_current_project_v02";
|
| 8 |
const state = {
|
| 9 |
projectId: null, projectName: "", asset: null, analysis: null,
|
| 10 |
-
stems: {}, report: null, separation: null,
|
| 11 |
model: "hpss", models: [], busy: false, playing: "original",
|
| 12 |
view: "studio",
|
| 13 |
};
|
|
@@ -62,9 +62,15 @@ function setBusy(value) {
|
|
| 62 |
$("#newProject").disabled = value;
|
| 63 |
$("#dropzone").setAttribute("aria-disabled", String(value));
|
| 64 |
$("#run").disabled = value || !state.projectId || !state.models.find(m => m.id === state.model && m.ready);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
function navigate(view) {
|
| 67 |
-
if (!["studio","stems","quality","guide"].includes(view)) return;
|
| 68 |
state.view = view;
|
| 69 |
$$(".view").forEach(node => node.classList.toggle("active", node.id === `view-${view}`));
|
| 70 |
$$(".nav-link").forEach(node => {
|
|
@@ -72,10 +78,11 @@ function navigate(view) {
|
|
| 72 |
node.classList.toggle("active", active);
|
| 73 |
if (active) node.setAttribute("aria-current", "page"); else node.removeAttribute("aria-current");
|
| 74 |
});
|
| 75 |
-
const names = {studio:"STUDIO",stems:"MEINE STEMS",quality:"FORENSIK-BERICHT",guide:"HILFE & TECHNIK"};
|
| 76 |
$("#crumbCurrent").textContent = names[view];
|
| 77 |
document.title = `ABSOLUTION Ω — ${names[view]}`;
|
| 78 |
closeMenu();
|
|
|
|
| 79 |
window.scrollTo({top:0,behavior:"instant"});
|
| 80 |
}
|
| 81 |
function closeMenu() {
|
|
@@ -86,7 +93,7 @@ function closeMenu() {
|
|
| 86 |
function resetUi() {
|
| 87 |
state.projectId = null; state.projectName = "";
|
| 88 |
state.analysis = null; state.asset = null;
|
| 89 |
-
state.stems = {}; state.report = null; state.separation = null;
|
| 90 |
audio.pause(); audio.removeAttribute("src"); audio.load();
|
| 91 |
state.playing = "original";
|
| 92 |
$("#nowPlaying").textContent = "Kein Audio geladen";
|
|
@@ -116,7 +123,8 @@ function resetUi() {
|
|
| 116 |
$("#reportExplanation").textContent = "Nach einer Separation berechnen wir, wie genau alle Stems inklusive Residual den internen Eingangsmix rekonstruieren.";
|
| 117 |
$("#reportMark").textContent = "◇";
|
| 118 |
$("#err").textContent = "—"; $("#rmsErr").textContent = "—";
|
| 119 |
-
renderStems(); drawWave();
|
|
|
|
| 120 |
setBusy(false);
|
| 121 |
}
|
| 122 |
function loadManifest(project) {
|
|
@@ -127,6 +135,9 @@ function loadManifest(project) {
|
|
| 127 |
state.stems = project.stems || {};
|
| 128 |
state.report = project.report;
|
| 129 |
state.separation = project.separation;
|
|
|
|
|
|
|
|
|
|
| 130 |
safeStore(project.id);
|
| 131 |
$("#sidebarProject").textContent = project.name || project.asset?.filename || "Projekt";
|
| 132 |
$("#sidebarProjectInfo").textContent = project.analysis ? `${timeText(project.analysis.duration_seconds)} · ${project.analysis.channels} Kanal/Kanäle` : "Projekt ohne Datei";
|
|
@@ -145,7 +156,11 @@ function loadManifest(project) {
|
|
| 145 |
}
|
| 146 |
renderStems();
|
| 147 |
renderReport();
|
|
|
|
|
|
|
|
|
|
| 148 |
drawWave();
|
|
|
|
| 149 |
setBusy(false);
|
| 150 |
}
|
| 151 |
async function uploadFile(file) {
|
|
@@ -364,12 +379,321 @@ async function runSeparation() {
|
|
| 364 |
toast(`Separation fehlgeschlagen: ${error.message}`,true);
|
| 365 |
} finally {setBusy(false);}
|
| 366 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 367 |
async function init() {
|
| 368 |
resetUi();
|
| 369 |
audio.volume=.8;
|
| 370 |
try{
|
| 371 |
const health = await api(`${BASE}/health`);
|
| 372 |
maxUploadBytes = Number(health.max_upload_bytes) || maxUploadBytes;
|
|
|
|
|
|
|
| 373 |
$("#uploadLimits").textContent = `WAV · FLAC · AIFF · MP3 · OGG • bis ${Math.round(maxUploadBytes/1048576)} MiB • keine feste Zeitgrenze`;
|
| 374 |
$("#guideImportLimits").textContent = `Maximale Dateigröße: ${Math.round(maxUploadBytes/1048576)} MiB. Keine feste Zeitgrenze; Verarbeitungszeit hängt von Datei und Hardware ab.`;
|
| 375 |
$("#apiIndicator").classList.add("online");$("#apiLabel").textContent="ENGINE ONLINE";
|
|
@@ -410,6 +734,30 @@ $("#dropzone").addEventListener("dragover",event=>{event.preventDefault();$("#dr
|
|
| 410 |
$("#dropzone").addEventListener("dragleave",()=>$("#dropzone").classList.remove("dragging"));
|
| 411 |
$("#dropzone").addEventListener("drop",event=>{event.preventDefault();$("#dropzone").classList.remove("dragging");uploadFile(event.dataTransfer.files?.[0]);});
|
| 412 |
$$(".method input").forEach(input=>input.addEventListener("change",()=>selectMethod(input.value)));
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 413 |
$("#run").addEventListener("click",runSeparation);
|
| 414 |
$("#export").addEventListener("click",()=>{if(state.projectId && Object.keys(state.stems).length) window.location.href=`${BASE}/projects/${state.projectId}/export`;});
|
| 415 |
$("#waveform").addEventListener("click",event=>{
|
|
|
|
| 7 |
const STORAGE = "absolution_omega_current_project_v02";
|
| 8 |
const state = {
|
| 9 |
projectId: null, projectName: "", asset: null, analysis: null,
|
| 10 |
+
stems: {}, report: null, separation: null, bass: null, noise: null, virtualbass: null, virtualReady: false,
|
| 11 |
model: "hpss", models: [], busy: false, playing: "original",
|
| 12 |
view: "studio",
|
| 13 |
};
|
|
|
|
| 62 |
$("#newProject").disabled = value;
|
| 63 |
$("#dropzone").setAttribute("aria-disabled", String(value));
|
| 64 |
$("#run").disabled = value || !state.projectId || !state.models.find(m => m.id === state.model && m.ready);
|
| 65 |
+
$("#bassRun").disabled = value || !state.asset;
|
| 66 |
+
$("#bassExport").disabled = value || !state.bass;
|
| 67 |
+
$("#virtualRun").disabled = value || !state.asset || state.analysis?.channels !== 2 || !state.virtualReady;
|
| 68 |
+
$("#noiseScan").disabled = value || !state.asset;
|
| 69 |
+
$("#noiseExport").disabled = value || !state.noise?.repair;
|
| 70 |
+
$("#noiseRepair").disabled = value || !state.noise?.scan || !document.querySelector("#noiseCandidates input:checked");
|
| 71 |
}
|
| 72 |
function navigate(view) {
|
| 73 |
+
if (!["studio","arrangement","bass","noise","stems","quality","guide"].includes(view)) return;
|
| 74 |
state.view = view;
|
| 75 |
$$(".view").forEach(node => node.classList.toggle("active", node.id === `view-${view}`));
|
| 76 |
$$(".nav-link").forEach(node => {
|
|
|
|
| 78 |
node.classList.toggle("active", active);
|
| 79 |
if (active) node.setAttribute("aria-current", "page"); else node.removeAttribute("aria-current");
|
| 80 |
});
|
| 81 |
+
const names = {studio:"STUDIO",arrangement:"ARRANGEMENT",bass:"BASS-CORE",noise:"NOISE-CORE",stems:"MEINE STEMS",quality:"FORENSIK-BERICHT",guide:"HILFE & TECHNIK"};
|
| 82 |
$("#crumbCurrent").textContent = names[view];
|
| 83 |
document.title = `ABSOLUTION Ω — ${names[view]}`;
|
| 84 |
closeMenu();
|
| 85 |
+
if(view==="arrangement" && window.omegaArrangementDraw)window.omegaArrangementDraw();
|
| 86 |
window.scrollTo({top:0,behavior:"instant"});
|
| 87 |
}
|
| 88 |
function closeMenu() {
|
|
|
|
| 93 |
function resetUi() {
|
| 94 |
state.projectId = null; state.projectName = "";
|
| 95 |
state.analysis = null; state.asset = null;
|
| 96 |
+
state.stems = {}; state.report = null; state.separation = null; state.bass = null; state.noise = null; state.virtualbass = null;
|
| 97 |
audio.pause(); audio.removeAttribute("src"); audio.load();
|
| 98 |
state.playing = "original";
|
| 99 |
$("#nowPlaying").textContent = "Kein Audio geladen";
|
|
|
|
| 123 |
$("#reportExplanation").textContent = "Nach einer Separation berechnen wir, wie genau alle Stems inklusive Residual den internen Eingangsmix rekonstruieren.";
|
| 124 |
$("#reportMark").textContent = "◇";
|
| 125 |
$("#err").textContent = "—"; $("#rmsErr").textContent = "—";
|
| 126 |
+
renderStems(); drawWave(); renderBass(); renderNoise(); renderVirtual();
|
| 127 |
+
if(window.omegaArrangementReset) window.omegaArrangementReset();
|
| 128 |
setBusy(false);
|
| 129 |
}
|
| 130 |
function loadManifest(project) {
|
|
|
|
| 135 |
state.stems = project.stems || {};
|
| 136 |
state.report = project.report;
|
| 137 |
state.separation = project.separation;
|
| 138 |
+
state.bass = project.bass || null;
|
| 139 |
+
state.noise = project.noise || null;
|
| 140 |
+
state.virtualbass = project.virtualbass || null;
|
| 141 |
safeStore(project.id);
|
| 142 |
$("#sidebarProject").textContent = project.name || project.asset?.filename || "Projekt";
|
| 143 |
$("#sidebarProjectInfo").textContent = project.analysis ? `${timeText(project.analysis.duration_seconds)} · ${project.analysis.channels} Kanal/Kanäle` : "Projekt ohne Datei";
|
|
|
|
| 156 |
}
|
| 157 |
renderStems();
|
| 158 |
renderReport();
|
| 159 |
+
renderBass();
|
| 160 |
+
renderNoise();
|
| 161 |
+
renderVirtual();
|
| 162 |
drawWave();
|
| 163 |
+
if(window.omegaArrangementLoad) window.omegaArrangementLoad(project);
|
| 164 |
setBusy(false);
|
| 165 |
}
|
| 166 |
async function uploadFile(file) {
|
|
|
|
| 379 |
toast(`Separation fehlgeschlagen: ${error.message}`,true);
|
| 380 |
} finally {setBusy(false);}
|
| 381 |
}
|
| 382 |
+
// BASS-CORE Ω: user-controlled, non-destructive DSP stage.
|
| 383 |
+
const bassPresets = {
|
| 384 |
+
transparent: {bassCrossover:220,bassFocus:75,bassKick:0,bassLine:0,bassSub:0,bassHarm:0,bassLowcut:10,bassMono:0,bassWet:100,bassCeiling:-1},
|
| 385 |
+
club: {bassCrossover:200,bassFocus:85,bassKick:3,bassLine:1.5,bassSub:2,bassHarm:35,bassLowcut:22,bassMono:110,bassWet:90,bassCeiling:-1},
|
| 386 |
+
warm: {bassCrossover:240,bassFocus:50,bassKick:0.5,bassLine:2,bassSub:2,bassHarm:45,bassLowcut:20,bassMono:90,bassWet:85,bassCeiling:-1},
|
| 387 |
+
translate: {bassCrossover:180,bassFocus:65,bassKick:1,bassLine:0,bassSub:-1,bassHarm:80,bassLowcut:26,bassMono:110,bassWet:100,bassCeiling:-1},
|
| 388 |
+
};
|
| 389 |
+
const bassSliderIds = ["bassCrossover","bassFocus","bassKick","bassLine","bassSub","bassHarm","bassLowcut","bassMono","bassWet","bassCeiling"];
|
| 390 |
+
function bassNumber(id) {return Number($("#"+id).value);}
|
| 391 |
+
function updateBassValues() {
|
| 392 |
+
const values={
|
| 393 |
+
bassCrossoverValue:`${bassNumber("bassCrossover")} Hz`,
|
| 394 |
+
bassFocusValue:`${bassNumber("bassFocus")} %`,
|
| 395 |
+
bassKickValue:`${bassNumber("bassKick")>=0?"+":""}${bassNumber("bassKick").toFixed(1)} dB`,
|
| 396 |
+
bassLineValue:`${bassNumber("bassLine")>=0?"+":""}${bassNumber("bassLine").toFixed(1)} dB`,
|
| 397 |
+
bassSubValue:`${bassNumber("bassSub")>=0?"+":""}${bassNumber("bassSub").toFixed(1)} dB`,
|
| 398 |
+
bassHarmValue:`${bassNumber("bassHarm")} %`,
|
| 399 |
+
bassLowcutValue:`${bassNumber("bassLowcut")} Hz`,
|
| 400 |
+
bassMonoValue:`${bassNumber("bassMono")} Hz`,
|
| 401 |
+
bassWetValue:`${bassNumber("bassWet")} %`,
|
| 402 |
+
bassCeilingValue:`${bassNumber("bassCeiling").toFixed(1)} dBFS`,
|
| 403 |
+
};
|
| 404 |
+
Object.entries(values).forEach(([id,label])=>$("#"+id).textContent=label);
|
| 405 |
+
}
|
| 406 |
+
function applyBassPreset(name) {
|
| 407 |
+
const p=bassPresets[name]; if(!p)return;
|
| 408 |
+
Object.entries(p).forEach(([id,val])=>{ $("#"+id).value=String(val);});
|
| 409 |
+
updateBassValues();
|
| 410 |
+
$$(".bass-preset").forEach(el=>el.classList.toggle("active",el.dataset.bassPreset===name));
|
| 411 |
+
}
|
| 412 |
+
function bassSourceUrl(track,preview=true) {
|
| 413 |
+
return `${BASE}/projects/${state.projectId}/bass/audio/${encodeURIComponent(track)}${preview?"?preview=true":""}`;
|
| 414 |
+
}
|
| 415 |
+
function playBassTrack(name) {
|
| 416 |
+
if(!state.bass || !state.projectId)return;
|
| 417 |
+
audio.pause();
|
| 418 |
+
audio.src=bassSourceUrl(name,true);
|
| 419 |
+
audio.dataset.stem="bass:"+name;
|
| 420 |
+
audio.load();
|
| 421 |
+
$("#playButton").disabled=false;
|
| 422 |
+
$("#back10").disabled=false;
|
| 423 |
+
$("#forward10").disabled=false;
|
| 424 |
+
$("#seekBar").disabled=false;
|
| 425 |
+
$("#nowPlaying").textContent=state.bass.stems[name]?.label||name;
|
| 426 |
+
$("#nowPlayingSub").textContent=`BASS-CORE · ${state.asset?.filename||""}`;
|
| 427 |
+
$("#playDuration").textContent=timeText(state.analysis?.duration_seconds);
|
| 428 |
+
audio.play().catch(()=>toast("Bass-Audio konnte nicht abgespielt werden.",true));
|
| 429 |
+
}
|
| 430 |
+
function renderBass() {
|
| 431 |
+
const content=$("#bassResults");
|
| 432 |
+
content.replaceChildren();
|
| 433 |
+
const data=state.bass;
|
| 434 |
+
$("#bassReady").textContent=!state.asset?"DATEI IMPORTIEREN":data?"VERARBEITET":"BEREIT";
|
| 435 |
+
$("#bassSourceUsed").textContent=data?.mode?.toUpperCase()||"—";
|
| 436 |
+
$("#bassMixPeak").textContent=data?dbText(data.report.output_peak_dbfs):"—";
|
| 437 |
+
$("#bassPeakGain").textContent=data?`${data.report.output_ceiling_gain_db.toFixed(2)} dB`:"—";
|
| 438 |
+
$("#bassRecon").textContent=data?(data.report.reconstruction_check.consistent?"OK":"PRÜFEN"):"—";
|
| 439 |
+
if(!data) {
|
| 440 |
+
const empty=el("div","empty-state");
|
| 441 |
+
empty.append(el("h3","","Noch keine Bass-Bearbeitung"),el("p","","Importiere eine Audiodatei im Studio und starte BASS-CORE."));
|
| 442 |
+
content.append(empty);
|
| 443 |
+
$("#bassFrequency").replaceChildren(el("div","bass-frequency-empty","Noch kein Spektralvergleich vorhanden."));
|
| 444 |
+
$("#bassExport").disabled=true;
|
| 445 |
+
return;
|
| 446 |
+
}
|
| 447 |
+
$("#bassExport").disabled=state.busy;
|
| 448 |
+
for(const [name,meta] of Object.entries(data.stems)) {
|
| 449 |
+
const block=el("article","bass-result");
|
| 450 |
+
const labels={
|
| 451 |
+
bass_band:"Bassband · vorher",kick_estimate:"Kick · Schätzung",
|
| 452 |
+
bassline_estimate:"Bassline · Schätzung",other_unprocessed:"Rest ohne Bassband",
|
| 453 |
+
harmonics_added:"Neue Obertöne · Synthese",bass_optimized:"Bassband · optimiert",
|
| 454 |
+
mix_optimized:"Voller Mix · nachher"
|
| 455 |
+
};
|
| 456 |
+
block.append(el("h3","",labels[name]||name),el("p","",meta.label||""));
|
| 457 |
+
const actions=el("div","stem-actions");
|
| 458 |
+
const play=el("button","","▶ Anhören");
|
| 459 |
+
play.type="button"; play.addEventListener("click",()=>playBassTrack(name));
|
| 460 |
+
const download=el("a","","↓ WAV 32-bit");
|
| 461 |
+
download.href=bassSourceUrl(name,false);
|
| 462 |
+
download.download=name+".wav";
|
| 463 |
+
actions.append(play,download);block.append(actions);content.append(block);
|
| 464 |
+
}
|
| 465 |
+
const freq=$("#bassFrequency");freq.replaceChildren();
|
| 466 |
+
const before=data.report.first_chunk_spectrum?.before||[];
|
| 467 |
+
const after=data.report.first_chunk_spectrum?.after||[];
|
| 468 |
+
for(let i=0;i<Math.min(before.length,after.length);i++){
|
| 469 |
+
const a=before[i].estimated_rms_dbfs, b=after[i].estimated_rms_dbfs;
|
| 470 |
+
const range=before[i].range_hz;
|
| 471 |
+
const scaled=v=>Math.max(0,Math.min(100,(v+95)/95*100));
|
| 472 |
+
const row=el("div","bass-freq-item");
|
| 473 |
+
const band=el("span","",`${range[0]}–${range[1]} Hz`);
|
| 474 |
+
const rail=el("div","bass-freq-rail");
|
| 475 |
+
const old=el("div","bass-before"), newer=el("div","bass-after");
|
| 476 |
+
old.style.width=scaled(a)+"%";newer.style.width=scaled(b)+"%";
|
| 477 |
+
rail.append(old,newer);
|
| 478 |
+
const info=el("span","bass-freq-key",`${(b-a)>=0?"+":""}${(b-a).toFixed(1)} dB`);
|
| 479 |
+
row.append(band,rail,info);freq.append(row);
|
| 480 |
+
}
|
| 481 |
+
}
|
| 482 |
+
function bassPayload() {
|
| 483 |
+
return {
|
| 484 |
+
project_id:state.projectId,source_mode:$("#bassMode").value,
|
| 485 |
+
crossover_hz:bassNumber("bassCrossover"),kick_focus:bassNumber("bassFocus")/100,
|
| 486 |
+
kick_gain_db:bassNumber("bassKick"),bass_gain_db:bassNumber("bassLine"),
|
| 487 |
+
sub_gain_db:bassNumber("bassSub"),harmonics:bassNumber("bassHarm")/100,
|
| 488 |
+
lowcut_hz:bassNumber("bassLowcut"),mono_below_hz:bassNumber("bassMono"),
|
| 489 |
+
wet:bassNumber("bassWet")/100,ceiling_dbfs:bassNumber("bassCeiling")
|
| 490 |
+
};
|
| 491 |
+
}
|
| 492 |
+
async function runBass() {
|
| 493 |
+
if(state.busy||!state.asset)return;
|
| 494 |
+
setBusy(true);
|
| 495 |
+
$("#bassProgress").hidden=false;
|
| 496 |
+
$("#bassProgressFill").style.width="0%";$("#bassProgressNum").textContent="0 %";
|
| 497 |
+
$("#bassJobLabel").textContent="Analyse und Bass-Bearbeitung starten …";
|
| 498 |
+
try {
|
| 499 |
+
const job=await api(`${BASE}/jobs/bass`,{method:"POST",headers:{"content-type":"application/json"},body:JSON.stringify(bassPayload())});
|
| 500 |
+
while(true){
|
| 501 |
+
await new Promise(resolve=>setTimeout(resolve,650));
|
| 502 |
+
const now=await api(`${BASE}/jobs/${job.id}`);
|
| 503 |
+
const pct=Math.min(100,Math.max(0,Number(now.progress)||0));
|
| 504 |
+
$("#bassProgressFill").style.width=`${pct}%`;
|
| 505 |
+
$("#bassProgressNum").textContent=`${pct} %`;
|
| 506 |
+
$("#bassJobLabel").textContent=now.status==="queued"?"Wartet auf freien Worker …":now.status==="running"?"Tieffrequenzen werden verarbeitet …":now.status==="done"?"Bass-Bearbeitung abgeschlossen":"Fehlgeschlagen";
|
| 507 |
+
if(now.status==="failed")throw new Error(now.error||"Fehler beim Bass-Processing.");
|
| 508 |
+
if(now.status==="done")break;
|
| 509 |
+
}
|
| 510 |
+
const project=await api(`${BASE}/projects/${state.projectId}`);
|
| 511 |
+
state.bass=project.bass;
|
| 512 |
+
renderBass();
|
| 513 |
+
toast("BASS-CORE abgeschlossen! Vergleiche Bassband vorher/nachher mit deinem Gehör.");
|
| 514 |
+
} catch(error){
|
| 515 |
+
$("#bassJobLabel").textContent="Verarbeitung fehlgeschlagen";
|
| 516 |
+
toast(`BASS-CORE: ${error.message}`,true);
|
| 517 |
+
} finally {setBusy(false);}
|
| 518 |
+
}
|
| 519 |
+
|
| 520 |
+
function renderVirtual() {
|
| 521 |
+
const res=state.virtualbass;
|
| 522 |
+
$("#virtualRun").disabled=state.busy||!state.asset||state.analysis?.channels!==2||!state.virtualReady;
|
| 523 |
+
$("#virtualReady").textContent=!state.virtualReady?"FFMPEG-FILTER FEHLT":!state.asset?"STEREO IMPORTIEREN":res?"2.1 EXPORT BEREIT":"BEREIT";
|
| 524 |
+
$("#virtualDownload").hidden=!res;
|
| 525 |
+
if(res) {
|
| 526 |
+
$("#virtualDownload").href=`${BASE}/projects/${encodeURIComponent(state.projectId)}/virtualbass/audio`;
|
| 527 |
+
$("#virtualDownload").download="ABSOLUTION_VIRTUAL_BASS_2_1.wav";
|
| 528 |
+
$("#virtualSummary").textContent=`3 Kanäle (L/R + LFE) · LFE Peak: ${res.report.lfe_peak_dbfs} dBFS · Stereo-Differenz: ${res.report.left_right_max_abs_difference.toExponential(2)}. Nicht automatisch als Stereo-Mix verwenden.`;
|
| 529 |
+
} else $("#virtualSummary").textContent="Benötigt Stereo + FFmpeg mit virtualbass. Exportiert einen 2.1-Master, ohne die Stereo-Originaldatei zu ändern.";
|
| 530 |
+
}
|
| 531 |
+
async function runVirtual() {
|
| 532 |
+
if(state.busy||!state.virtualReady||!state.asset)return;
|
| 533 |
+
setBusy(true);
|
| 534 |
+
try {
|
| 535 |
+
const payload={
|
| 536 |
+
project_id:state.projectId,
|
| 537 |
+
cutoff_hz:Number($("#virtualCutoff").value),
|
| 538 |
+
strength:Number($("#virtualStrength").value)
|
| 539 |
+
};
|
| 540 |
+
const job=await api(`${BASE}/jobs/bass/virtual`,{method:"POST",headers:{"content-type":"application/json"},body:JSON.stringify(payload)});
|
| 541 |
+
toast("Virtual Bass 2.1 wird lokal erzeugt …");
|
| 542 |
+
while(true){
|
| 543 |
+
await new Promise(resolve=>setTimeout(resolve,600));
|
| 544 |
+
const current=await api(`${BASE}/jobs/${job.id}`);
|
| 545 |
+
if(current.status==="failed")throw new Error(current.error||"Virtual Bass konnte nicht erzeugt werden.");
|
| 546 |
+
if(current.status==="done")break;
|
| 547 |
+
}
|
| 548 |
+
state.virtualbass=(await api(`${BASE}/projects/${state.projectId}/virtualbass`)).virtualbass;
|
| 549 |
+
toast("2.1-Virtual-Bass-Datei erstellt. Links/Rechts-Kanäle bleiben getrennt vom synthetischen LFE.");
|
| 550 |
+
}catch(error){toast(`Virtual Bass: ${error.message}`,true)}
|
| 551 |
+
finally{setBusy(false);renderVirtual();}
|
| 552 |
+
}
|
| 553 |
+
// NOISE-CORE: all changes require individually selected scan samples.
|
| 554 |
+
function noiseAudioUrl(name,preview=true) {
|
| 555 |
+
return `${BASE}/projects/${encodeURIComponent(state.projectId)}/noise/audio/${encodeURIComponent(name)}${preview?"?preview=true":""}`;
|
| 556 |
+
}
|
| 557 |
+
function playNoiseTrack(name) {
|
| 558 |
+
if(!state.noise?.repair)return;
|
| 559 |
+
audio.pause();
|
| 560 |
+
audio.src=noiseAudioUrl(name,true);
|
| 561 |
+
audio.dataset.stem="noise:"+name;
|
| 562 |
+
audio.load();
|
| 563 |
+
$("#playButton").disabled=false;
|
| 564 |
+
$("#back10").disabled=false;
|
| 565 |
+
$("#forward10").disabled=false;
|
| 566 |
+
$("#seekBar").disabled=false;
|
| 567 |
+
$("#nowPlaying").textContent=name==="clean"?"Manuell repariertes Signal":"DIFFERENZ: tatsächlich verändertes Musiksignal";
|
| 568 |
+
$("#nowPlayingSub").textContent=`NOISE-CORE · ${state.asset?.filename||""}`;
|
| 569 |
+
$("#playDuration").textContent=timeText(state.analysis?.duration_seconds);
|
| 570 |
+
audio.play().catch(()=>toast("Audio konnte nicht wiedergegeben werden.",true));
|
| 571 |
+
}
|
| 572 |
+
function renderNoise() {
|
| 573 |
+
const scan=state.noise?.scan;
|
| 574 |
+
const repair=state.noise?.repair;
|
| 575 |
+
$("#noiseReady").textContent=!state.asset?"DATEI IMPORTIEREN":scan?"SCAN VORHANDEN":"BEREIT";
|
| 576 |
+
$("#noiseScan").disabled=state.busy||!state.asset;
|
| 577 |
+
$("#noiseScanMeta").textContent=scan?`${scan.event_count} Kandidaten · keine automatische Veränderung`:"Noch kein Scan";
|
| 578 |
+
$("#noiseCount").textContent=scan?`${scan.event_count} Kandidaten`:"0 Kandidaten";
|
| 579 |
+
const candidates=$("#noiseCandidates");
|
| 580 |
+
candidates.replaceChildren();
|
| 581 |
+
if(!scan) {
|
| 582 |
+
const placeholder=el("div","empty-state");
|
| 583 |
+
placeholder.append(el("h3","","Noch keine Kandidaten"),el("p","","Lade eine Audiodatei und starte den Scan."));
|
| 584 |
+
candidates.append(placeholder);
|
| 585 |
+
} else if (!scan.events.length) {
|
| 586 |
+
candidates.append(el("p","bass-note","Keine auffälligen Einzel-Sample-Impulse gefunden. Das beweist nicht die Abwesenheit von Störungen."));
|
| 587 |
+
} else {
|
| 588 |
+
for(const event of scan.events) {
|
| 589 |
+
const row=el("div","noise-candidate");
|
| 590 |
+
const cb=el("input");
|
| 591 |
+
cb.type="checkbox";cb.value=String(event.sample);cb.id=`noiseEvent_${event.sample}`;
|
| 592 |
+
cb.addEventListener("change",()=>{$("#noiseRepair").disabled=state.busy||!document.querySelector("#noiseCandidates input:checked")});
|
| 593 |
+
const label=el("label");
|
| 594 |
+
label.htmlFor=cb.id;
|
| 595 |
+
label.append(el("strong","",`${event.time_seconds.toFixed(4)} s · Kandidat #${event.sample}`));
|
| 596 |
+
label.append(el("small","","Unsicherer Einzelimpuls · kein Nachweis für einen Defekt"));
|
| 597 |
+
const button=el("button","","▶ Umfeld anhören");
|
| 598 |
+
button.type="button";
|
| 599 |
+
button.addEventListener("click",()=>{
|
| 600 |
+
setSource("original",false);
|
| 601 |
+
audio.currentTime=Math.max(0,event.time_seconds-.3);
|
| 602 |
+
audio.play().catch(()=>toast("Original konnte nicht abgespielt werden.",true));
|
| 603 |
+
});
|
| 604 |
+
row.append(cb,label,button);
|
| 605 |
+
candidates.append(row);
|
| 606 |
+
}
|
| 607 |
+
}
|
| 608 |
+
$("#noiseRepair").disabled=state.busy||!scan||!document.querySelector("#noiseCandidates input:checked");
|
| 609 |
+
const results=$("#noiseTracks");
|
| 610 |
+
results.replaceChildren();
|
| 611 |
+
if(repair) {
|
| 612 |
+
for(const name of ["clean","difference"]) {
|
| 613 |
+
const track=el("div","noise-track");
|
| 614 |
+
track.append(el("h3","",name==="clean"?"Reparatur · nachher":"Differenzspur · entnommenes Signal"));
|
| 615 |
+
track.append(el("p","",name==="clean"?"Bearbeiteter Mix aus explizit bestätigten Korrekturen.":"WICHTIG: Enthält möglicherweise echte Musikanteile. Immer abhören!"));
|
| 616 |
+
const actions=el("div","stem-actions");
|
| 617 |
+
const play=el("button","","▶ Anhören");
|
| 618 |
+
play.addEventListener("click",()=>playNoiseTrack(name));
|
| 619 |
+
const download=el("a","","↓ WAV Float32");
|
| 620 |
+
download.href=noiseAudioUrl(name,false);download.download=`noise_${name}.wav`;
|
| 621 |
+
actions.append(play,download);
|
| 622 |
+
track.append(actions);results.append(track);
|
| 623 |
+
}
|
| 624 |
+
} else {
|
| 625 |
+
const blank=el("div","empty-state");
|
| 626 |
+
blank.append(el("h3","","Noch keine Bearbeitung"),el("p","","Das unveränderte Original ist weiterhin verfügbar."));
|
| 627 |
+
results.append(blank);
|
| 628 |
+
}
|
| 629 |
+
$("#noiseExport").disabled=state.busy||!repair;
|
| 630 |
+
const details=$("#noiseDiagnostics");details.replaceChildren();
|
| 631 |
+
if(scan) {
|
| 632 |
+
const tonal=scan.tonal_indicators||[];
|
| 633 |
+
details.append(el("div","noise-line",tonal.length ?
|
| 634 |
+
`Mögliche schmale Spektralspitzen (keine sichere Störung): ${tonal.map(t=>`${t.frequency_hz} Hz · +${t.peak_to_local_median_db} dB`).join(" | ")}. Keine automatischen Notches.`
|
| 635 |
+
:"Keine auffällige 50-/60-Hz-Spektralspitze festgestellt. Kein automatisches Breitband-Entrauschen."));
|
| 636 |
+
if(scan.event_limit_reached) details.append(el("div","noise-line","Anzeigegrenze für Klickkandidaten erreicht; vollständige Zählung siehe Bericht."));
|
| 637 |
+
}
|
| 638 |
+
if(repair) {
|
| 639 |
+
const report=repair.report;
|
| 640 |
+
details.append(el("div","noise-line",
|
| 641 |
+
`${report.changed_sample_frames} explizit bestätigte Einzel-Samples verändert · Max. absolute Änderung ${report.peak_absolute_change.toExponential(3)} · Rekonstruktionsfehler ${report.reconstruction_max_absolute_error.toExponential(3)}. Die Differenzspur kann musikalische Anteile enthalten.`));
|
| 642 |
+
}
|
| 643 |
+
}
|
| 644 |
+
async function pollNoiseJob(jobId,caption) {
|
| 645 |
+
while(true) {
|
| 646 |
+
await new Promise(resolve=>setTimeout(resolve,650));
|
| 647 |
+
const status=await api(`${BASE}/jobs/${jobId}`);
|
| 648 |
+
const pct=Math.min(100,Math.max(0,Number(status.progress)||0));
|
| 649 |
+
$("#noiseProgressFill").style.width=`${pct}%`;
|
| 650 |
+
$("#noiseProgressNum").textContent=`${pct} %`;
|
| 651 |
+
$("#noiseJobLabel").textContent=status.status==="queued"?"Wartet auf Worker …":status.status==="running"?caption:status.status==="done"?"Fertig":"Fehlgeschlagen";
|
| 652 |
+
if(status.status==="failed") throw new Error(status.error||"NOISE-CORE Job fehlgeschlagen.");
|
| 653 |
+
if(status.status==="done")break;
|
| 654 |
+
}
|
| 655 |
+
}
|
| 656 |
+
async function startNoiseScan() {
|
| 657 |
+
if(state.busy||!state.asset)return;
|
| 658 |
+
setBusy(true);
|
| 659 |
+
$("#noiseProgress").hidden=false;$("#noiseProgressFill").style.width="0%";
|
| 660 |
+
try{
|
| 661 |
+
const job=await api(`${BASE}/jobs/noise/scan`,{method:"POST",headers:{"content-type":"application/json"},body:JSON.stringify({project_id:state.projectId})});
|
| 662 |
+
await pollNoiseJob(job.id,"Musikalische Impulse werden vorsichtig untersucht …");
|
| 663 |
+
const response=await api(`${BASE}/projects/${state.projectId}/noise`);
|
| 664 |
+
state.noise=response.noise;renderNoise();
|
| 665 |
+
toast("Scan beendet. Nichts wurde verändert. Bitte jeden Kandidaten einzeln prüfen.");
|
| 666 |
+
}catch(error){toast(`NOISE-CORE: ${error.message}`,true)}
|
| 667 |
+
finally{setBusy(false);renderNoise();}
|
| 668 |
+
}
|
| 669 |
+
async function startNoiseRepair() {
|
| 670 |
+
if(state.busy||!state.noise?.scan)return;
|
| 671 |
+
const selected=$$("#noiseCandidates input:checked").map(x=>Number(x.value));
|
| 672 |
+
if(!selected.length)return toast("Wähle eine geprüfte Klickstelle aus.",true);
|
| 673 |
+
if(!window.confirm(`Du hast ${selected.length} Stelle(n) ausgewählt. Diese Samples werden interpoliert. Die Differenzspur kann echte Musikanteile enthalten. Fortfahren?`))return;
|
| 674 |
+
setBusy(true);
|
| 675 |
+
$("#noiseProgress").hidden=false;$("#noiseProgressFill").style.width="0%";
|
| 676 |
+
try{
|
| 677 |
+
const job=await api(`${BASE}/jobs/noise/repair`,{method:"POST",headers:{"content-type":"application/json"},body:JSON.stringify({
|
| 678 |
+
project_id:state.projectId,approved_samples:selected,
|
| 679 |
+
strength:Number($("#noiseStrength").value)/100
|
| 680 |
+
})});
|
| 681 |
+
await pollNoiseJob(job.id,"Nur freigegebene Einzelstellen werden behutsam bearbeitet …");
|
| 682 |
+
const response=await api(`${BASE}/projects/${state.projectId}/noise`);
|
| 683 |
+
state.noise=response.noise;renderNoise();
|
| 684 |
+
toast("Reparatur gerendert. Bitte die Differenzspur anhören.");
|
| 685 |
+
}catch(error){toast(`NOISE-CORE: ${error.message}`,true)}
|
| 686 |
+
finally{setBusy(false);renderNoise();}
|
| 687 |
+
}
|
| 688 |
+
|
| 689 |
async function init() {
|
| 690 |
resetUi();
|
| 691 |
audio.volume=.8;
|
| 692 |
try{
|
| 693 |
const health = await api(`${BASE}/health`);
|
| 694 |
maxUploadBytes = Number(health.max_upload_bytes) || maxUploadBytes;
|
| 695 |
+
state.virtualReady=Boolean(health.virtualbass_ready);
|
| 696 |
+
renderVirtual();
|
| 697 |
$("#uploadLimits").textContent = `WAV · FLAC · AIFF · MP3 · OGG • bis ${Math.round(maxUploadBytes/1048576)} MiB • keine feste Zeitgrenze`;
|
| 698 |
$("#guideImportLimits").textContent = `Maximale Dateigröße: ${Math.round(maxUploadBytes/1048576)} MiB. Keine feste Zeitgrenze; Verarbeitungszeit hängt von Datei und Hardware ab.`;
|
| 699 |
$("#apiIndicator").classList.add("online");$("#apiLabel").textContent="ENGINE ONLINE";
|
|
|
|
| 734 |
$("#dropzone").addEventListener("dragleave",()=>$("#dropzone").classList.remove("dragging"));
|
| 735 |
$("#dropzone").addEventListener("drop",event=>{event.preventDefault();$("#dropzone").classList.remove("dragging");uploadFile(event.dataTransfer.files?.[0]);});
|
| 736 |
$$(".method input").forEach(input=>input.addEventListener("change",()=>selectMethod(input.value)));
|
| 737 |
+
bassSliderIds.forEach(id=>$("#"+id).addEventListener("input",()=>{
|
| 738 |
+
updateBassValues();$$(".bass-preset").forEach(node=>node.classList.remove("active"));
|
| 739 |
+
}));
|
| 740 |
+
$$(".bass-preset").forEach(node=>node.addEventListener("click",()=>applyBassPreset(node.dataset.bassPreset)));
|
| 741 |
+
$("#virtualRun").addEventListener("click",runVirtual);
|
| 742 |
+
for(const id of ["virtualCutoff","virtualStrength"]) {
|
| 743 |
+
$("#"+id).addEventListener("input",()=>{
|
| 744 |
+
$("#virtualCutoffValue").textContent=$("#virtualCutoff").value+" Hz";
|
| 745 |
+
$("#virtualStrengthValue").textContent=Number($("#virtualStrength").value).toFixed(1);
|
| 746 |
+
});
|
| 747 |
+
}
|
| 748 |
+
$("#noiseScan").addEventListener("click",startNoiseScan);
|
| 749 |
+
$("#noiseRepair").addEventListener("click",startNoiseRepair);
|
| 750 |
+
$("#noiseStrength").addEventListener("input",event=>{
|
| 751 |
+
$("#noiseStrengthValue").textContent=`${event.target.value} %`;
|
| 752 |
+
});
|
| 753 |
+
$("#noiseExport").addEventListener("click",()=>{
|
| 754 |
+
if(state.projectId&&state.noise?.repair)window.location.href=`${BASE}/projects/${state.projectId}/noise/export`;
|
| 755 |
+
});
|
| 756 |
+
$("#bassRun").addEventListener("click",runBass);
|
| 757 |
+
$("#bassExport").addEventListener("click",()=>{
|
| 758 |
+
if(state.projectId&&state.bass)window.location.href=`${BASE}/projects/${state.projectId}/bass/export`;
|
| 759 |
+
});
|
| 760 |
+
applyBassPreset("transparent");
|
| 761 |
$("#run").addEventListener("click",runSeparation);
|
| 762 |
$("#export").addEventListener("click",()=>{if(state.projectId && Object.keys(state.stems).length) window.location.href=`${BASE}/projects/${state.projectId}/export`;});
|
| 763 |
$("#waveform").addEventListener("click",event=>{
|
app/static/arrangement.css
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/* ABSOLUTION Ω Arrangement Studio — specialized DAW view.
|
| 2 |
+
Scoped to arr-* classes: existing BASS-/NOISE-CORE views remain unchanged. */
|
| 3 |
+
main:has(>.arr-view.active){width:100%;max-width:1840px;padding:26px 24px 22px}
|
| 4 |
+
.arr-view{--arr-bg:#0c1524;--arr-panel:#101d2d;--arr-muted:#91a6b9;--arr-edge:#26394b;--arr-teal:#72f3cf;--arr-gold:#f2c47c;color:#eaf6fc}
|
| 5 |
+
.arr-view h1,.arr-view h2,.arr-view p{margin:0}
|
| 6 |
+
.arr-view button,.arr-view select,.arr-view input{font:inherit}
|
| 7 |
+
.arr-header{display:flex;align-items:center;justify-content:space-between;gap:25px;padding:12px 7px 24px}
|
| 8 |
+
.arr-kicker{color:#82dfca;letter-spacing:.18em;font-size:10px;font-weight:800;display:flex;align-items:center;gap:10px;margin-bottom:16px}
|
| 9 |
+
.arr-light{width:8px;height:8px;border-radius:50%;background:#81f1c9;box-shadow:0 0 15px #81f1c9}
|
| 10 |
+
.arr-beta{margin-left:10px;font-size:10px;color:#d2e3df;background:#163f3e;border:1px solid #275d57;padding:4px 8px;border-radius:99px;letter-spacing:0}
|
| 11 |
+
.arr-title h1{font-weight:750;font-size:clamp(27px,3.6vw,48px);letter-spacing:-.045em;line-height:1.12}
|
| 12 |
+
.arr-title h1 em{font-style:normal;background:linear-gradient(100deg,#86ffdb,#65cbeb 45%,#c9acff);-webkit-background-clip:text;background-clip:text;color:transparent}
|
| 13 |
+
.arr-title p{color:#a1b3c6;font-size:13px;margin-top:12px;line-height:1.6}
|
| 14 |
+
.arr-header-actions,.arr-toolbar,.arr-plan-foot>div,.arr-footer-actions,.arr-separate-group{display:flex;align-items:center;gap:9px;flex-wrap:wrap}
|
| 15 |
+
.arr-header-actions{flex-shrink:0}
|
| 16 |
+
.arr-btn{border:1px solid #365168;border-radius:9px;background:#172738;color:#c9e9f2;padding:11px 14px;line-height:1;min-height:38px;font-weight:750;font-size:12px;display:inline-flex;justify-content:center;align-items:center;gap:8px;transition:background .15s,border-color .15s}
|
| 17 |
+
.arr-btn:hover{border-color:#73b9bc;background:#243b51}
|
| 18 |
+
.arr-btn-primary{background:linear-gradient(130deg,#74efcf,#67bbd8);color:#06232c;border-color:#8cf8d7;box-shadow:0 4px 18px #3fe8c620}
|
| 19 |
+
.arr-btn-primary:hover{background:#9af7d7;border-color:#d4fff1}
|
| 20 |
+
.arr-btn-ghost{background:#152536;color:#d0e6ef}
|
| 21 |
+
.arr-btn:disabled{opacity:.4;cursor:not-allowed}
|
| 22 |
+
.arr-status{display:flex;justify-content:space-between;align-items:center;gap:10px;white-space:nowrap;overflow:hidden;border:1px solid #28404e;background:linear-gradient(90deg,#122432,#121d2c);border-radius:9px;color:#bdd6e0;font-size:11px;padding:12px 18px}
|
| 23 |
+
#arrSourceName{overflow:hidden;text-overflow:ellipsis}
|
| 24 |
+
#arrStemStatus{color:#89ead1;font-weight:800;flex-shrink:0}
|
| 25 |
+
.arr-workflow{margin:15px 0 16px;display:flex;align-items:stretch;gap:11px}
|
| 26 |
+
.arr-step{min-width:0;flex:1;padding:13px 15px;border:1px solid #203d4a;border-radius:9px;background:#101d2a;display:grid;grid-template-columns:auto 1fr;grid-template-rows:auto auto;gap:3px 9px}
|
| 27 |
+
.arr-step>span{grid-row:span 2;font-size:18px;font-weight:750;color:#68dec2;align-self:center}
|
| 28 |
+
.arr-step strong{font-size:10px;letter-spacing:.08em}
|
| 29 |
+
.arr-step small{font-size:10px;color:#879eae}
|
| 30 |
+
.arr-workflow-arrow{display:grid;place-items:center;color:#507c83}
|
| 31 |
+
.arr-card{background:linear-gradient(140deg,#111e2e,#101925 90%);border:1px solid #2a3c50;border-radius:14px;box-shadow:0 18px 50px #03071117}
|
| 32 |
+
.arr-planning{padding:20px 21px;margin-bottom:20px}
|
| 33 |
+
.arr-card-head,.arr-console-top{display:flex;align-items:center;justify-content:space-between;gap:14px}
|
| 34 |
+
.arr-card-head h2,.arr-console-heading h2{font-size:20px;letter-spacing:-.03em;margin-top:6px}
|
| 35 |
+
.arr-micro{color:#87c9c4;letter-spacing:.16em;font-size:9px;font-weight:800}
|
| 36 |
+
.arr-kind{border:1px solid #385b6b;border-radius:30px;color:#91ecd1;background:#17363d;padding:7px 12px;font-size:9px;font-weight:800;letter-spacing:.08em;white-space:nowrap}
|
| 37 |
+
.arr-desc{color:#91aab9;line-height:1.6;margin:10px 0 16px!important;font-size:12px;max-width:920px}
|
| 38 |
+
.arr-desc strong{color:#e4f3f2}
|
| 39 |
+
.arr-plan-content{display:grid;grid-template-columns:repeat(auto-fill,minmax(min(100%,365px),1fr));gap:9px;margin:13px 0}
|
| 40 |
+
.arr-plan-row{display:flex;align-items:center;gap:10px;min-width:0;border:1px solid #2a3c4f;border-radius:9px;padding:9px 10px;background:#152638}
|
| 41 |
+
.arr-plan-name{min-width:75px;flex:1;border:1px solid transparent;border-radius:4px;background:transparent;color:#dbeaf4;font-size:11px;padding:6px}
|
| 42 |
+
.arr-plan-name:focus{border-color:#70c7c4;outline:none;background:#1d3144}
|
| 43 |
+
.arr-check input{width:16px;height:16px;accent-color:#70e7c9}
|
| 44 |
+
.arr-plan-score{width:64px;display:grid;gap:4px;flex-shrink:0;color:#a2b5bf;font-size:9px;text-align:right}
|
| 45 |
+
.arr-score-bar{width:100%;height:3px;border-radius:4px;background:#2d4050;overflow:hidden}
|
| 46 |
+
.arr-score-bar i{display:block;background:#71d3c5;height:100%}
|
| 47 |
+
.arr-planned-pill{font-size:8px;font-weight:900;color:#d4bb79;background:#3f3928;padding:5px;border-radius:4px}
|
| 48 |
+
.arr-remove{padding:0 3px;background:transparent;border:0;color:#91a1af;font-size:18px}
|
| 49 |
+
.arr-remove:hover{color:#ff8f99}
|
| 50 |
+
.arr-plan-asterisk{grid-column:1/-1;color:#879eac;font-size:10px}
|
| 51 |
+
.arr-empty-inline{color:#93abb9;font-size:12px;padding:13px;background:#142332;border:1px dashed #34485b;border-radius:8px}
|
| 52 |
+
.arr-plan-foot{border-top:1px solid #263a4c;display:flex;justify-content:space-between;gap:12px;align-items:center;padding-top:16px}
|
| 53 |
+
.arr-separate-group>span{font-size:10px;color:#93b5bc}
|
| 54 |
+
.arr-separate-group select{color:#d8eff5;background:#132533;border:1px solid #375365;border-radius:8px;padding:9px 13px;max-width:300px;font-size:11px}
|
| 55 |
+
.arr-separate-group select option{background:#132533}
|
| 56 |
+
.arr-help-text{margin-top:12px;color:#89a1b3;font-size:11px}
|
| 57 |
+
.arr-console{overflow:hidden}
|
| 58 |
+
.arr-console-top{padding:20px 20px 16px}
|
| 59 |
+
.arr-toolbar{gap:8px}
|
| 60 |
+
.arr-compact{display:flex;align-items:center;gap:8px;color:#91b0be;font-weight:800;font-size:9px;letter-spacing:.09em}
|
| 61 |
+
.arr-compact input{width:80px;accent-color:#71e4ca}
|
| 62 |
+
.arr-overview-box{padding:0 20px}
|
| 63 |
+
.arr-overview-title{display:flex;justify-content:space-between;background:#0b1928;border:1px solid #294151;border-bottom:0;border-radius:9px 9px 0 0;padding:10px 15px;color:#80c6bd;font-size:9px;letter-spacing:.16em;font-weight:850}
|
| 64 |
+
.arr-overview-title span:last-child{color:#6b91a4}
|
| 65 |
+
.arr-overview-canvas{position:relative;background:#0a1320;border:1px solid #294151;overflow:hidden;height:136px}
|
| 66 |
+
#arrOverview{display:block;width:100%;height:100%;cursor:crosshair}
|
| 67 |
+
.arr-overview-empty{position:absolute;inset:0;display:grid;place-items:center;color:#788f9e;font-size:12px;text-align:center;padding:15px;pointer-events:none}
|
| 68 |
+
.arr-playhead{position:absolute;top:0;bottom:0;border-left:2px solid #f8f6d5;box-shadow:0 0 11px #fff9;left:0;pointer-events:none}
|
| 69 |
+
.arr-ruler{display:flex;justify-content:space-between;padding:9px 10px;background:#0c1b2b;border:1px solid #294151;border-top:0;border-radius:0 0 8px 8px;color:#8ca9bd;font-size:10px;font-variant-numeric:tabular-nums}
|
| 70 |
+
.arr-mix-meta{display:flex;align-items:center;justify-content:space-between;gap:10px;flex-wrap:wrap;padding:14px 20px}
|
| 71 |
+
.arr-selection{display:flex;align-items:center;gap:8px;color:#9faebc;font-size:11px}
|
| 72 |
+
.arr-selection strong{color:#80e7cf}
|
| 73 |
+
.arr-sep{color:#43687a}
|
| 74 |
+
.arr-mix-warning{color:#8ba7b5;font-size:10px}
|
| 75 |
+
.arr-tracks-wrap{padding:0 20px 16px;overflow-x:auto}
|
| 76 |
+
.arr-track-labels,.arr-track{display:grid;grid-template-columns:260px 156px minmax(230px,1fr) 230px;gap:0;min-width:906px}
|
| 77 |
+
.arr-track-labels{background:#101c2b;color:#6c93a6;font-size:8px;letter-spacing:.12em;font-weight:850;border:1px solid #2b4153;border-bottom:0;border-radius:8px 8px 0 0}
|
| 78 |
+
.arr-track-labels>div{padding:13px 12px}
|
| 79 |
+
.arr-track-labels>div+div{border-left:1px solid #2b4153}
|
| 80 |
+
.arr-track{border:1px solid #2a3f52;border-bottom:0;background:#132132;min-height:116px}
|
| 81 |
+
.arr-track:last-child{border-bottom:1px solid #2a3f52;border-radius:0 0 8px 8px}
|
| 82 |
+
.arr-track:nth-child(even){background:#12202f}
|
| 83 |
+
.arr-track>div+div{border-left:1px solid #2a3f52}
|
| 84 |
+
.arr-track-left{padding:12px 12px;min-width:0}
|
| 85 |
+
.arr-track-name{display:flex;gap:10px;align-items:center;min-width:0}
|
| 86 |
+
.arr-track-dot{width:7px;height:31px;border-radius:5px;background:var(--arr-color);box-shadow:0 0 12px var(--arr-color);flex-shrink:0}
|
| 87 |
+
.arr-track-name>div{min-width:0;flex:1}
|
| 88 |
+
.arr-track-name strong{font-size:12px;display:block;overflow:hidden;white-space:nowrap;text-overflow:ellipsis}
|
| 89 |
+
.arr-track-name small{display:block;color:var(--arr-color);font-size:8px;letter-spacing:.09em;margin-top:5px}
|
| 90 |
+
.arr-track-preview{color:#c0dde7;background:#1c3244;border:1px solid #395062;width:27px;height:27px;display:grid;place-items:center;border-radius:6px}
|
| 91 |
+
.arr-track-preview:hover{background:#2d5863;color:white}
|
| 92 |
+
.arr-track-ctrl{margin-top:15px;display:flex;align-items:center;gap:6px}
|
| 93 |
+
.arr-mute,.arr-solo{width:28px;height:26px;flex-shrink:0;border:1px solid #375167;border-radius:5px;font-size:10px;font-weight:850;color:#8fabb9;background:#1b3041}
|
| 94 |
+
.arr-mute.on{background:#6b343a;border-color:#db7a7d;color:#ffe2e1}
|
| 95 |
+
.arr-solo.on{background:#675027;border-color:#f5c86b;color:#fff1c3}
|
| 96 |
+
.arr-track-ctrl input{min-width:35px;max-width:100%;flex:1;accent-color:var(--arr-color);height:15px}
|
| 97 |
+
.arr-track-ctrl output{width:39px;text-align:right;flex-shrink:0;font-size:9px;font-variant-numeric:tabular-nums;color:#c2d6e1}
|
| 98 |
+
.arr-pan-area{padding:15px 13px;display:flex;align-items:center;flex-direction:column;justify-content:center;gap:8px}
|
| 99 |
+
.arr-pan-label{width:100%;display:flex;justify-content:space-between;color:#88acbe;font-size:9px;letter-spacing:.1em;font-weight:800}
|
| 100 |
+
.arr-pan-label span:nth-child(2){font-size:7px;color:#6d93a1}
|
| 101 |
+
.arr-pan-guide{position:relative;width:100%;display:flex;align-items:center}
|
| 102 |
+
.arr-pan-guide>i{position:absolute;left:50%;top:-7px;bottom:-8px;border-left:1px dashed #63819a;pointer-events:none}
|
| 103 |
+
.arr-pan-guide input{width:100%;accent-color:var(--arr-color);z-index:1}
|
| 104 |
+
.arr-pan-area output{color:var(--arr-color);font-weight:850;font-size:12px;font-variant-numeric:tabular-nums}
|
| 105 |
+
.arr-wave-area{position:relative;background:#0a1421;overflow:hidden;min-width:0}
|
| 106 |
+
.arr-stemwave{display:block;width:100%;height:116px;cursor:crosshair}
|
| 107 |
+
.arr-stemhead{position:absolute;top:0;bottom:0;width:1px;background:#ecfbf4;box-shadow:0 0 9px #f7ffde;left:0;pointer-events:none}
|
| 108 |
+
.arr-fx-area{padding:10px;align-self:stretch;min-width:0}
|
| 109 |
+
.arr-fx{border:1px solid #304d60;background:#192c3d;border-radius:7px}
|
| 110 |
+
.arr-fx summary{cursor:pointer;padding:11px 12px;list-style:none;color:#d0e4e8;font-size:11px;font-weight:700;display:flex;gap:9px;align-items:center}
|
| 111 |
+
.arr-fx summary::-webkit-details-marker{display:none}
|
| 112 |
+
.arr-fx summary>span{color:var(--arr-color)}
|
| 113 |
+
.arr-fx summary>b{margin-left:auto;color:#8da5b7}
|
| 114 |
+
.arr-fx[open] summary>b{transform:rotate(45deg)}
|
| 115 |
+
.arr-fx-stack{padding:11px;display:grid;gap:12px;border-top:1px solid #344a59}
|
| 116 |
+
.arr-fx-stack label{display:grid;grid-template-columns:1fr auto;font-size:9px;font-weight:800;color:#a2c3cc;gap:6px}
|
| 117 |
+
.arr-fx-stack input{grid-column:1/-1;width:100%;accent-color:var(--arr-color)}
|
| 118 |
+
.arr-fx-stack span{color:#e5f1f4;font-variant-numeric:tabular-nums}
|
| 119 |
+
.arr-fx-stack small{color:#91a6b6;font-size:9px;line-height:1.5}
|
| 120 |
+
.arr-empty-track{min-height:170px;display:flex;flex-direction:column;align-items:center;justify-content:center;gap:9px;padding:24px;text-align:center;color:#8aa3b2;border:1px dashed #385168;border-radius:0 0 9px 9px;font-size:11px;background:#111d2c}
|
| 121 |
+
.arr-empty-track strong{color:#98d7cc;letter-spacing:.15em;font-size:10px}
|
| 122 |
+
.arr-mixer-footer{padding:18px 20px 20px;border-top:1px solid #2b4154;display:flex;align-items:end;justify-content:space-between;gap:18px}
|
| 123 |
+
.arr-transform{display:flex;align-items:center;gap:18px;flex-wrap:wrap}
|
| 124 |
+
.arr-transform label{display:flex;flex-direction:column;gap:8px;font-size:9px;font-weight:800;letter-spacing:.08em;color:#8dabba;min-width:145px}
|
| 125 |
+
.arr-transform label span{font-size:12px;color:#8cf4d5;letter-spacing:0;font-variant-numeric:tabular-nums}
|
| 126 |
+
.arr-transform input{accent-color:#8af4d5;width:165px}
|
| 127 |
+
.arr-transform small{font-size:10px;color:#8498a8;max-width:200px;line-height:1.5}
|
| 128 |
+
.arr-footer-actions{justify-content:end}
|
| 129 |
+
.arr-render-report{font-size:10px;color:#96beae;font-variant-numeric:tabular-nums;max-width:250px}
|
| 130 |
+
.arr-download.disabled{pointer-events:none;opacity:.45}
|
| 131 |
+
.arr-disclaimer{font-size:11px;color:#859db0;line-height:1.6;margin:13px 8px 0!important}
|
| 132 |
+
@media(max-width:1600px){
|
| 133 |
+
.arr-track-labels,.arr-track{grid-template-columns:218px 130px minmax(200px,1fr) 198px;min-width:746px}
|
| 134 |
+
.arr-track-name strong{font-size:11px}
|
| 135 |
+
.arr-fx summary{padding:9px}
|
| 136 |
+
.arr-track-ctrl output{font-size:8px;width:34px}
|
| 137 |
+
}
|
| 138 |
+
@media(max-width:1100px){
|
| 139 |
+
.arr-header{align-items:start;flex-wrap:wrap}
|
| 140 |
+
.arr-plan-foot{align-items:start;flex-direction:column}
|
| 141 |
+
.arr-workflow{gap:5px}.arr-step{padding:9px}.arr-workflow-arrow{font-size:12px}
|
| 142 |
+
.arr-step strong{font-size:9px}.arr-step small{font-size:9px}
|
| 143 |
+
.arr-mixer-footer{align-items:start;flex-direction:column}
|
| 144 |
+
}
|
| 145 |
+
@media(max-width:760px){
|
| 146 |
+
main:has(>.arr-view.active){padding:20px 12px}
|
| 147 |
+
.arr-header{padding:4px 4px 17px}
|
| 148 |
+
.arr-title h1{font-size:29px}
|
| 149 |
+
.arr-header-actions{width:100%;justify-content:space-between}
|
| 150 |
+
.arr-header-actions .arr-btn{flex:1}
|
| 151 |
+
.arr-workflow{display:grid;grid-template-columns:1fr 1fr}
|
| 152 |
+
.arr-workflow-arrow{display:none}
|
| 153 |
+
.arr-step{min-height:61px}
|
| 154 |
+
.arr-planning{padding:14px}
|
| 155 |
+
.arr-card-head{flex-wrap:wrap}
|
| 156 |
+
.arr-plan-content{grid-template-columns:minmax(0,1fr)}
|
| 157 |
+
.arr-console-top{align-items:start;flex-direction:column;padding:16px}
|
| 158 |
+
.arr-overview-box,.arr-tracks-wrap{padding-left:12px;padding-right:12px}
|
| 159 |
+
.arr-overview-canvas{height:112px}
|
| 160 |
+
.arr-overview-canvas canvas{height:112px}
|
| 161 |
+
.arr-mix-meta{padding:12px}
|
| 162 |
+
.arr-mixer-footer{padding:14px 12px}
|
| 163 |
+
.arr-footer-actions{justify-content:start}
|
| 164 |
+
.arr-separate-group{align-items:stretch}
|
| 165 |
+
.arr-separate-group>span{width:100%}
|
| 166 |
+
.arr-separate-group select{flex:1;max-width:100%}
|
| 167 |
+
.arr-plan-row{gap:6px;padding:7px}
|
| 168 |
+
}
|
| 169 |
+
|
| 170 |
+
.arr-scroll-label{display:flex;align-items:center;justify-content:end;gap:10px;padding:8px 3px;color:#89a9b6;font-size:9px;font-weight:800;letter-spacing:.1em}
|
| 171 |
+
.arr-scroll-label input{width:min(320px,60%);accent-color:#70e4cb}
|
app/static/arrangement.js
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/* ABSOLUTION Ω v0.6 — no external libraries, analytics or remote requests.
|
| 2 |
+
* Frontend renders real sampled stem envelopes. Editable inventory is not audio.
|
| 3 |
+
* Mixer FX are applied only by backend after an explicit Render action.
|
| 4 |
+
*/
|
| 5 |
+
"use strict";
|
| 6 |
+
(() => {
|
| 7 |
+
const A=document.querySelector.bind(document);
|
| 8 |
+
const ROOT="/api/v1";
|
| 9 |
+
const COLORS=["#5ee2cf","#f0ba72","#a99afb","#f579a2","#6eaafb","#bcf178","#f68d65",
|
| 10 |
+
"#6ed7f3","#d59bf4","#e7df79","#ef87b5","#7ab3c3"];
|
| 11 |
+
const G={
|
| 12 |
+
inventory:null,plan:[],real:[],peaks:{},settings:{},zoom:1,scroll:0,
|
| 13 |
+
mixed:null,projectId:null,rubberband:false,serverModel:true,rendering:false,
|
| 14 |
+
length:0
|
| 15 |
+
};
|
| 16 |
+
const escape=(x)=>String(x??"").replace(/[&<>"']/g,c=>({"&":"&","<":"<",">":">",'"':""","'":"'"}[c]));
|
| 17 |
+
const dt=t=>{if(!Number.isFinite(t))return "—";let h=Math.floor(t/3600),m=Math.floor(t%3600/60),s=Math.floor(t%60);return h?`${h}:${String(m).padStart(2,"0")}:${String(s).padStart(2,"0")}`:`${m}:${String(s).padStart(2,"0")}`;};
|
| 18 |
+
const byId=x=>document.getElementById(x);
|
| 19 |
+
const notice=(txt,err=false)=>{if(typeof toast==="function")toast(txt,err);};
|
| 20 |
+
async function request(route,init={}){
|
| 21 |
+
if(typeof api==="function")return api(ROOT+route,init);
|
| 22 |
+
const r=await fetch(ROOT+route,init);if(!r.ok)throw new Error(`HTTP ${r.status}`);return r.json();
|
| 23 |
+
}
|
| 24 |
+
function updateStatus(){
|
| 25 |
+
byId("arrSourceName").textContent=state.asset?.filename||"Noch keine Datei — importiere im Studio oder lade die Demo.";
|
| 26 |
+
byId("arrStemStatus").textContent=`${G.real.length} echte Stems`;
|
| 27 |
+
byId("arrActiveTracks").textContent=`${G.real.length} reale Spuren`;
|
| 28 |
+
byId("arrInspect").disabled=!state.asset||G.rendering;
|
| 29 |
+
byId("arrSeparate").disabled=!state.asset||G.rendering;
|
| 30 |
+
byId("arrRender").disabled=!G.real.length||G.rendering;
|
| 31 |
+
byId("arrSourceName").title=state.asset?.filename||"";
|
| 32 |
+
const solos=G.real.filter(x=>G.settings[x]?.solo);
|
| 33 |
+
byId("arrSoloList").textContent=solos.length?`SOLO: ${solos.join(" · ")}`:"Keine Solo-Spur aktiv";
|
| 34 |
+
}
|
| 35 |
+
function setUnrendered(){
|
| 36 |
+
G.mixed=null;
|
| 37 |
+
byId("arrListenMix").disabled=true;
|
| 38 |
+
const dl=byId("arrDownload");dl.removeAttribute("href");dl.classList.add("disabled");dl.setAttribute("aria-disabled","true");
|
| 39 |
+
byId("arrRenderReport").textContent=G.real.length?"Änderungen ungerendert":"Noch kein Mix berechnet";
|
| 40 |
+
}
|
| 41 |
+
function reset(){
|
| 42 |
+
G.projectId=null;G.inventory=null;G.plan=[];G.real=[];G.peaks={};G.settings={};G.mixed=null;G.length=0;
|
| 43 |
+
byId("arrPlanContent").innerHTML='<div class="arr-empty-inline">Noch keine Vorinventur. Klicke auf „Mini-KI analysieren“.</div>';
|
| 44 |
+
renderTracks();updateStatus();setUnrendered();draw();
|
| 45 |
+
}
|
| 46 |
+
async function onProject(manifest){
|
| 47 |
+
const projectId=manifest.id;
|
| 48 |
+
const different=G.projectId!==projectId;
|
| 49 |
+
G.projectId=projectId;G.inventory=manifest.inventory||null;
|
| 50 |
+
G.plan=(manifest.plan||[]).map(p=>({...p}));
|
| 51 |
+
G.real=Object.keys(manifest.stems||{});
|
| 52 |
+
G.length=Number(manifest.analysis?.duration_seconds)||0;
|
| 53 |
+
if(different){G.peaks={};G.settings={};G.mixed=null;}
|
| 54 |
+
const settings=manifest.mixer?.settings?.tracks||{};
|
| 55 |
+
if(different){for(const [n,p] of Object.entries(settings))G.settings[n]={...p};}
|
| 56 |
+
if(different && manifest.mixer)G.mixed=manifest.mixer;
|
| 57 |
+
if(different){
|
| 58 |
+
const tempo=Math.round((manifest.mixer?.settings?.tempo??1)*100);
|
| 59 |
+
const pitch=Number(manifest.mixer?.settings?.pitch_semitones??0);
|
| 60 |
+
byId("arrTempo").value=String(tempo);
|
| 61 |
+
byId("arrPitch").value=String(pitch);
|
| 62 |
+
byId("arrTempoOut").textContent=tempo+" %";
|
| 63 |
+
byId("arrPitchOut").textContent=(pitch>=0?"+":"")+pitch+" HT";
|
| 64 |
+
}
|
| 65 |
+
renderPlan();renderTracks();updateStatus();
|
| 66 |
+
if(G.mixed)setMixed(G.mixed);
|
| 67 |
+
else setUnrendered();
|
| 68 |
+
await Promise.all([
|
| 69 |
+
...["original",...G.real].map(async name=>{
|
| 70 |
+
if(G.peaks[name])return;
|
| 71 |
+
try{
|
| 72 |
+
const data=await request(`/projects/${encodeURIComponent(projectId)}/wave/${encodeURIComponent(name)}?points=480`);
|
| 73 |
+
if(G.projectId===projectId)G.peaks[name]=data.samples||[];
|
| 74 |
+
}catch(e){console.warn("Waveform not ready",name,e);}
|
| 75 |
+
}),
|
| 76 |
+
refreshModelStatus()
|
| 77 |
+
]);
|
| 78 |
+
if(G.projectId===projectId)draw();
|
| 79 |
+
}
|
| 80 |
+
async function refreshModelStatus(){
|
| 81 |
+
try{
|
| 82 |
+
const m=await request("/models");
|
| 83 |
+
const neural=m.models?.find(x=>x.id==="demucs");
|
| 84 |
+
const opt=byId("arrModel").querySelector('option[value="demucs"]');
|
| 85 |
+
opt.disabled=!neural?.ready;
|
| 86 |
+
opt.textContent=neural?.ready?"Demucs · 4 Gruppen (konfiguriert)":"Demucs · lokale Gewichte fehlen";
|
| 87 |
+
const h=await request("/health");
|
| 88 |
+
G.rubberband=!!h.rubberband_ready;
|
| 89 |
+
byId("arrRubberbandNote").textContent=G.rubberband?
|
| 90 |
+
"Tempo und Transposition verwenden FFmpeg/Rubber Band beim Export. Tonart-Erkennung ist nicht implementiert.":
|
| 91 |
+
"Unabhängiges Tempo/Transponieren benötigt FFmpeg mit Rubber Band; Standard-Mix funktioniert ohne.";
|
| 92 |
+
for(const id of ["arrTempo","arrPitch"]){byId(id).disabled=!G.rubberband;}
|
| 93 |
+
}catch(e){console.warn("Could not refresh model capabilities",e);}
|
| 94 |
+
}
|
| 95 |
+
function renderPlan(){
|
| 96 |
+
const c=byId("arrPlanContent");
|
| 97 |
+
if(!G.inventory&&!G.plan.length){c.innerHTML='<div class="arr-empty-inline">Noch keine Mini-KI-Vorinventur. Die Hypothesen erscheinen hier.</div>';return;}
|
| 98 |
+
const acts=new Map((G.inventory?.detections||[]).map(x=>[x.id,x]));
|
| 99 |
+
c.innerHTML=G.plan.map((p,i)=>{
|
| 100 |
+
const act=acts.get(p.id);
|
| 101 |
+
return `<div class="arr-plan-row" data-plan="${i}">
|
| 102 |
+
<label class="arr-check"><input type="checkbox" class="arr-plan-on" ${p.enabled?"checked":""}><span></span></label>
|
| 103 |
+
<input class="arr-plan-name" aria-label="Trennziel ${i+1}" maxlength="100" value="${escape(p.label)}">
|
| 104 |
+
<div class="arr-plan-score">${act?`<div class="arr-score-bar"><i style="width:${Math.round(act.score*100)}%"></i></div><span>${Math.round(act.score*100)} / 100*</span>`:'<span>Manuell</span>'}</div>
|
| 105 |
+
<span class="arr-planned-pill">PLAN</span>
|
| 106 |
+
<button class="arr-remove" title="Planpunkt entfernen" aria-label="Trennziel entfernen">×</button>
|
| 107 |
+
</div>`;
|
| 108 |
+
}).join("")+`<small class="arr-plan-asterisk">* Unkalibrierte Modellaktivität — ausdrücklich keine Wahrscheinlichkeit, dass ein Instrument vorhanden ist.</small>`;
|
| 109 |
+
}
|
| 110 |
+
function pullPlanEdits(){
|
| 111 |
+
for(const node of byId("arrPlanContent").querySelectorAll(".arr-plan-row")){
|
| 112 |
+
const i=Number(node.dataset.plan);
|
| 113 |
+
if(G.plan[i]){G.plan[i].label=node.querySelector(".arr-plan-name").value.trim().slice(0,100)||"Unbenannt";
|
| 114 |
+
G.plan[i].enabled=node.querySelector(".arr-plan-on").checked;}
|
| 115 |
+
}
|
| 116 |
+
}
|
| 117 |
+
async function inspect(){
|
| 118 |
+
if(!state.projectId){notice("Importiere zuerst im Studio eine Datei.",true);return;}
|
| 119 |
+
const b=byId("arrInspect");b.disabled=true;b.textContent="✧ Analysiere lokal …";
|
| 120 |
+
try{
|
| 121 |
+
const result=await request(`/projects/${state.projectId}/inventory`,{method:"POST"});
|
| 122 |
+
G.inventory=result.inventory;G.plan=result.plan||[];
|
| 123 |
+
renderPlan();notice(`Mini-Modell: ${G.inventory.sampled_windows} Ausschnitte analysiert. Bitte Hypothesen prüfen.`);
|
| 124 |
+
}catch(e){notice("Mini-KI: "+e.message,true);}
|
| 125 |
+
finally{b.disabled=false;b.textContent="✧ Mini-KI analysieren";}
|
| 126 |
+
}
|
| 127 |
+
async function savePlan(){
|
| 128 |
+
if(!state.projectId){notice("Erst Datei importieren.",true);return;}
|
| 129 |
+
pullPlanEdits();
|
| 130 |
+
try{
|
| 131 |
+
await request(`/projects/${state.projectId}/plan`,{
|
| 132 |
+
method:"PUT",headers:{"content-type":"application/json"},
|
| 133 |
+
body:JSON.stringify({tracks:G.plan})
|
| 134 |
+
});
|
| 135 |
+
notice("Trennplan gespeichert. Noch keine Audiospur wurde dadurch erzeugt.");
|
| 136 |
+
}catch(e){notice("Trennplan: "+e.message,true);}
|
| 137 |
+
}
|
| 138 |
+
function defaultSettings(){return {gain_db:0,pan:0,mute:false,solo:false,highpass_hz:0,lowpass_hz:0,width:1,drive:0};}
|
| 139 |
+
function getSettings(name){return G.settings[name]||(G.settings[name]=defaultSettings());}
|
| 140 |
+
function colorFor(index){return COLORS[index%COLORS.length];}
|
| 141 |
+
function pretty(name){
|
| 142 |
+
const labels={vocals:"Gesang / Vocals",drums:"Schlagzeug / Drums",
|
| 143 |
+
bass:"Bass",other:"Andere Instrumente",harmonic:"Harmonische Klanganteile",
|
| 144 |
+
percussive:"Perkussive Klanganteile",residual:"Residuum / Restmaterial"};
|
| 145 |
+
return labels[name]||name.replace(/[_-]/g," ");
|
| 146 |
+
}
|
| 147 |
+
function renderTracks(){
|
| 148 |
+
const wrap=byId("arrTracks");
|
| 149 |
+
if(!G.real.length){
|
| 150 |
+
wrap.innerHTML='<div class="arr-empty-track"><strong>NOCH KEINE SEPARIERTEN SPUREN</strong><span>Analysiere den Track, überprüfe den Plan und starte die Separation. Die vorhandenen Stems erscheinen dann farbig auf der Timeline.</span></div>';
|
| 151 |
+
updateStatus();return;
|
| 152 |
+
}
|
| 153 |
+
wrap.innerHTML=G.real.map((name,i)=>{
|
| 154 |
+
const p=getSettings(name),color=colorFor(i);
|
| 155 |
+
return `<article class="arr-track" style="--arr-color:${color}" data-index="${i}">
|
| 156 |
+
<div class="arr-track-left">
|
| 157 |
+
<div class="arr-track-name"><span class="arr-track-dot"></span><div><strong title="${escape(name)}">${escape(pretty(name))}</strong><small>STEM ${String(i+1).padStart(2,"0")} · REAL AUDIO</small></div>
|
| 158 |
+
<button type="button" class="arr-track-preview" data-action="play" title="Diese Spur einzeln hören" aria-label="${escape(pretty(name))} anhören">▶</button>
|
| 159 |
+
</div>
|
| 160 |
+
<div class="arr-track-ctrl"><button class="arr-mute ${p.mute?"on":""}" type="button" data-action="mute" aria-pressed="${!!p.mute}" title="Mute">M</button>
|
| 161 |
+
<button class="arr-solo ${p.solo?"on":""}" type="button" data-action="solo" aria-pressed="${!!p.solo}" title="Solo">S</button>
|
| 162 |
+
<input type="range" data-param="gain_db" min="-48" max="12" step=".5" value="${p.gain_db}" aria-label="${escape(pretty(name))} Lautstärke">
|
| 163 |
+
<output data-output="gain_db">${p.gain_db>0?"+":""}${p.gain_db} dB</output>
|
| 164 |
+
</div>
|
| 165 |
+
</div>
|
| 166 |
+
<div class="arr-pan-area"><div class="arr-pan-label"><span>L</span><span>STEREO FIELD</span><span>R</span></div>
|
| 167 |
+
<div class="arr-pan-guide"><i></i><input type="range" data-param="pan" min="-1" max="1" step=".01" value="${p.pan}" aria-label="${escape(pretty(name))} Stereo-Panorama"></div>
|
| 168 |
+
<output data-output="pan">${p.pan===0?"C":p.pan<0?`L${Math.round(-p.pan*100)}`:`R${Math.round(p.pan*100)}`}</output>
|
| 169 |
+
</div>
|
| 170 |
+
<div class="arr-wave-area"><canvas class="arr-stemwave" data-wave="${i}" height="114" role="img" aria-label="Waveform ${escape(pretty(name))}" tabindex="0"></canvas><i class="arr-stemhead" aria-hidden="true"></i></div>
|
| 171 |
+
<div class="arr-fx-area"><details class="arr-fx"><summary><span>◈</span> Effekte <b>+</b></summary><div class="arr-fx-stack">
|
| 172 |
+
<label>LOW CUT <span data-output="highpass_hz">${p.highpass_hz||"Aus"}${p.highpass_hz?" Hz":""}</span><input type="range" data-param="highpass_hz" min="0" max="400" step="5" value="${p.highpass_hz}"></label>
|
| 173 |
+
<label>HIGH CUT <span data-output="lowpass_hz">${p.lowpass_hz?p.lowpass_hz+" Hz":"Aus"}</span><input type="range" data-param="lowpass_hz" min="0" max="18000" step="100" value="${p.lowpass_hz}"></label>
|
| 174 |
+
<label>SÄTTIGUNG <span data-output="drive">${Math.round(p.drive*100)} %</span><input type="range" data-param="drive" min="0" max="1" step=".01" value="${p.drive}"></label>
|
| 175 |
+
<label>STEREO WIDTH <span data-output="width">${Math.round(p.width*100)} %</span><input type="range" data-param="width" min="0" max="2" step=".02" value="${p.width}"></label>
|
| 176 |
+
<small>Effekte wirken erst nach „Mix berechnen“ und verändern nie das Original.</small>
|
| 177 |
+
</div></details></div>
|
| 178 |
+
</article>`;
|
| 179 |
+
}).join("");
|
| 180 |
+
updateStatus();requestAnimationFrame(draw);
|
| 181 |
+
}
|
| 182 |
+
function outputValue(param,p){
|
| 183 |
+
switch(param){
|
| 184 |
+
case"gain_db":return `${p>0?"+":""}${p} dB`;
|
| 185 |
+
case"pan":return p===0?"C":p<0?`L${Math.round(-p*100)}`:`R${Math.round(p*100)}`;
|
| 186 |
+
case"highpass_hz":return p?p+" Hz":"Aus";
|
| 187 |
+
case"lowpass_hz":return p?p+" Hz":"Aus";
|
| 188 |
+
case"drive":case"width":return Math.round(p*100)+" %";
|
| 189 |
+
}return String(p);
|
| 190 |
+
}
|
| 191 |
+
function drawCanvas(canvas,fn){
|
| 192 |
+
if(!canvas||!canvas.isConnected)return;
|
| 193 |
+
const cssW=canvas.getBoundingClientRect().width;
|
| 194 |
+
if(cssW<8)return;
|
| 195 |
+
const cssH=canvas.getBoundingClientRect().height;
|
| 196 |
+
const dpr=Math.min(2,window.devicePixelRatio||1);
|
| 197 |
+
canvas.width=Math.floor(cssW*dpr);
|
| 198 |
+
canvas.height=Math.floor(cssH*dpr);
|
| 199 |
+
const ctx=canvas.getContext("2d");ctx.setTransform(dpr,0,0,dpr,0,0);
|
| 200 |
+
fn(ctx,cssW,cssH);
|
| 201 |
+
}
|
| 202 |
+
function grid(ctx,w,h){
|
| 203 |
+
ctx.fillStyle="#0a1320";ctx.fillRect(0,0,w,h);
|
| 204 |
+
ctx.strokeStyle="#203044";ctx.lineWidth=.7;
|
| 205 |
+
for(let i=0;i<=16;i++){const x=Math.round(i*w/16)+.5;ctx.beginPath();ctx.moveTo(x,0);ctx.lineTo(x,h);ctx.stroke();}
|
| 206 |
+
ctx.strokeStyle="#30435a";ctx.beginPath();ctx.moveTo(0,h/2+.5);ctx.lineTo(w,h/2+.5);ctx.stroke();
|
| 207 |
+
}
|
| 208 |
+
function plot(ctx,peaks,color,w,h,zoom=1,scroll=0,alpha=1){
|
| 209 |
+
if(!peaks?.length)return;
|
| 210 |
+
ctx.strokeStyle=color;ctx.lineWidth=Math.max(.75,1/Math.min(zoom,2));ctx.globalAlpha=alpha;
|
| 211 |
+
const n=peaks.length;const visible=1/zoom;
|
| 212 |
+
const start=scroll*(1-visible);
|
| 213 |
+
for(let x=0;x<w;x+=2){
|
| 214 |
+
const fraction=x/Math.max(1,w);
|
| 215 |
+
const a=Math.floor((start+fraction*visible)*n);
|
| 216 |
+
const b=Math.max(a+1,Math.ceil((start+(fraction+2)/w*visible)*n));
|
| 217 |
+
let val=0;
|
| 218 |
+
for(let j=Math.max(0,a);j<Math.min(n,b);j++){val=Math.max(val,Math.abs(peaks[j]));}
|
| 219 |
+
const v=Math.min(1,Math.sqrt(val))*h*.45;
|
| 220 |
+
ctx.beginPath();ctx.moveTo(x,h/2-v);ctx.lineTo(x,h/2+v);ctx.stroke();
|
| 221 |
+
}
|
| 222 |
+
ctx.globalAlpha=1;
|
| 223 |
+
}
|
| 224 |
+
function draw(){
|
| 225 |
+
const ov=byId("arrOverview");
|
| 226 |
+
drawCanvas(ov,(ctx,w,h)=>{
|
| 227 |
+
grid(ctx,w,h);
|
| 228 |
+
if(G.real.length){
|
| 229 |
+
G.real.forEach((name,i)=>plot(ctx,G.peaks[name],colorFor(i),w,h,1,0,.7));
|
| 230 |
+
}else if(G.peaks.original?.length){plot(ctx,G.peaks.original,"#667688",w,h,1,0,.65);}
|
| 231 |
+
});
|
| 232 |
+
byId("arrOverviewEmpty").hidden=G.real.length>0;
|
| 233 |
+
for(const canvas of document.querySelectorAll(".arr-stemwave")){
|
| 234 |
+
const i=Number(canvas.dataset.wave),name=G.real[i];
|
| 235 |
+
drawCanvas(canvas,(ctx,w,h)=>{
|
| 236 |
+
grid(ctx,w,h);
|
| 237 |
+
plot(ctx,G.peaks[name],colorFor(i),w,h,G.zoom,G.scroll,.95);
|
| 238 |
+
});
|
| 239 |
+
}
|
| 240 |
+
const span=G.length/G.zoom,start=G.scroll*(G.length-span);
|
| 241 |
+
const ruler=byId("arrRuler");
|
| 242 |
+
ruler.innerHTML=Array.from({length:5},(_,i)=>`<span>${dt(start+span*i/4)}</span>`).join("");
|
| 243 |
+
updatePlayhead();
|
| 244 |
+
}
|
| 245 |
+
function updatePlayhead(){
|
| 246 |
+
const t=audio?.currentTime||0;
|
| 247 |
+
const fraction=G.length>0?Math.max(0,Math.min(1,t/G.length)):0;
|
| 248 |
+
byId("arrPlayhead").style.left=(fraction*100)+"%";
|
| 249 |
+
const visible=1/G.zoom;
|
| 250 |
+
const start=G.scroll*(1-visible);
|
| 251 |
+
const local=(fraction-start)/visible;
|
| 252 |
+
for(const node of document.querySelectorAll(".arr-stemhead")){
|
| 253 |
+
node.style.display=local>=0&&local<=1?"block":"none";
|
| 254 |
+
node.style.left=(local*100)+"%";
|
| 255 |
+
}
|
| 256 |
+
}
|
| 257 |
+
function timelineSeek(e,overview=false){
|
| 258 |
+
if(!G.length)return;
|
| 259 |
+
const rect=e.currentTarget.getBoundingClientRect();
|
| 260 |
+
let f=Math.max(0,Math.min(1,(e.clientX-rect.left)/rect.width));
|
| 261 |
+
if(!overview)f=G.scroll*(1-1/G.zoom)+f/G.zoom;
|
| 262 |
+
audio.currentTime=f*G.length;updatePlayhead();
|
| 263 |
+
}
|
| 264 |
+
function setMixed(mixer){
|
| 265 |
+
G.mixed=mixer;
|
| 266 |
+
byId("arrListenMix").disabled=false;
|
| 267 |
+
const d=byId("arrDownload");
|
| 268 |
+
d.href=`${ROOT}/projects/${encodeURIComponent(G.projectId)}/mixer/audio`;
|
| 269 |
+
d.classList.remove("disabled");d.removeAttribute("aria-disabled");
|
| 270 |
+
const r=mixer.result||{};
|
| 271 |
+
byId("arrRenderReport").textContent=`✓ WAV Float32 · Peak ${r.peak_dbfs??"—"} dBFS${r.clip_warning?" · WARNUNG: über 0 dBFS":""}`;
|
| 272 |
+
}
|
| 273 |
+
async function renderMix(){
|
| 274 |
+
if(!G.real.length || G.rendering){notice("Erst real separieren.",true);return;}
|
| 275 |
+
G.rendering=true;updateStatus();setUnrendered();
|
| 276 |
+
const btn=byId("arrRender");btn.textContent="◴ MIX LÄUFT …";
|
| 277 |
+
const project=G.projectId;
|
| 278 |
+
try{
|
| 279 |
+
const job=await request("/jobs/mix",{method:"POST",
|
| 280 |
+
headers:{"content-type":"application/json"},
|
| 281 |
+
body:JSON.stringify({project_id:project,tracks:G.settings,
|
| 282 |
+
tempo:Number(byId("arrTempo").value)/100,
|
| 283 |
+
pitch_semitones:Number(byId("arrPitch").value)})
|
| 284 |
+
});
|
| 285 |
+
while(true){
|
| 286 |
+
await new Promise(r=>setTimeout(r,400));
|
| 287 |
+
const status=await request("/jobs/"+job.id);
|
| 288 |
+
if(status.status==="failed")throw new Error(status.error||"Mix fehlgeschlagen");
|
| 289 |
+
if(project!==G.projectId)return;
|
| 290 |
+
byId("arrRenderReport").textContent=`Mix wird berechnet: ${status.progress||0} %`;
|
| 291 |
+
if(status.status==="done")break;
|
| 292 |
+
}
|
| 293 |
+
const r=await request(`/projects/${project}/mixer`);
|
| 294 |
+
setMixed(r.mixer);
|
| 295 |
+
notice("Arrangierter Mix gerendert. Hörprobe und Download bereit.");
|
| 296 |
+
}catch(e){notice("Arrangement: "+e.message,true);byId("arrRenderReport").textContent="Mix fehlgeschlagen";}
|
| 297 |
+
finally{G.rendering=false;btn.textContent="◉ Mix berechnen";updateStatus();}
|
| 298 |
+
}
|
| 299 |
+
function listenMix(){
|
| 300 |
+
if(!G.mixed)return;
|
| 301 |
+
audio.pause();
|
| 302 |
+
audio.src=`${ROOT}/projects/${G.projectId}/mixer/audio?v=${encodeURIComponent(G.mixed.id)}`;
|
| 303 |
+
state.playing="arrangement_mix";
|
| 304 |
+
byId("nowPlaying").textContent="Arrangement Mix";
|
| 305 |
+
byId("nowPlayingSub").textContent="Gerenderte Stems · Float WAV";
|
| 306 |
+
audio.load();audio.play().catch(()=>notice("Mix lässt sich nicht abspielen.",true));
|
| 307 |
+
}
|
| 308 |
+
function listeners(){
|
| 309 |
+
byId("arrDemo").addEventListener("click",loadDemo);
|
| 310 |
+
byId("arrInspect").addEventListener("click",inspect);
|
| 311 |
+
byId("arrSavePlan").addEventListener("click",savePlan);
|
| 312 |
+
byId("arrAddPlan").addEventListener("click",()=>{
|
| 313 |
+
pullPlanEdits();
|
| 314 |
+
if(G.plan.length>=128)return notice("Mehr als 128 Plan-Ziele erfordern ein erweitertes Ressourcenprofil.",true);
|
| 315 |
+
G.plan.push({id:"custom_"+Date.now().toString(36)+"_"+G.plan.length,label:"Neues Element",enabled:true});renderPlan();
|
| 316 |
+
});
|
| 317 |
+
byId("arrPlanContent").addEventListener("click",e=>{
|
| 318 |
+
const b=e.target.closest(".arr-remove");if(!b)return;
|
| 319 |
+
pullPlanEdits();G.plan.splice(Number(b.closest(".arr-plan-row").dataset.plan),1);renderPlan();
|
| 320 |
+
});
|
| 321 |
+
byId("arrSeparate").addEventListener("click",()=>{
|
| 322 |
+
if(!state.asset)return notice("Importiere erst Audio.",true);
|
| 323 |
+
const selected=byId("arrModel").value;
|
| 324 |
+
if(selected==="demucs" && byId("arrModel").querySelector('option[value="demucs"]').disabled)
|
| 325 |
+
return notice("Demucs ist ohne lokale Gewichte nicht verfügbar.",true);
|
| 326 |
+
selectMethod(selected);runSeparation();
|
| 327 |
+
});
|
| 328 |
+
byId("arrResetMix").addEventListener("click",()=>{
|
| 329 |
+
G.settings={};for(const n of G.real)G.settings[n]=defaultSettings();
|
| 330 |
+
byId("arrTempo").value=100;byId("arrPitch").value=0;byId("arrTempoOut").textContent="100 %";byId("arrPitchOut").textContent="±0 HT";
|
| 331 |
+
renderTracks();setUnrendered();
|
| 332 |
+
});
|
| 333 |
+
byId("arrTracks").addEventListener("input",e=>{
|
| 334 |
+
const el=e.target;
|
| 335 |
+
if(!el.matches("[data-param]"))return;
|
| 336 |
+
const node=el.closest(".arr-track"),i=Number(node.dataset.index),name=G.real[i];
|
| 337 |
+
if(!name)return;
|
| 338 |
+
const param=el.dataset.param,val=Number(el.value);
|
| 339 |
+
getSettings(name)[param]=val;
|
| 340 |
+
const output=node.querySelector(`[data-output="${param}"]`);
|
| 341 |
+
if(output)output.textContent=outputValue(param,val);
|
| 342 |
+
setUnrendered();
|
| 343 |
+
});
|
| 344 |
+
byId("arrTracks").addEventListener("click",e=>{
|
| 345 |
+
const a=e.target.closest("[data-action]");if(!a)return;
|
| 346 |
+
const row=a.closest(".arr-track"),name=G.real[Number(row.dataset.index)];
|
| 347 |
+
if(!name)return;
|
| 348 |
+
if(a.dataset.action==="play"){setSource(name,true);return;}
|
| 349 |
+
const s=getSettings(name),kind=a.dataset.action;
|
| 350 |
+
s[kind]=!s[kind];a.classList.toggle("on",s[kind]);a.setAttribute("aria-pressed",String(s[kind]));
|
| 351 |
+
updateStatus();setUnrendered();
|
| 352 |
+
});
|
| 353 |
+
byId("arrRender").addEventListener("click",renderMix);
|
| 354 |
+
byId("arrListenMix").addEventListener("click",listenMix);
|
| 355 |
+
byId("arrZoom").addEventListener("input",e=>{G.zoom=Number(e.target.value);draw();});
|
| 356 |
+
for(const [id,out,suffix] of [["arrTempo","arrTempoOut"," %"],["arrPitch","arrPitchOut"," HT"]]){
|
| 357 |
+
byId(id).addEventListener("input",e=>{
|
| 358 |
+
const v=Number(e.target.value);byId(out).textContent=(id==="arrPitch"&&v>=0?"+":"")+v+suffix;
|
| 359 |
+
setUnrendered();
|
| 360 |
+
});
|
| 361 |
+
}
|
| 362 |
+
byId("arrOverview").addEventListener("click",e=>timelineSeek(e,true));
|
| 363 |
+
byId("arrOverview").addEventListener("keydown",e=>{
|
| 364 |
+
if(e.key==="ArrowLeft"||e.key==="ArrowRight"){e.preventDefault();audio.currentTime=Math.max(0,Math.min(G.length,(audio.currentTime||0)+(e.key==="ArrowRight"?5:-5)));updatePlayhead();}
|
| 365 |
+
});
|
| 366 |
+
byId("arrTracks").addEventListener("click",e=>{
|
| 367 |
+
if(e.target.classList.contains("arr-stemwave"))timelineSeek(e,false);
|
| 368 |
+
});
|
| 369 |
+
byId("arrTracks").addEventListener("keydown",e=>{
|
| 370 |
+
if(e.target.classList.contains("arr-stemwave")&&(e.key==="ArrowLeft"||e.key==="ArrowRight")){
|
| 371 |
+
e.preventDefault();audio.currentTime=Math.max(0,Math.min(G.length,(audio.currentTime||0)+(e.key==="ArrowRight"?1:-1)));updatePlayhead();
|
| 372 |
+
}
|
| 373 |
+
});
|
| 374 |
+
window.addEventListener("resize",()=>{if(state.view==="arrangement")draw();});
|
| 375 |
+
audio.addEventListener("timeupdate",updatePlayhead);
|
| 376 |
+
byId("arrScroll")?.addEventListener("input",e=>{G.scroll=Number(e.target.value)/1000;draw();});
|
| 377 |
+
}
|
| 378 |
+
window.omegaArrangementReset=reset;
|
| 379 |
+
window.omegaArrangementLoad=onProject;
|
| 380 |
+
window.omegaArrangementDraw=()=>requestAnimationFrame(draw);
|
| 381 |
+
listeners();updateStatus();draw();
|
| 382 |
+
})();
|
app/static/index.html
CHANGED
|
@@ -8,7 +8,9 @@
|
|
| 8 |
<title>ABSOLUTION Ω — Dein Audio-Labor</title>
|
| 9 |
<link rel="icon" href="/static/favicon.svg" type="image/svg+xml">
|
| 10 |
<link rel="stylesheet" href="/static/style.css">
|
|
|
|
| 11 |
<script src="/static/app.js" defer></script>
|
|
|
|
| 12 |
</head>
|
| 13 |
<body>
|
| 14 |
<a class="skip-link" href="#main-content">Zum Inhalt springen</a>
|
|
@@ -21,6 +23,9 @@
|
|
| 21 |
<div class="nav-group-label">WORKSPACE</div>
|
| 22 |
<nav class="nav-stack" aria-label="Bereiche">
|
| 23 |
<button class="nav-link active" data-view="studio" aria-current="page"><span class="nav-icon">◈</span> Studio <span class="nav-number">01</span></button>
|
|
|
|
|
|
|
|
|
|
| 24 |
<button class="nav-link" data-view="stems"><span class="nav-icon">≋</span> Meine Stems <span class="nav-count" id="stem-count">0</span></button>
|
| 25 |
<button class="nav-link" data-view="quality"><span class="nav-icon">◇</span> Forensik-Bericht <span class="nav-number">03</span></button>
|
| 26 |
<button class="nav-link" data-view="guide"><span class="nav-icon">ⓘ</span> Hilfe & Technik <span class="nav-number">04</span></button>
|
|
@@ -36,7 +41,7 @@
|
|
| 36 |
<span class="privacy-icon">◉</span>
|
| 37 |
<div><strong>Lokale Verarbeitung</strong><small>Kein Cloud-Upload durch diese App</small></div>
|
| 38 |
</div>
|
| 39 |
-
<div class="sidebar-foot">ABSOLUTION Ω · v0.
|
| 40 |
</aside>
|
| 41 |
|
| 42 |
<div class="content-shell">
|
|
@@ -50,6 +55,89 @@
|
|
| 50 |
</header>
|
| 51 |
|
| 52 |
<main id="main-content" tabindex="-1">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
<section id="view-studio" class="view active" aria-label="Audio-Studio">
|
| 54 |
<div class="hero">
|
| 55 |
<div class="hero-copy">
|
|
@@ -123,6 +211,105 @@
|
|
| 123 |
<div id="stemsPreview" class="stems-preview"><div class="empty-state"><div class="empty-icon">≋</div><h3>Noch keine Stems vorhanden</h3><p>Importiere einen Track und starte die Separation. Deine Ergebnisse erscheinen genau hier.</p></div></div>
|
| 124 |
</section>
|
| 125 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
<section id="view-stems" class="view" aria-label="Export und Stems">
|
| 127 |
<div class="page-heading"><span class="eyebrow">WORKSPACE / STEM LIBRARY</span><h1>Jeder Klang. <em>Einzeln.</em></h1><p>Höre die getrennten Komponenten an und exportiere die unkomprimierten Dateien.</p></div>
|
| 128 |
<div class="section-header section-header-tight"><div><span class="section-numeral">LIBRARY</span><h2>Extrahierte Audiospuren</h2></div><button id="export" class="btn btn-primary" type="button" disabled>Alle Stems als ZIP <span>↓</span></button></div>
|
|
@@ -153,7 +340,7 @@
|
|
| 153 |
</div>
|
| 154 |
<div class="help-split">
|
| 155 |
<section class="panel help-panel"><span class="eyebrow">WAS IST BEREITS MÖGLICH?</span><ul class="feature-list"><li>✓ Audioanalyse und Wellenform</li><li>✓ Harmonic-Percussive-Separation</li><li>✓ Residual- und Rekonstruktionsprüfung</li><li>✓ Originaltreue und SHA-256-Nachweis</li><li>✓ Browser-Player und WAV-Export</li><li>◌ Optionales Demucs mit lokalen Gewichten</li></ul></section>
|
| 156 |
-
<section class="panel help-panel"><span class="eyebrow">NOCH NICHT VERFÜGBAR</span><ul class="feature-list future"><li>— Freie Sprachbefehle für beliebige Klänge</li><li>
|
| 157 |
</div>
|
| 158 |
<div class="guide-actions"><button data-goto="studio" class="btn btn-primary" type="button">Audio-Labor öffnen <span>↗</span></button><a href="/docs" class="btn btn-outline">API-Dokumentation ↗</a></div>
|
| 159 |
</section>
|
|
|
|
| 8 |
<title>ABSOLUTION Ω — Dein Audio-Labor</title>
|
| 9 |
<link rel="icon" href="/static/favicon.svg" type="image/svg+xml">
|
| 10 |
<link rel="stylesheet" href="/static/style.css">
|
| 11 |
+
<link rel="stylesheet" href="/static/arrangement.css">
|
| 12 |
<script src="/static/app.js" defer></script>
|
| 13 |
+
<script src="/static/arrangement.js" defer></script>
|
| 14 |
</head>
|
| 15 |
<body>
|
| 16 |
<a class="skip-link" href="#main-content">Zum Inhalt springen</a>
|
|
|
|
| 23 |
<div class="nav-group-label">WORKSPACE</div>
|
| 24 |
<nav class="nav-stack" aria-label="Bereiche">
|
| 25 |
<button class="nav-link active" data-view="studio" aria-current="page"><span class="nav-icon">◈</span> Studio <span class="nav-number">01</span></button>
|
| 26 |
+
<button class="nav-link" data-view="arrangement"><span class="nav-icon">▥</span> Arrangement <span class="nav-number">NEU</span></button>
|
| 27 |
+
<button class="nav-link" data-view="bass"><span class="nav-icon">♮</span> BASS-CORE <span class="nav-number">02</span></button>
|
| 28 |
+
<button class="nav-link" data-view="noise"><span class="nav-icon">⌁</span> NOISE-CORE <span class="nav-number">03</span></button>
|
| 29 |
<button class="nav-link" data-view="stems"><span class="nav-icon">≋</span> Meine Stems <span class="nav-count" id="stem-count">0</span></button>
|
| 30 |
<button class="nav-link" data-view="quality"><span class="nav-icon">◇</span> Forensik-Bericht <span class="nav-number">03</span></button>
|
| 31 |
<button class="nav-link" data-view="guide"><span class="nav-icon">ⓘ</span> Hilfe & Technik <span class="nav-number">04</span></button>
|
|
|
|
| 41 |
<span class="privacy-icon">◉</span>
|
| 42 |
<div><strong>Lokale Verarbeitung</strong><small>Kein Cloud-Upload durch diese App</small></div>
|
| 43 |
</div>
|
| 44 |
+
<div class="sidebar-foot">ABSOLUTION Ω · v0.6 ARRANGEMENT<br>Forschungsversion · Single User</div>
|
| 45 |
</aside>
|
| 46 |
|
| 47 |
<div class="content-shell">
|
|
|
|
| 55 |
</header>
|
| 56 |
|
| 57 |
<main id="main-content" tabindex="-1">
|
| 58 |
+
<section id="view-arrangement" class="view arr-view" aria-label="Mehrspur-Arrangement Studio">
|
| 59 |
+
<div class="arr-header">
|
| 60 |
+
<div class="arr-title">
|
| 61 |
+
<div class="arr-kicker"><span class="arr-light"></span> ABSOLUTION Ω / MULTITRACK WORKSTATION <span class="arr-beta">v0.6</span></div>
|
| 62 |
+
<h1>Alle Frequenzen. <em>Alle Ebenen.</em></h1>
|
| 63 |
+
<p>KI-Vorinventur → editierbarer Trennplan → echte Stems → präziser Mix. Originaltreue steht über aggressiver Verarbeitung.</p>
|
| 64 |
+
</div>
|
| 65 |
+
<div class="arr-header-actions">
|
| 66 |
+
<button class="arr-btn arr-btn-ghost" id="arrDemo">♫ Demo laden</button>
|
| 67 |
+
<button class="arr-btn arr-btn-primary" id="arrInspect">✧ Mini-KI analysieren</button>
|
| 68 |
+
</div>
|
| 69 |
+
</div>
|
| 70 |
+
|
| 71 |
+
<div class="arr-status" role="status" aria-live="polite"><span id="arrSourceName">Noch keine Datei — importiere im Studio oder lade die Demo.</span><span id="arrStemStatus">0 echte Stems</span></div>
|
| 72 |
+
|
| 73 |
+
<div class="arr-workflow">
|
| 74 |
+
<div class="arr-step"><span>01</span><strong>KI-VORINVENTUR</strong><small>Hypothesen, keine Stems</small></div>
|
| 75 |
+
<div class="arr-workflow-arrow">→</div>
|
| 76 |
+
<div class="arr-step"><span>02</span><strong>TRENNPLAN</strong><small>frei editierbar</small></div>
|
| 77 |
+
<div class="arr-workflow-arrow">→</div>
|
| 78 |
+
<div class="arr-step"><span>03</span><strong>QUELLENSEPARATION</strong><small>HPSS oder lokale Demucs</small></div>
|
| 79 |
+
<div class="arr-workflow-arrow">→</div>
|
| 80 |
+
<div class="arr-step"><span>04</span><strong>ARRANGEMENT</strong><small>bearbeiten & exportieren</small></div>
|
| 81 |
+
</div>
|
| 82 |
+
|
| 83 |
+
<section class="arr-planning arr-card">
|
| 84 |
+
<div class="arr-card-head"><div><span class="arr-micro">KI-ANALYSE / ELEMENTAR-PLANER</span><h2>Was steckt in deinem Track?</h2></div>
|
| 85 |
+
<span class="arr-kind">OMEGA-TAG MINI · LOKAL</span></div>
|
| 86 |
+
<p class="arr-desc">Das kleine neuronale Modell wurde auf synthetischen Überlagerungen feinjustiert. Es erkennt nur grobe Klangtexturen als <strong>unsichere Hypothesen</strong> — keine zuverlässigen Instrumentnamen. Markiere, benenne und ergänze die gewünschten Trennziele.</p>
|
| 87 |
+
<div class="arr-plan-content" id="arrPlanContent"><div class="arr-empty-inline">Noch keine Vorinventur. Klicke auf „Mini-KI analysieren“.</div></div>
|
| 88 |
+
<div class="arr-plan-foot">
|
| 89 |
+
<div><button class="arr-btn arr-btn-ghost" id="arrAddPlan">+ Trennziel hinzufügen</button><button class="arr-btn arr-btn-ghost" id="arrSavePlan">Plan speichern</button></div>
|
| 90 |
+
<div class="arr-separate-group"><span>Reale Stems erzeugen mit</span><select id="arrModel"><option value="hpss">HPSS / DSP · 3 Signalanteile</option><option value="demucs">Demucs · 4 Instrument-Gruppen (nur mit Gewichten)</option></select><button class="arr-btn arr-btn-primary" id="arrSeparate">Separation starten ↗</button></div>
|
| 91 |
+
</div>
|
| 92 |
+
<div class="arr-help-text" id="arrPlanHint">Der Trennplan kann mehr Ziele enthalten als das gewählte Modell separat erzeugen kann. Nicht verfügbare Instrumente bleiben Planungseinträge, keine Audiodateien.</div>
|
| 93 |
+
</section>
|
| 94 |
+
|
| 95 |
+
<section class="arr-console arr-card">
|
| 96 |
+
<div class="arr-console-top">
|
| 97 |
+
<div class="arr-console-heading"><span class="arr-micro">MULTI-STEM WORKSPACE / MIXER</span><h2>Arrangement & Frequenzspuren</h2></div>
|
| 98 |
+
<div class="arr-toolbar">
|
| 99 |
+
<label class="arr-compact">ZOOM <input id="arrZoom" type="range" min="1" max="4" step="0.5" value="1" aria-label="Timeline-Zoom"></label>
|
| 100 |
+
<button class="arr-btn arr-btn-ghost" id="arrResetMix">↺ Regler zurücksetzen</button>
|
| 101 |
+
<button class="arr-btn arr-btn-primary" id="arrRender">◉ Mix berechnen</button>
|
| 102 |
+
</div>
|
| 103 |
+
</div>
|
| 104 |
+
|
| 105 |
+
<div class="arr-overview-box">
|
| 106 |
+
<div class="arr-overview-title"><span>MASTER OVERVIEW</span><span id="arrOverviewInfo">ALLE ELEMENTE / FARBEN</span></div>
|
| 107 |
+
<div class="arr-overview-canvas">
|
| 108 |
+
<canvas id="arrOverview" height="136" aria-label="Farbig überlagerte, tatsächlich separierte Signalwellen" role="img" tabindex="0"></canvas>
|
| 109 |
+
<div id="arrPlayhead" class="arr-playhead" aria-hidden="true"></div>
|
| 110 |
+
<span id="arrOverviewEmpty" class="arr-overview-empty">Nach der Separation erscheinen hier alle Spuren in ihren eigenen Farben.</span>
|
| 111 |
+
</div>
|
| 112 |
+
<div class="arr-ruler" id="arrRuler"><span>0:00</span><span>—</span><span>—</span><span>—</span><span>—</span></div>
|
| 113 |
+
<label class="arr-scroll-label">TIMELINE SCHIEBEN <input id="arrScroll" type="range" min="0" max="1000" value="0" aria-label="Timeline horizontal verschieben"></label>
|
| 114 |
+
</div>
|
| 115 |
+
<div class="arr-mix-meta">
|
| 116 |
+
<div class="arr-selection"><strong id="arrActiveTracks">0 Spuren</strong><span class="arr-sep">/</span><span id="arrSoloList">Keine Solo-Spur aktiv</span></div>
|
| 117 |
+
<div class="arr-mix-warning">ⓘ Keine automatische Klangänderung · Original bleibt sicher</div>
|
| 118 |
+
</div>
|
| 119 |
+
<div class="arr-tracks-wrap">
|
| 120 |
+
<div class="arr-track-labels">
|
| 121 |
+
<div>SPUR · LEVEL · MUTE / SOLO</div><div>STEREOFELD / PAN</div><div>FREQUENZ-WAVEFORM / ZEIT</div><div>EFFEKTE / MODULE</div>
|
| 122 |
+
</div>
|
| 123 |
+
<div id="arrTracks"><div class="arr-empty-track">Hier erscheinen deine tatsächlich separierten Stems. Die Anzahl richtet sich nach dem Separationsmodell und den vorhandenen Quellen.</div></div>
|
| 124 |
+
</div>
|
| 125 |
+
<div class="arr-mixer-footer">
|
| 126 |
+
<div class="arr-transform">
|
| 127 |
+
<label>TEMPO <span id="arrTempoOut">100 %</span><input type="range" id="arrTempo" min="50" max="200" value="100" step="5"></label>
|
| 128 |
+
<label>TONHÖHE / TRANSPOSE <span id="arrPitchOut">±0 HT</span><input type="range" id="arrPitch" min="-12" max="12" step="1" value="0"></label>
|
| 129 |
+
<small id="arrRubberbandNote">Unabhängiges Tempo/Transponieren benötigt FFmpeg mit Rubber Band. Die Tonart wird nicht automatisch erkannt.</small>
|
| 130 |
+
</div>
|
| 131 |
+
<div class="arr-footer-actions">
|
| 132 |
+
<span id="arrRenderReport" class="arr-render-report">Noch kein Mix berechnet</span>
|
| 133 |
+
<button class="arr-btn arr-btn-ghost" id="arrListenMix" disabled>▶ Mix anhören</button>
|
| 134 |
+
<a class="arr-btn arr-btn-primary arr-download disabled" id="arrDownload" aria-disabled="true">↓ WAV exportieren</a>
|
| 135 |
+
</div>
|
| 136 |
+
</div>
|
| 137 |
+
</section>
|
| 138 |
+
<p class="arr-disclaimer">Präzisionshinweis: Farbige Wellenformen sind Visualisierungen realer, geschätzter Stems; die Mini-KI liefert nur Textur-Hypothesen. Der Offline-Mix kann mit Filtern, Sättigung, Pan und Transposition hörbar vom Original abweichen und wird deshalb separat gerendert.</p>
|
| 139 |
+
</section>
|
| 140 |
+
|
| 141 |
<section id="view-studio" class="view active" aria-label="Audio-Studio">
|
| 142 |
<div class="hero">
|
| 143 |
<div class="hero-copy">
|
|
|
|
| 211 |
<div id="stemsPreview" class="stems-preview"><div class="empty-state"><div class="empty-icon">≋</div><h3>Noch keine Stems vorhanden</h3><p>Importiere einen Track und starte die Separation. Deine Ergebnisse erscheinen genau hier.</p></div></div>
|
| 212 |
</section>
|
| 213 |
|
| 214 |
+
<section id="view-bass" class="view" aria-label="BASS-CORE Bass-Labor">
|
| 215 |
+
<div class="page-heading">
|
| 216 |
+
<span class="eyebrow">ABSOLUTION Ω / BASS-CORE · v0.3</span>
|
| 217 |
+
<h1>Tiefen verstehen. <em>Bass formen.</em></h1>
|
| 218 |
+
<p>Kick-Impulse, Bassline, Subfrequenzen und synthetische Obertöne kontrolliert bearbeiten. Vollständig lokal, ohne Veränderung des Originals.</p>
|
| 219 |
+
</div>
|
| 220 |
+
<div class="bass-truth"><strong>Was dieser Modus tatsächlich macht</strong><p>DSP schätzt Kick- und Bassanteile aus tiefen Frequenzen – keine perfekte Instrumententrennung. Liegen HPSS-Stems oder separat erzeugte Demucs-Bass/Drum-Stems vor, verwendet „Automatisch“ diese als bessere Ausgangsschätzung. Zugesetzte Obertöne sind synthetisiert und werden nicht als zurückgewonnene Originalinformationen ausgegeben.</p></div>
|
| 221 |
+
<section class="panel bass-workspace">
|
| 222 |
+
<div class="panel-head"><div><span class="eyebrow">01 / AUDIO SOURCE ROUTING</span><h2>Analysiere die Tiefen</h2></div><span id="bassReady" class="panel-pill">DATEI IMPORTIEREN</span></div>
|
| 223 |
+
<div class="bass-mode-row">
|
| 224 |
+
<label for="bassMode">Quellenbasis</label>
|
| 225 |
+
<select id="bassMode" class="bass-select">
|
| 226 |
+
<option value="auto">Automatisch · Beste vorhandene Stems</option>
|
| 227 |
+
<option value="dsp">DSP · Tiefband und Transienten</option>
|
| 228 |
+
<option value="hpss">HPSS · Harmonisch / Perkussiv (vorher trennen)</option>
|
| 229 |
+
<option value="demucs">Demucs · Bass / Drums (vorher trennen)</option>
|
| 230 |
+
</select>
|
| 231 |
+
</div>
|
| 232 |
+
<div class="bass-presets" role="group" aria-label="Bass-Presets">
|
| 233 |
+
<button type="button" class="bass-preset active" data-bass-preset="transparent">Originaltreu</button>
|
| 234 |
+
<button type="button" class="bass-preset" data-bass-preset="club">Club / Punch</button>
|
| 235 |
+
<button type="button" class="bass-preset" data-bass-preset="warm">Warm & rund</button>
|
| 236 |
+
<button type="button" class="bass-preset" data-bass-preset="translate">Kleine Lautsprecher</button>
|
| 237 |
+
</div>
|
| 238 |
+
<div class="bass-controls">
|
| 239 |
+
<label class="bass-control"><span>Low-Band-Grenze <small>Cutoff / Frequenzbereich</small></span><output id="bassCrossoverValue">220 Hz</output><input type="range" id="bassCrossover" min="45" max="350" value="220" step="5"></label>
|
| 240 |
+
<label class="bass-control"><span>Kick-Erkennung <small>Transienten-Gewichtung nur in DSP</small></span><output id="bassFocusValue">75 %</output><input type="range" id="bassFocus" min="0" max="100" value="75" step="5"></label>
|
| 241 |
+
<label class="bass-control"><span>Kick-Punch <small>Geschätzte Kick-Lautstärke</small></span><output id="bassKickValue">+0.0 dB</output><input type="range" id="bassKick" min="-12" max="12" value="0" step=".5"></label>
|
| 242 |
+
<label class="bass-control"><span>Bassline-Körper <small>Geschätzter Bassline-Anteil</small></span><output id="bassLineValue">+0.0 dB</output><input type="range" id="bassLine" min="-12" max="12" value="0" step=".5"></label>
|
| 243 |
+
<label class="bass-control"><span>Subfrequenzen <small>Bassline unter ca. 65 Hz</small></span><output id="bassSubValue">+0.0 dB</output><input type="range" id="bassSub" min="-12" max="12" value="0" step=".5"></label>
|
| 244 |
+
<label class="bass-control"><span>Obertöne hinzufügen <small>Synthetische Sättigung, kein Repair</small></span><output id="bassHarmValue">20 %</output><input type="range" id="bassHarm" min="0" max="100" value="20" step="5"></label>
|
| 245 |
+
<label class="bass-control"><span>Rumpeln entfernen <small>Hochpass im bearbeiteten Bass</small></span><output id="bassLowcutValue">22 Hz</output><input type="range" id="bassLowcut" min="10" max="45" value="22" step="1"></label>
|
| 246 |
+
<label class="bass-control"><span>Mono-Bass bis <small>Nur im veränderten Bassband</small></span><output id="bassMonoValue">100 Hz</output><input type="range" id="bassMono" min="0" max="180" value="100" step="10"></label>
|
| 247 |
+
<label class="bass-control"><span>Dry / Wet <small>Nur die Bassbearbeitung mischen</small></span><output id="bassWetValue">100 %</output><input type="range" id="bassWet" min="0" max="100" value="100" step="5"></label>
|
| 248 |
+
<label class="bass-control"><span>Peak-Ceiling <small>Globale Verstärkung des Mix-Exports</small></span><output id="bassCeilingValue">−1.0 dBFS</output><input type="range" id="bassCeiling" min="-6" max="-.1" value="-1" step=".1"></label>
|
| 249 |
+
</div>
|
| 250 |
+
<div class="bass-action-row">
|
| 251 |
+
<button id="bassRun" class="btn btn-primary" type="button" disabled>Bass analysieren & optimieren ↗</button>
|
| 252 |
+
<button id="bassExport" class="btn btn-outline" type="button" disabled>↓ Alle Bass-Tracks herunterladen</button>
|
| 253 |
+
</div>
|
| 254 |
+
<div class="job-progress" id="bassProgress" hidden role="status" aria-live="polite"><div class="job-track"><div id="bassProgressFill"></div></div><div class="job-label"><span id="bassJobLabel">Vorbereitung …</span><span id="bassProgressNum">0 %</span></div></div>
|
| 255 |
+
</section>
|
| 256 |
+
<div class="section-header section-header-tight"><div><span class="section-numeral">02 — RESULTS / BEFORE AFTER</span><h2>Deine Tiefen, einzeln hörbar</h2></div></div>
|
| 257 |
+
<div class="bass-stats" id="bassStats"><div><span>QUELLENMODUS</span><strong id="bassSourceUsed">—</strong></div><div><span>OPTIMIERTER MIX-PEAK</span><strong id="bassMixPeak">—</strong></div><div><span>CEILING-ABSENKUNG</span><strong id="bassPeakGain">—</strong></div><div><span>REKONSTRUKTION</span><strong id="bassRecon">—</strong></div></div>
|
| 258 |
+
<div id="bassResults" class="bass-result-grid"><div class="empty-state"><h3>Noch keine Bass-Bearbeitung</h3><p>Importiere Audio im Studio und starte hier das BASS-CORE Processing.</p></div></div>
|
| 259 |
+
<div class="panel bass-spectrum"><div class="panel-head"><div><span class="eyebrow">03 / FREQUENCY INSPECTOR</span><h2>Frequenzenergie vor / nach Bearbeitung</h2></div></div><div id="bassFrequency" class="bass-frequency-empty">Nach dem Processing werden hier gemessene Frequenzbänder von 20 bis 1280 Hz angezeigt.</div><p class="bass-note">RMS-Bandschätzungen des ersten Processing-Blocks, keine Einzelnoten oder instrumentengenaue Quellenidentifikation. Vergleiche immer mit pegelangepasster Hörprobe.</p></div>
|
| 260 |
+
<div class="panel noise-panel" style="margin-top:24px">
|
| 261 |
+
<div class="panel-head"><div><span class="eyebrow">04 / OPTIONAL LFE SYNTHESIS</span><h2>Virtual Bass — wie bei Kdenlive</h2></div><span id="virtualReady" class="panel-pill">FFMPEG / OPTIONAL</span></div>
|
| 262 |
+
<p class="bass-note">Der FFmpeg-Filter <code>virtualbass</code> erzeugt einen zusätzlichen künstlichen LFE-Kanal (Stereo → 2.1). Die ursprünglichen Links-/Rechts-Kanäle werden im Filter nicht verändert. Keine Original-Bass-Restauration und nicht für normale Stereo-Player gedacht.</p>
|
| 263 |
+
<div class="noise-tools">
|
| 264 |
+
<label for="virtualCutoff">LFE Cutoff <strong id="virtualCutoffValue">250 Hz</strong></label>
|
| 265 |
+
<input id="virtualCutoff" type="range" min="100" max="500" step="10" value="250">
|
| 266 |
+
<label for="virtualStrength">Virtual Bass Stärke <strong id="virtualStrengthValue">1.0</strong></label>
|
| 267 |
+
<input id="virtualStrength" type="range" min=".5" max="3" step=".1" value="1">
|
| 268 |
+
<button id="virtualRun" class="btn btn-outline" type="button" disabled>2.1 Virtual Bass erzeugen</button>
|
| 269 |
+
<a id="virtualDownload" class="btn btn-primary" href="#" hidden>↓ LFE 2.1 WAV herunterladen</a>
|
| 270 |
+
<p class="bass-note" id="virtualSummary">Benötigt eine Stereo-Datei und lokal installiertes FFmpeg mit virtualbass-Filter.</p>
|
| 271 |
+
</div>
|
| 272 |
+
</div>
|
| 273 |
+
</section>
|
| 274 |
+
|
| 275 |
+
|
| 276 |
+
<section id="view-noise" class="view" aria-label="NOISE-CORE Störgeräuschinspektor">
|
| 277 |
+
<div class="page-heading">
|
| 278 |
+
<span class="eyebrow">WORKSPACE / NOISE-CORE Ω v0.4</span>
|
| 279 |
+
<h1>Musik bewahren. <em>Störquellen prüfen.</em></h1>
|
| 280 |
+
<p>Jeder Ton zählt. Wir markieren isolierte Klick-Verdachtsfälle, aber entfernen standardmäßig nichts. Nur von dir einzeln bestätigte Stellen werden vorsichtig interpoliert.</p>
|
| 281 |
+
</div>
|
| 282 |
+
<div class="noise-law">
|
| 283 |
+
<strong>◉ PRESERVE FIRST — DAS KLANGSCHUTZ-GESETZ</strong>
|
| 284 |
+
<p>Kein automatisches De-Noise oder Notch-Filtering. Kein pauschales Löschen von Rauschen, „Luft“, Hall oder Musiktransienten. Bearbeitungen benötigen deine Freigabe; die Differenzspur zeigt, was tatsächlich verändert wurde.</p>
|
| 285 |
+
</div>
|
| 286 |
+
<div class="panel noise-panel">
|
| 287 |
+
<div class="panel-head"><div><span class="eyebrow">01 / NON-DESTRUCTIVE SCAN</span><h2>Störgeräusche untersuchen</h2></div><span id="noiseReady" class="panel-pill">DATEI IMPORTIEREN</span></div>
|
| 288 |
+
<p class="bass-note">Einzelne Sample-Ausreißer werden als <strong>Hypothesen</strong> markiert. Musik mit scharfen Transienten kann dieselben Muster erzeugen. Es findet zunächst keine Signalveränderung statt.</p>
|
| 289 |
+
<div class="noise-actions"><button id="noiseScan" class="btn btn-primary" type="button" disabled>♫ Störspur analysieren →</button><span id="noiseScanMeta">Noch kein Scan</span></div>
|
| 290 |
+
<div class="job-progress" id="noiseProgress" hidden>
|
| 291 |
+
<div class="progress-top"><strong id="noiseJobLabel">Analyse …</strong><span id="noiseProgressNum">0 %</span></div>
|
| 292 |
+
<div class="progress-track"><div id="noiseProgressFill"></div></div>
|
| 293 |
+
</div>
|
| 294 |
+
</div>
|
| 295 |
+
<div class="panel noise-panel">
|
| 296 |
+
<div class="panel-head"><div><span class="eyebrow">02 / REVIEW REQUIRED</span><h2>Klick-Verdachtsfälle freigeben</h2></div><span id="noiseCount" class="panel-pill">0 Kandidaten</span></div>
|
| 297 |
+
<p class="bass-note">Prüfe jede Markierung im Original. Eine Markierung ist kein Nachweis für ein Störgeräusch. Niemals blind alle auswählen.</p>
|
| 298 |
+
<div id="noiseCandidates" class="noise-candidates"><div class="empty-state"><h3>Noch keine Kandidaten</h3><p>Starte zuerst den Scan.</p></div></div>
|
| 299 |
+
<div class="noise-tools">
|
| 300 |
+
<label for="noiseStrength">Reparaturstärke <strong id="noiseStrengthValue">80 %</strong></label>
|
| 301 |
+
<input id="noiseStrength" type="range" min="0" max="100" step="5" value="80">
|
| 302 |
+
<span class="bass-note">Nur ausdrücklich markierte Einzel-Samples werden verändert. 0 % = keine Änderung, 100 % = lineare Nachbarinterpolation.</span>
|
| 303 |
+
<button id="noiseRepair" class="btn btn-primary" type="button" disabled>Ausgewählte Stellen reparieren →</button>
|
| 304 |
+
</div>
|
| 305 |
+
</div>
|
| 306 |
+
<div class="panel noise-panel">
|
| 307 |
+
<div class="panel-head"><div><span class="eyebrow">03 / DIFFERENCE MONITOR</span><h2>Original · Reparatur · Differenzspur</h2></div><button id="noiseExport" class="btn btn-outline" type="button" disabled>WAVs + Bericht als ZIP ↓</button></div>
|
| 308 |
+
<div id="noiseTracks" class="noise-track-grid"><div class="empty-state"><h3>Noch keine Bearbeitung</h3><p>Die Originaldatei bleibt jederzeit erhalten. Nach einer Reparatur kannst du das Ergebnis und die Differenzspur anhören.</p></div></div>
|
| 309 |
+
<div id="noiseDiagnostics" class="noise-diagnostics"></div>
|
| 310 |
+
</div>
|
| 311 |
+
</section>
|
| 312 |
+
|
| 313 |
<section id="view-stems" class="view" aria-label="Export und Stems">
|
| 314 |
<div class="page-heading"><span class="eyebrow">WORKSPACE / STEM LIBRARY</span><h1>Jeder Klang. <em>Einzeln.</em></h1><p>Höre die getrennten Komponenten an und exportiere die unkomprimierten Dateien.</p></div>
|
| 315 |
<div class="section-header section-header-tight"><div><span class="section-numeral">LIBRARY</span><h2>Extrahierte Audiospuren</h2></div><button id="export" class="btn btn-primary" type="button" disabled>Alle Stems als ZIP <span>↓</span></button></div>
|
|
|
|
| 340 |
</div>
|
| 341 |
<div class="help-split">
|
| 342 |
<section class="panel help-panel"><span class="eyebrow">WAS IST BEREITS MÖGLICH?</span><ul class="feature-list"><li>✓ Audioanalyse und Wellenform</li><li>✓ Harmonic-Percussive-Separation</li><li>✓ Residual- und Rekonstruktionsprüfung</li><li>✓ Originaltreue und SHA-256-Nachweis</li><li>✓ Browser-Player und WAV-Export</li><li>◌ Optionales Demucs mit lokalen Gewichten</li></ul></section>
|
| 343 |
+
<section class="panel help-panel"><span class="eyebrow">NOCH NICHT VERFÜGBAR</span><ul class="feature-list future"><li>— Freie Sprachbefehle für beliebige Klänge</li><li>✓ NOISE-CORE: manuelle Einzelklick-Reparatur · breitbandige Entrauschung noch nicht verfügbar</li><li>— Echte Sprecher- und Instrumentenerkennung mit HPSS</li><li>— Cloud-GPU oder öffentliche Mehrnutzer-Website</li><li>— Native Desktop-App</li></ul><p class="help-note">Aus Sicherheitsgründen ausschließlich lokal oder in einer geschützten Umgebung verwenden. Die Anwendung besitzt noch keine Anmeldung.</p></section>
|
| 344 |
</div>
|
| 345 |
<div class="guide-actions"><button data-goto="studio" class="btn btn-primary" type="button">Audio-Labor öffnen <span>↗</span></button><a href="/docs" class="btn btn-outline">API-Dokumentation ↗</a></div>
|
| 346 |
</section>
|
app/static/style.css
CHANGED
|
@@ -28,3 +28,59 @@ main{width:min(1440px,100%);margin:0 auto;flex:1;padding:38px 44px 20px}.view{di
|
|
| 28 |
@media(max-width:750px){.sidebar{transform:translateX(-100%);transition:transform .2s;width:260px;flex-basis:260px;box-shadow:0 0 40px #02071190}.sidebar.open{transform:translateX(0)}.content-shell{margin-left:0}.transport{left:0;height:76px;padding:0 13px}.topbar{height:60px;padding:0 18px}.menu-toggle{display:block;font-size:23px;padding:0 8px 0 0}.top-right{gap:8px}.top-help{display:none}.crumb{font-size:9px}main{padding:20px 16px}.hero{min-height:auto;padding:25px 22px;margin-bottom:27px}.hero h1{font-size:clamp(28px,7vw,42px)}.hero-tags{gap:10px;font-size:9px}.upload-surface{flex-wrap:wrap;padding:18px;gap:13px}.upload-icon{height:49px;width:49px;font-size:30px}.upload-copy{flex-basis:calc(100% - 75px)}.upload-browse{width:100%}.import-footer{flex-wrap:wrap}.import-optional{display:none}.stems-preview,.stems-full,.report-grid,.guide-grid,.help-split{grid-template-columns:1fr}.page-footer{padding:14px 16px 22px;flex-wrap:wrap}.transport-track{width:140px}.transport-volume{display:none}.report-banner{padding:19px}.report-mark{height:45px;width:45px;font-size:25px}.provenance-panel dl>div{grid-template-columns:1fr;gap:5px}.mobile-scrim{position:fixed;inset:0;background:#0009;z-index:18}.quickresults-heading{align-items:start}.quickresults-heading .btn{padding:10px;font-size:10px}.waveform-frame{height:160px}}
|
| 29 |
@media(max-width:450px){.api-indicator span{display:none}.hero h1{font-size:30px}.hero-tags{gap:10px}.transport-track{max-width:100px}.track-thumb{display:none}.transport{gap:8px}.transport-timeline{gap:6px}.transport-timeline span{font-size:8px}.transport-main{min-width:0}.transport-controls{gap:7px}.audio-stats strong{font-size:13px}.section-header h2,.quickresults-heading h2{font-size:18px}.quickresults-heading .btn{font-size:0;gap:0}.quickresults-heading .btn span{font-size:18px}.wave-panel,.engine-panel{padding:15px}}
|
| 30 |
@media(prefers-reduced-motion:reduce){*,*:before,*:after{scroll-behavior:auto!important;transition:none!important;animation:none!important}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
@media(max-width:750px){.sidebar{transform:translateX(-100%);transition:transform .2s;width:260px;flex-basis:260px;box-shadow:0 0 40px #02071190}.sidebar.open{transform:translateX(0)}.content-shell{margin-left:0}.transport{left:0;height:76px;padding:0 13px}.topbar{height:60px;padding:0 18px}.menu-toggle{display:block;font-size:23px;padding:0 8px 0 0}.top-right{gap:8px}.top-help{display:none}.crumb{font-size:9px}main{padding:20px 16px}.hero{min-height:auto;padding:25px 22px;margin-bottom:27px}.hero h1{font-size:clamp(28px,7vw,42px)}.hero-tags{gap:10px;font-size:9px}.upload-surface{flex-wrap:wrap;padding:18px;gap:13px}.upload-icon{height:49px;width:49px;font-size:30px}.upload-copy{flex-basis:calc(100% - 75px)}.upload-browse{width:100%}.import-footer{flex-wrap:wrap}.import-optional{display:none}.stems-preview,.stems-full,.report-grid,.guide-grid,.help-split{grid-template-columns:1fr}.page-footer{padding:14px 16px 22px;flex-wrap:wrap}.transport-track{width:140px}.transport-volume{display:none}.report-banner{padding:19px}.report-mark{height:45px;width:45px;font-size:25px}.provenance-panel dl>div{grid-template-columns:1fr;gap:5px}.mobile-scrim{position:fixed;inset:0;background:#0009;z-index:18}.quickresults-heading{align-items:start}.quickresults-heading .btn{padding:10px;font-size:10px}.waveform-frame{height:160px}}
|
| 29 |
@media(max-width:450px){.api-indicator span{display:none}.hero h1{font-size:30px}.hero-tags{gap:10px}.transport-track{max-width:100px}.track-thumb{display:none}.transport{gap:8px}.transport-timeline{gap:6px}.transport-timeline span{font-size:8px}.transport-main{min-width:0}.transport-controls{gap:7px}.audio-stats strong{font-size:13px}.section-header h2,.quickresults-heading h2{font-size:18px}.quickresults-heading .btn{font-size:0;gap:0}.quickresults-heading .btn span{font-size:18px}.wave-panel,.engine-panel{padding:15px}}
|
| 30 |
@media(prefers-reduced-motion:reduce){*,*:before,*:after{scroll-behavior:auto!important;transition:none!important;animation:none!important}}
|
| 31 |
+
|
| 32 |
+
/* BASS-CORE Ω v0.3 -- integrated controls */
|
| 33 |
+
.bass-truth{border:1px solid rgba(114,234,214,.27);border-left:3px solid #7ce8cb;background:rgba(23,73,73,.28);border-radius:12px;padding:19px 23px;margin:18px 0 25px}
|
| 34 |
+
.bass-truth strong{color:#a4f7dc;font-size:.95rem}.bass-truth p{line-height:1.7;color:#aebec8;margin:8px 0 0;font-size:.9rem}
|
| 35 |
+
.bass-workspace{padding:24px}.bass-mode-row{display:flex;align-items:center;justify-content:space-between;gap:14px;margin:24px 0 18px;flex-wrap:wrap}
|
| 36 |
+
.bass-mode-row label{font-weight:650}.bass-select{max-width:100%;background:#141f2b;border:1px solid #38515e;color:#effaf8;border-radius:10px;padding:13px;font:inherit;min-width:min(100%,340px)}
|
| 37 |
+
.bass-presets{display:flex;flex-wrap:wrap;gap:9px;margin:18px 0 24px}
|
| 38 |
+
.bass-preset{padding:11px 13px;color:#b8c9d1;background:#192733;border:1px solid #3a5260;border-radius:9px;font:inherit;cursor:pointer}
|
| 39 |
+
.bass-preset.active,.bass-preset:hover{border-color:#72dbc7;background:#153c39;color:#a9ffe4}
|
| 40 |
+
.bass-controls{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:14px}
|
| 41 |
+
.bass-control{display:grid;grid-template-columns:1fr auto;gap:8px 12px;padding:17px;background:#121e29;border:1px solid #304552;border-radius:12px}
|
| 42 |
+
.bass-control span{font-size:.93rem;font-weight:680}.bass-control small{display:block;color:#8fa8b6;font-weight:400;margin-top:4px;font-size:.77rem}
|
| 43 |
+
.bass-control output{font-size:.88rem;color:#9cf8d8;font-weight:700;white-space:nowrap}.bass-control input{grid-column:1 / -1;width:100%;accent-color:#7cf0c4;cursor:pointer}
|
| 44 |
+
.bass-action-row{display:flex;flex-wrap:wrap;gap:12px;margin-top:24px}.bass-action-row .btn{min-height:45px}
|
| 45 |
+
.bass-stats{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:11px;margin:15px 0 24px}
|
| 46 |
+
.bass-stats>div{border-radius:12px;background:#16232e;border:1px solid #304552;padding:19px 14px;min-width:0}
|
| 47 |
+
.bass-stats span{display:block;color:#87a2b0;font-size:.7rem;letter-spacing:.07em}.bass-stats strong{display:block;margin-top:10px;color:#b8ffe8;font-size:1.2rem;overflow-wrap:anywhere}
|
| 48 |
+
.bass-result-grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:12px}
|
| 49 |
+
.bass-result{background:#16232e;border:1px solid #344c56;padding:19px;border-radius:12px;min-width:0}
|
| 50 |
+
.bass-result h3{font-size:1.01rem;margin:0 0 7px}.bass-result p{font-size:.79rem;color:#9cb4c1;margin:0 0 15px;line-height:1.5}
|
| 51 |
+
.bass-result .stem-actions{display:flex;gap:10px;flex-wrap:wrap}.bass-result .stem-actions button,.bass-result .stem-actions a{border:1px solid #43616c;background:#223641;border-radius:7px;padding:10px 12px;color:#d7f8ed;cursor:pointer;font:inherit;font-size:.85rem;text-decoration:none}
|
| 52 |
+
.bass-result .stem-actions button:hover,.bass-result .stem-actions a:hover{background:#31534f}
|
| 53 |
+
.bass-spectrum{padding:20px;margin-top:20px}.bass-frequency-empty{color:#8ca9b7;padding:25px}
|
| 54 |
+
.bass-freq-item{display:grid;grid-template-columns:100px 1fr 65px;align-items:center;gap:12px;margin:12px 0;font-size:.85rem}
|
| 55 |
+
.bass-freq-rail{height:10px;display:flex;align-items:center;position:relative;border-radius:12px;background:#2b4250;overflow:hidden}
|
| 56 |
+
.bass-freq-rail .bass-before{height:100%;background:#587a91;position:absolute;left:0}
|
| 57 |
+
.bass-freq-rail .bass-after{height:4px;background:#89f6ce;position:absolute;left:0;top:3px}
|
| 58 |
+
.bass-freq-key{font-size:.78rem;color:#acbbc6;text-align:right}
|
| 59 |
+
.bass-note{font-size:.8rem;color:#8fa7b4;line-height:1.6}
|
| 60 |
+
@media(max-width:950px){.bass-stats{grid-template-columns:repeat(2,minmax(0,1fr))}.bass-result-grid{grid-template-columns:1fr}}
|
| 61 |
+
@media(max-width:720px){.bass-controls{grid-template-columns:1fr}.bass-workspace{padding:16px}.bass-stats strong{font-size:1rem}.bass-mode-row{display:grid}.bass-select{min-width:0;width:100%}}
|
| 62 |
+
|
| 63 |
+
/* NOISE-CORE Ω */
|
| 64 |
+
.noise-law{border:1px solid #4a615d;border-left:4px solid #94edc9;border-radius:13px;padding:23px 25px;margin-bottom:24px;background:linear-gradient(100deg,#162b2c,#161e2d)}
|
| 65 |
+
.noise-law strong{display:block;color:#aaf7dd;font-size:13px;letter-spacing:.55px}
|
| 66 |
+
.noise-law p{margin:10px 0 0;color:#b8c9d0;font-size:13px;line-height:1.75;max-width:900px}
|
| 67 |
+
.noise-panel{padding:25px;margin-bottom:21px}
|
| 68 |
+
.noise-actions,.noise-tools{display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-top:15px}
|
| 69 |
+
.noise-actions>span{color:#92a5b7;font-size:12px}
|
| 70 |
+
.noise-candidates{display:grid;gap:8px;max-height:420px;overflow:auto}
|
| 71 |
+
.noise-candidate{display:flex;align-items:center;gap:14px;background:#121c2b;border:1px solid #2b3748;border-radius:10px;padding:12px 14px}
|
| 72 |
+
.noise-candidate:has(input:checked){border-color:#74cbaf;background:#1a3436}
|
| 73 |
+
.noise-candidate input{accent-color:#96edcd;width:18px;height:18px}
|
| 74 |
+
.noise-candidate>label{flex:1;line-height:1.5;cursor:pointer}
|
| 75 |
+
.noise-candidate small{display:block;color:#91a3b6;font-size:11px}
|
| 76 |
+
.noise-candidate button{background:#202d3d;border:1px solid #40596e;border-radius:8px;color:#c7f2e9;padding:8px 12px}
|
| 77 |
+
.noise-tools{display:grid;gap:12px;grid-template-columns:1fr;justify-items:start;border-top:1px solid #263648;padding-top:22px;margin-top:24px}
|
| 78 |
+
.noise-tools input{width:min(460px,100%);accent-color:#94edc9}
|
| 79 |
+
.noise-track-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(210px,1fr));gap:12px}
|
| 80 |
+
.noise-track{background:#141f30;border:1px solid #2e4050;border-radius:13px;padding:18px}
|
| 81 |
+
.noise-track h3{font-size:15px}.noise-track p{font-size:12px;color:#98aabc;line-height:1.6}
|
| 82 |
+
.noise-track .stem-actions{margin-top:14px;display:flex;gap:10px;flex-wrap:wrap}
|
| 83 |
+
.noise-track a,.noise-track button{display:inline-block;background:#1c3037;border:1px solid #437868;border-radius:8px;padding:9px 11px;color:#cdf9e9;font-size:12px;cursor:pointer}
|
| 84 |
+
.noise-diagnostics{margin-top:20px;display:grid;gap:10px}
|
| 85 |
+
.noise-diagnostics .noise-line{font-size:12px;color:#b1c6ce;border:1px solid #2b3e4a;background:#172330;padding:11px;border-radius:8px}
|
| 86 |
+
@media (max-width:650px){.noise-panel{padding:16px}.noise-candidate{gap:8px;padding:9px}.noise-candidate button{font-size:11px;padding:8px}}
|
app/virtualbass.py
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Kdenlive-compatible FFmpeg Virtual Bass adapter (optional, local only).
|
| 2 |
+
|
| 3 |
+
FFmpeg's 'virtualbass' filter converts stereo to 2.1, preserving L/R and
|
| 4 |
+
adding a synthesized LFE channel. This is a loudspeaker effect and *not*
|
| 5 |
+
source separation, denoising, or a restored original bass signal.
|
| 6 |
+
"""
|
| 7 |
+
from __future__ import annotations
|
| 8 |
+
import os
|
| 9 |
+
import shutil
|
| 10 |
+
import subprocess
|
| 11 |
+
import math
|
| 12 |
+
from pathlib import Path
|
| 13 |
+
|
| 14 |
+
import numpy as np
|
| 15 |
+
import soundfile as sf
|
| 16 |
+
from .audio import AudioError, audio_info
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def available() -> bool:
|
| 20 |
+
binary=shutil.which("ffmpeg")
|
| 21 |
+
if not binary:
|
| 22 |
+
return False
|
| 23 |
+
try:
|
| 24 |
+
result=subprocess.run([binary,"-hide_banner","-filters"],
|
| 25 |
+
capture_output=True,text=True,timeout=10)
|
| 26 |
+
return result.returncode==0 and "virtualbass" in result.stdout
|
| 27 |
+
except (OSError,subprocess.TimeoutExpired):
|
| 28 |
+
return False
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
def render_virtualbass(
|
| 32 |
+
source:Path, destination:Path, cutoff_hz:float=250,
|
| 33 |
+
strength:float=1.0
|
| 34 |
+
) -> dict:
|
| 35 |
+
if not (100<=cutoff_hz<=500 and .5<=strength<=3):
|
| 36 |
+
raise ValueError("Virtualbass cutoff 100–500 Hz, strength 0.5–3.")
|
| 37 |
+
info=audio_info(source)
|
| 38 |
+
if info.channels!=2:
|
| 39 |
+
raise AudioError("FFmpeg virtualbass requires a stereo source (2 channels).")
|
| 40 |
+
if not available():
|
| 41 |
+
raise AudioError("ffmpeg with virtualbass audio filter not installed.")
|
| 42 |
+
binary=shutil.which("ffmpeg")
|
| 43 |
+
destination.parent.mkdir(parents=True,exist_ok=True)
|
| 44 |
+
tmp=destination.with_name(".virtualbass-tmp.wav")
|
| 45 |
+
command=[
|
| 46 |
+
binary,"-nostdin","-hide_banner","-loglevel","error",
|
| 47 |
+
"-y","-i",str(source),
|
| 48 |
+
"-map","0:a:0","-vn","-af",
|
| 49 |
+
f"virtualbass=cutoff={float(cutoff_hz):.3f}:strength={float(strength):.3f}",
|
| 50 |
+
"-c:a","pcm_f32le",str(tmp)
|
| 51 |
+
]
|
| 52 |
+
try:
|
| 53 |
+
completed=subprocess.run(command,capture_output=True,text=True)
|
| 54 |
+
if completed.returncode:
|
| 55 |
+
raise AudioError("FFmpeg Virtualbass failed: "+completed.stderr[-550:])
|
| 56 |
+
output=sf.info(str(tmp))
|
| 57 |
+
if (output.channels!=3 or output.samplerate!=info.samplerate
|
| 58 |
+
or output.frames!=info.frames):
|
| 59 |
+
raise AudioError("Invalid Virtualbass 2.1 output dimensions.")
|
| 60 |
+
# Confirm that the two stereo channels were not unintentionally altered
|
| 61 |
+
# by the FFmpeg processing pipeline. For codecs, decoder variations are
|
| 62 |
+
# possible, so report actual error rather than promising bit identity.
|
| 63 |
+
diff_max=0.0
|
| 64 |
+
lfe_peak=0.0
|
| 65 |
+
with sf.SoundFile(str(source),"r") as inp, sf.SoundFile(str(tmp),"r") as out:
|
| 66 |
+
while True:
|
| 67 |
+
a=inp.read(65536,dtype="float64",always_2d=True)
|
| 68 |
+
b=out.read(len(a),dtype="float64",always_2d=True)
|
| 69 |
+
if not len(a):
|
| 70 |
+
break
|
| 71 |
+
if len(a)!=len(b):
|
| 72 |
+
raise AudioError("Virtualbass channel alignment error.")
|
| 73 |
+
diff_max=max(diff_max,float(np.max(np.abs(a-b[:,:2]))))
|
| 74 |
+
lfe_peak=max(lfe_peak,float(np.max(np.abs(b[:,2]))))
|
| 75 |
+
# Extra float32 rounding and some codec decode differences are legitimate.
|
| 76 |
+
tmp.replace(destination)
|
| 77 |
+
return {
|
| 78 |
+
"mode":"ffmpeg_virtualbass_2_1",
|
| 79 |
+
"output_filename":destination.name,
|
| 80 |
+
"channels":3,"samplerate":info.samplerate,"frames":info.frames,
|
| 81 |
+
"cutoff_hz":cutoff_hz,"strength":strength,
|
| 82 |
+
"left_right_max_abs_difference":diff_max,
|
| 83 |
+
"lfe_peak_dbfs":round(20*math.log10(max(lfe_peak,1e-12)),3),
|
| 84 |
+
"virtual_lfe_is_synthetic":True,
|
| 85 |
+
"warning":"2.1 output. L/R should remain unchanged; added LFE is synthesized, not recovered. LFE output may exceed 0 dBFS."
|
| 86 |
+
}
|
| 87 |
+
finally:
|
| 88 |
+
tmp.unlink(missing_ok=True)
|
docs/ARRANGEMENT_STUDIO.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Arrangement Studio / v0.6
|
| 2 |
+
|
| 3 |
+
## Audio routing
|
| 4 |
+
|
| 5 |
+
Import -> immutable source -> user-assisted mini inventory -> optional plan -> real source
|
| 6 |
+
separator -> actual WAV stems -> mixer offline rendering -> float WAV + independent report.
|
| 7 |
+
|
| 8 |
+
The plan is metadata only. An "instrument" in the plan is not a synthesized or
|
| 9 |
+
separated track and must never be represented as a stem.
|
| 10 |
+
|
| 11 |
+
## OMEGA-TAG Mini
|
| 12 |
+
|
| 13 |
+
`python -m app.mini_model --train` reproduces synthetic two-stage training with a
|
| 14 |
+
fixed seed. Re-training replaces the checked-in mini model artifact, so keep a backup
|
| 15 |
+
if reproducibility is required.
|
| 16 |
+
|
| 17 |
+
Its six activations are *uncalibrated*. The model analyzes at most twelve short
|
| 18 |
+
windows, so segments missed by sampling can go undetected. Sounds containing
|
| 19 |
+
musical hiss, cymbals or reverb may trigger the 'noise texture' tag. The mini model
|
| 20 |
+
must never authorize irreversible noise subtraction.
|
| 21 |
+
|
| 22 |
+
The tiny model is not the engine that extracts sources; HPSS and Demucs adapters
|
| 23 |
+
provide the actual separation.
|
| 24 |
+
|
| 25 |
+
## Non-destructive mix
|
| 26 |
+
|
| 27 |
+
`app/mixer.py`: sample-aligned chunked float WAV mix. Gain, Mute, Solo, constant-
|
| 28 |
+
center-gain stereo balance, low/high cuts (stateful IIR), tanh saturation, Mid/Side
|
| 29 |
+
width. Warning if output peak exceeds 0 dBFS; no hidden normalization.
|
| 30 |
+
Optional FFmpeg rubberband independent time stretch + pitch shifting.
|
| 31 |
+
Users should re-evaluate all effects when changing tempo/pitch, since no
|
| 32 |
+
perceptual losslessness can be assured.
|
| 33 |
+
|
| 34 |
+
## Practical limits
|
| 35 |
+
|
| 36 |
+
Up to 128 plan targets, up to 128 simultaneously mixed real stems in code.
|
| 37 |
+
Heavy sessions can exceed open-file/resource limits; not a hard promise of 128
|
| 38 |
+
instrument-aware separations. Source sample rates, lengths and channels must match.
|
| 39 |
+
No real-time multi-audio-device ASIO/AU/VST plugin hosting in this version.
|
| 40 |
+
Stereo track waveform uses sparse sampling, not bit-exact peak extraction.
|
| 41 |
+
Audio-player previews isolated stems; full multitrack playback requires an
|
| 42 |
+
explicit offline mix render and is not DAW-grade zero-latency audition.
|
docs/BASS_CORE_DESIGN.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BASS-CORE Ω — Entwicklungskonzept
|
| 2 |
+
|
| 3 |
+
## Trennen vs. bearbeiten
|
| 4 |
+
Tiefe Frequenzen schneiden sich über mehrere Instrumente: ein 50-Hz-Band
|
| 5 |
+
ist kein Synonym für Bassgitarre, und ein Kick-Transient kann Obertonenergie
|
| 6 |
+
bis in den kHz-Bereich besitzen. Deshalb trennt das System Qualitätsstufen.
|
| 7 |
+
|
| 8 |
+
1. **Mix DSP**: Tiefband plus Transientenmaskierung. Schnelle
|
| 9 |
+
frequenzgebundene Schätzung, keine Instrumentenidentifikation.
|
| 10 |
+
2. **HPSS**: Tiefband von harmonischen/perkussiven Quellenschätzungen.
|
| 11 |
+
3. **Demucs**: Tiefband von bereits geschätztem Bass-/Drum-Stem.
|
| 12 |
+
4. **Geplant**: Multimodale ereignisbasierte Separation bis zu Kick-Attack,
|
| 13 |
+
Kick-Body, Bassline, Subbass, Slide, Saturation und Room-Tail.
|
| 14 |
+
|
| 15 |
+
## Signalkette
|
| 16 |
+
|
| 17 |
+
```
|
| 18 |
+
Original X
|
| 19 |
+
├── Quellschätzung: Kick K, Bassline B
|
| 20 |
+
├── Low-band L = K+B
|
| 21 |
+
├── Unprocessed U = X-L
|
| 22 |
+
├── Repair: lowcut DC/Rumble; edit kick / bassline
|
| 23 |
+
├── Sub-EQ + synthetische Obertöne H
|
| 24 |
+
├── Stereo-Bass-Center + Dry/Wet
|
| 25 |
+
├── Edited Bass E
|
| 26 |
+
└── Edited Mix Y = U + E
|
| 27 |
+
└── optional global gain ceiling
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
Kein Signalbereich wird als verlorenes Originalmaterial ausgegeben, wenn
|
| 31 |
+
er synthetisiert wurde. FFT-/PSD- und RMS-Ergebnisse sind Indikatoren für
|
| 32 |
+
Bandenergie, keine messtechnisch validierte Aussage über wahrgenommene
|
| 33 |
+
Qualität.
|
| 34 |
+
|
| 35 |
+
## Detaillierte Weiterentwicklung
|
| 36 |
+
|
| 37 |
+
### Quellzuordnung
|
| 38 |
+
Transiente Kick-Events mit mehrskaliger Wavelet-/STFT-Analyse ermitteln,
|
| 39 |
+
Bassline-F0 mit pYIN/CREPE vergleichend schätzen, Polyphonie diagnostizieren.
|
| 40 |
+
Unsichere Events müssen als Hypothesen angezeigt werden.
|
| 41 |
+
|
| 42 |
+
### Reparatur
|
| 43 |
+
De-click und Aussetzer-Erkennung zunächst in einzelnen Events ermitteln,
|
| 44 |
+
anschließend signalerhaltende Ersatzverfahren auf ausgewählten Zeitfenstern.
|
| 45 |
+
Alle Eingriffe mit Region, Modell, Parameter und A/B-Ansicht protokollieren.
|
| 46 |
+
|
| 47 |
+
### Synthetischer Subbass
|
| 48 |
+
Phasenkohärente subharmonische Oszillatoren nur bei stabiler harmonischer
|
| 49 |
+
Basis, mindestens mit Confidence-Filter. Ohne sichere Tonhöhe kein
|
| 50 |
+
subtonaler Ersatz. Der jetzige Overdrive ergänzt Obertöne, keine
|
| 51 |
+
zuverlässige fehlende Grundfrequenz.
|
| 52 |
+
|
| 53 |
+
### VST3-/AU-Plugins
|
| 54 |
+
Als mögliche Host-Bibliothek eignet sich Spotifys `pedalboard`, die
|
| 55 |
+
VST3 und auf macOS AU unterstützt (GPL-3.0 im Repository). Nicht im
|
| 56 |
+
Produktionsserver in-process: Plugins als eigener beschränkter Prozess
|
| 57 |
+
mit Dateibasiertem IPC/Timeout/Crash-Isolation und explizitem Nutzerpfad.
|
| 58 |
+
Nur vom Nutzer installierte Plugins, keinerlei automatische Downloads.
|
| 59 |
+
Lizenzprüfung vor Weiterverteilung.
|
| 60 |
+
|
| 61 |
+
Geeignete erste Integrationsziele: FabFilter Pro-Q 4 (dynamische/spektrale
|
| 62 |
+
EQ-Bearbeitung), Pro-MB (Low-Band-Dynamik), Sonic Academy KICK 3
|
| 63 |
+
(Kick-Synthese), Surge XT (freie Synthese, GPL3). Diese Tools sind
|
| 64 |
+
Vorschläge und nicht Bestandteil der bisherigen Implementierung.
|
docs/NOISE_CORE_DESIGN.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# NOISE-CORE Ω v0.4 — Preservation-First Design
|
| 2 |
+
|
| 3 |
+
## Grundprinzip
|
| 4 |
+
|
| 5 |
+
Ein beobachteter Signalanteil darf nicht allein deshalb als Störgeräusch
|
| 6 |
+
gelten, weil er rauschhaft, kurz oder tonal wirkt. Transienten, Hall,
|
| 7 |
+
Luft, Mikrodetails und tieffrequente Noten können ähnliche Merkmale tragen.
|
| 8 |
+
|
| 9 |
+
**Fachliche Grenze:** Aus der gemischten Wellenform lässt sich nicht in jedem
|
| 10 |
+
Fall nachweisen, dass eine bestimmte Komponente kein musikalischer Anteil
|
| 11 |
+
ist. Perfektion ist deshalb kein garantiertes Feature. Die risikoärmste
|
| 12 |
+
Standard-Aktion ist **Original unverändert lassen**.
|
| 13 |
+
|
| 14 |
+
## v0.4 ausgeliefert
|
| 15 |
+
|
| 16 |
+
- Chunk-streamende Suche nach isolierten Single-Sample-Impulsen
|
| 17 |
+
(`app/noise.py`) mit bewusst konservativem Schwellenwert;
|
| 18 |
+
- Mehrdeutige Indikatoren für schmale 50/60/100/120-Hz-Spektralspitzen;
|
| 19 |
+
- Standardmäßig reiner Inspektionsmodus: keine Signalveränderung;
|
| 20 |
+
- Explizite Einzelmarkierung aller zu reparierenden Samples;
|
| 21 |
+
- Nur diese Stellen werden mittels Nachbarinterpolation bearbeitet;
|
| 22 |
+
- Einstellbarer Blend-Faktor 0–1;
|
| 23 |
+
- WAV-Float32: Clean-Signal und Original-minus-Clean als Differenzspur;
|
| 24 |
+
- PCM16-Hörkopien und ZIP mit JSON-Provenance-Bericht;
|
| 25 |
+
- SHA-256 des Originals unverändert; rekonstruktive Konsistenz geprüft;
|
| 26 |
+
- Zeitlich beliebig lange Dateien **innerhalb RAM-/Festplatten-/Dateigrößenlimits**;
|
| 27 |
+
- Optionaler Virtualbass 2.1-Export mit FFmpeg.
|
| 28 |
+
|
| 29 |
+
## NICHT ausgeliefert
|
| 30 |
+
|
| 31 |
+
- Kein KI-Modell für semantische Stördetektion;
|
| 32 |
+
- Keine automatische Entrauschung eines gesamten Stücks;
|
| 33 |
+
- Keine echte Störquelle als wiederhergestelltes Ground-Truth-Signal;
|
| 34 |
+
- Kein breitbandiges Spectral De-Noise, keine 50/60-Hz-Notch-Reparatur;
|
| 35 |
+
- Keine beliebig breiten Pops/Crackles, mehrmillisekündigen Dropouts
|
| 36 |
+
oder vollständige Spektralrekonstruktion;
|
| 37 |
+
- Keine absolute Garantie für Erhaltung aller Musikdetails.
|
| 38 |
+
|
| 39 |
+
## Safety/QA
|
| 40 |
+
|
| 41 |
+
- Niemals auto approve, nie „Select all“;
|
| 42 |
+
- Report enthält alle angewandten Samples, Stärke und Effektstärke;
|
| 43 |
+
- Alle Kandidaten müssen nach menschlicher Bestätigung akzeptiert werden;
|
| 44 |
+
- Differenzspur darf musikalische Anteile enthalten. Immer abhören;
|
| 45 |
+
- Code prüft Inputlänge, Finite Values, Outputlänge und Mix-Identität;
|
| 46 |
+
- UI-Erfolgsmeldung erst nach tatsächlicher Fertigstellung des Jobs.
|
| 47 |
+
|
| 48 |
+
**Bekannte Limitierung:** Click Detector benutzt blocklokale Statistik;
|
| 49 |
+
Kandidaten abhängig vom Quellmaterial. Stereo-Musik mit extrem hoher
|
| 50 |
+
Transientendichte kann False Positives erzeugen. Durch die manuelle
|
| 51 |
+
Freigabe wird der automatische Schaden vermieden, nicht jeder Schaden
|
| 52 |
+
durch menschlichen Irrtum.
|
| 53 |
+
|
| 54 |
+
## Höchster KI-Hebel
|
| 55 |
+
|
| 56 |
+
1. **Event Classifier (Listen First):** echte Klicks vs Snare/Kick/HiHat
|
| 57 |
+
und plucked instruments mit calibrated confidence und abstention.
|
| 58 |
+
2. **Sound Source Model:** Störer vom Instrumenten-Stem unterscheiden,
|
| 59 |
+
Leakage messen und unklare Zeit-Frequenz-Zellen erhalten.
|
| 60 |
+
3. **Conservative Inpainting (nur bestätigte Region):** Fallunterscheidung
|
| 61 |
+
Click (einige Samples), Glitch (Millisekunden), Dropout (länger),
|
| 62 |
+
vollständig identifizierte alternative Kanäle; Änderungen markieren.
|
| 63 |
+
4. **Artifact/Detail Judge:** Erhalt von Sustain, Hall und Air durch
|
| 64 |
+
blind und reference-based Tests, plus Removal-Audition.
|
| 65 |
+
5. **Bass Event Graph + F0 tracking:** Phasen-/Tonhöhen-gebundene
|
| 66 |
+
resynthetische Verstärkung statt pauschaler Bass-Normalisierung.
|
| 67 |
+
|
| 68 |
+
## Referenzen
|
| 69 |
+
|
| 70 |
+
- https://downloads.izotope.com/docs/rx6/34-spectral-de-noise/index.html
|
| 71 |
+
- https://downloads.izotope.com/docs/rx6/35-spectral-repair/index.html
|
| 72 |
+
- https://www.izotope.com/community/blog/audio-artifacts
|
| 73 |
+
- https://ffmpeg.org/ffmpeg-filters.html#virtualbass
|
| 74 |
+
- https://github.com/facebookresearch/demucs
|
docs/RELEASE_0.6.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ABSOLUTION Ω · Release v0.6.0
|
| 2 |
+
|
| 3 |
+
## Delivered
|
| 4 |
+
- Arrangement nav/page and responsive DAW-like UI
|
| 5 |
+
- Real color-coded stereo/mono stem waveforms + color overview
|
| 6 |
+
- Mute, Solo, Gain, Pan, low/high cut, saturation, stereo width
|
| 7 |
+
- Offline mix WAV float32 and report; independent tempo and pitch via optional FFmpeg rubberband
|
| 8 |
+
- Synthetic-only fine-tuned OMEGA-TAG Mini inventory, editable plan with up to 128 hypotheses
|
| 9 |
+
- Existing NOISE-CORE and BASS-CORE workflows preserved
|
| 10 |
+
|
| 11 |
+
## Quality verification performed in build environment
|
| 12 |
+
- Python pytest: 32 passed
|
| 13 |
+
- Node.js: app.js and arrangement.js passed `node --check`
|
| 14 |
+
- Actual localhost backend API tested: upload, inventory, real HPSS separation,
|
| 15 |
+
colored stem waveform endpoints, mixer render, +2 semitones, 115% tempo,
|
| 16 |
+
float WAV export.
|
| 17 |
+
- Browser visuals tested in an isolated JavaScript/browser environment with
|
| 18 |
+
actual waveform API samples. Mobile viewport had no page-level horizontal overflow.
|
| 19 |
+
- Direct browser HTTP navigation was blocked by the testing environment.
|
| 20 |
+
- Docker build and real Demucs inference were not performed.
|
| 21 |
+
|
| 22 |
+
## Research limitation
|
| 23 |
+
OMEGA-TAG Mini is trained/fine-tuned on synthetic signals only. It cannot
|
| 24 |
+
confirm real instrument identity. The separation engine remains HPSS or
|
| 25 |
+
optionally locally installed Demucs; editable plan labels do NOT produce
|
| 26 |
+
isolated audio tracks on their own. Neither correct instrument attribution,
|
| 27 |
+
bit-exact perfection, nor zero-impact processing is guaranteed.
|
pyproject.toml
CHANGED
|
@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
|
|
| 4 |
|
| 5 |
[project]
|
| 6 |
name = "absolution-omega"
|
| 7 |
-
version = "0.
|
| 8 |
-
description = "Local-first audio
|
| 9 |
requires-python = ">=3.11"
|
| 10 |
dependencies = [
|
| 11 |
"fastapi>=0.115,<1",
|
|
@@ -23,7 +23,7 @@ neural = ["demucs==4.0.1", "torch>=2.2,<3"]
|
|
| 23 |
[tool.setuptools]
|
| 24 |
packages = ["app"]
|
| 25 |
[tool.setuptools.package-data]
|
| 26 |
-
app = ["static/*.html", "static/*.css", "static/*.js", "static/*.svg", "static/*.wav"]
|
| 27 |
|
| 28 |
[tool.pytest.ini_options]
|
| 29 |
testpaths = ["tests"]
|
|
|
|
| 4 |
|
| 5 |
[project]
|
| 6 |
name = "absolution-omega"
|
| 7 |
+
version = "0.6.0"
|
| 8 |
+
description = "Local-first audio workbench with multi-stem arrangement, synthetic mini tag model, BASS-CORE and NOISE-CORE."
|
| 9 |
requires-python = ">=3.11"
|
| 10 |
dependencies = [
|
| 11 |
"fastapi>=0.115,<1",
|
|
|
|
| 23 |
[tool.setuptools]
|
| 24 |
packages = ["app"]
|
| 25 |
[tool.setuptools.package-data]
|
| 26 |
+
app = ["static/*.html", "static/*.css", "static/*.js", "static/*.svg", "static/*.wav", "models/*.npz"]
|
| 27 |
|
| 28 |
[tool.pytest.ini_options]
|
| 29 |
testpaths = ["tests"]
|
tests/test_arrangement.py
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""ABSOLUTION Ω v0.6: multi-stem planning and audible arrangement render."""
|
| 2 |
+
from pathlib import Path
|
| 3 |
+
import math
|
| 4 |
+
import threading
|
| 5 |
+
import time
|
| 6 |
+
|
| 7 |
+
import numpy as np
|
| 8 |
+
import pytest
|
| 9 |
+
import soundfile as sf
|
| 10 |
+
from fastapi.testclient import TestClient
|
| 11 |
+
from app.mixer import render_mix, sampled_peaks
|
| 12 |
+
from app.mini_model import MODEL_FILE, inspect_file
|
| 13 |
+
from app.server import create_app
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
def make_stems(folder, sr=8000, seconds=1.5):
|
| 17 |
+
folder.mkdir(parents=True,exist_ok=True)
|
| 18 |
+
t=np.arange(int(sr*seconds))/sr
|
| 19 |
+
a=np.column_stack((.10*np.sin(2*np.pi*90*t),.08*np.sin(2*np.pi*90*t)))
|
| 20 |
+
b=np.column_stack((.07*np.sin(2*np.pi*420*t),.05*np.sin(2*np.pi*420*t)))
|
| 21 |
+
for k,v in (("bass",a),("other",b)):
|
| 22 |
+
sf.write(folder/f"{k}.wav",v,sr,subtype="FLOAT")
|
| 23 |
+
return {"bass":folder/"bass.wav","other":folder/"other.wav"},a,b
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
def test_mixer_is_additive_at_neutral_controls(tmp_path):
|
| 27 |
+
paths,a,b=make_stems(tmp_path)
|
| 28 |
+
report=render_mix(paths,{},tmp_path/"mixed.wav")
|
| 29 |
+
out,sr=sf.read(tmp_path/"mixed.wav",always_2d=True)
|
| 30 |
+
assert sr==8000 and report["channels"]==2
|
| 31 |
+
assert np.max(np.abs(out-(a+b)))<2e-7
|
| 32 |
+
assert report["float_wav"] is True
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
def test_mute_solo_and_pan_are_real(tmp_path):
|
| 36 |
+
paths,a,b=make_stems(tmp_path)
|
| 37 |
+
options={"tracks":{"bass":{"solo":True,"pan":-1},"other":{"mute":False}}}
|
| 38 |
+
render_mix(paths,options,tmp_path/"mix.wav")
|
| 39 |
+
out,_=sf.read(tmp_path/"mix.wav",always_2d=True)
|
| 40 |
+
assert np.max(np.abs(out[:,1]))<1e-7
|
| 41 |
+
assert np.max(np.abs(out[:,0]))>0.06
|
| 42 |
+
options={"tracks":{"bass":{"mute":True},"other":{"mute":True}}}
|
| 43 |
+
render_mix(paths,options,tmp_path/"silent.wav")
|
| 44 |
+
out,_=sf.read(tmp_path/"silent.wav",always_2d=True)
|
| 45 |
+
assert np.max(np.abs(out))==0
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def test_mixer_fx_and_reject_unknown(tmp_path):
|
| 49 |
+
paths,a,b=make_stems(tmp_path)
|
| 50 |
+
options={"tracks":{"bass":{"gain_db":-6,"highpass_hz":60,"lowpass_hz":550,
|
| 51 |
+
"drive":.3,"width":.7}}}
|
| 52 |
+
report=render_mix(paths,options,tmp_path/"fx.wav")
|
| 53 |
+
assert math.isfinite(report["peak_dbfs"])
|
| 54 |
+
assert sf.info(tmp_path/"fx.wav").frames==len(a)
|
| 55 |
+
with pytest.raises(ValueError,match="Unknown track"):
|
| 56 |
+
render_mix(paths,{"tracks":{"vocals":{"gain_db":3}}},tmp_path/"bad.wav")
|
| 57 |
+
with pytest.raises(ValueError,match="Highpass"):
|
| 58 |
+
render_mix(paths,{"tracks":{"bass":{"highpass_hz":300,"lowpass_hz":120}}},tmp_path/"bad2.wav")
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def test_sparse_waveform_is_file_derived(tmp_path):
|
| 62 |
+
paths,a,b=make_stems(tmp_path)
|
| 63 |
+
w=sampled_peaks(paths["bass"],80)
|
| 64 |
+
assert len(w["samples"])==80 and max(w["samples"])>.08
|
| 65 |
+
assert w["peak_reliability"].startswith("visualization")
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def test_synthetic_mini_model_is_bundled(tmp_path):
|
| 69 |
+
assert MODEL_FILE.is_file()
|
| 70 |
+
paths,a,b=make_stems(tmp_path)
|
| 71 |
+
inv=inspect_file(paths["bass"],max_windows=3)
|
| 72 |
+
assert inv["model"]=="OMEGA-TAG Mini v1"
|
| 73 |
+
assert len(inv["detections"])==6
|
| 74 |
+
assert inv["sampled_windows"]==3
|
| 75 |
+
assert "SYNTHETIC" in inv["scope"]
|
| 76 |
+
assert all(0<=d["score"]<=1 for d in inv["detections"])
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
def test_inventory_plan_and_mixer_api(tmp_path):
|
| 80 |
+
app=create_app(tmp_path/"data")
|
| 81 |
+
with TestClient(app) as cli:
|
| 82 |
+
paths,a,b=make_stems(tmp_path/"testsignal")
|
| 83 |
+
res=cli.post("/api/v1/projects",json={"name":"Arrangement QA"})
|
| 84 |
+
assert res.status_code==201
|
| 85 |
+
project=res.json()["id"]
|
| 86 |
+
with open(paths["bass"],"rb") as f:
|
| 87 |
+
up=cli.post("/api/v1/assets",data={"project_id":project},
|
| 88 |
+
files={"file":("mix.wav",f,"audio/wav")})
|
| 89 |
+
assert up.status_code==201,up.text
|
| 90 |
+
res=cli.post(f"/api/v1/projects/{project}/inventory")
|
| 91 |
+
assert res.status_code==200,res.text
|
| 92 |
+
assert res.json()["inventory"]["model_kind"].startswith("tiny_neural_network")
|
| 93 |
+
plan=[{"id":"my_custom_bass","label":"Bass-Synth 2","enabled":True},
|
| 94 |
+
{"id":"kick_like","label":"Kick-Verdacht","enabled":False}]
|
| 95 |
+
resp=cli.put(f"/api/v1/projects/{project}/plan",json={"tracks":plan})
|
| 96 |
+
assert resp.status_code==200,resp.text
|
| 97 |
+
assert resp.json()["status"]=="hypotheses_only"
|
| 98 |
+
assert cli.get(f"/api/v1/projects/{project}").json()["plan"]==plan
|
| 99 |
+
bad=cli.put(f"/api/v1/projects/{project}/plan",
|
| 100 |
+
json={"tracks":[plan[0],plan[0]]})
|
| 101 |
+
assert bad.status_code==422
|
| 102 |
+
assert cli.post("/api/v1/jobs/mix",
|
| 103 |
+
json={"project_id":project,"tracks":{}}).status_code==409
|
| 104 |
+
wave=cli.get(f"/api/v1/projects/{project}/wave/original?points=64")
|
| 105 |
+
assert wave.status_code==200 and len(wave.json()["samples"])==64
|
| 106 |
+
assert cli.get(f"/api/v1/projects/{project}/wave/not-a-stem").status_code==404
|
| 107 |
+
start=cli.post("/api/v1/jobs/separate",json={"project_id":project,"model":"hpss"})
|
| 108 |
+
assert start.status_code==202,start.text
|
| 109 |
+
jobid=start.json()["id"]
|
| 110 |
+
for _ in range(100):
|
| 111 |
+
item=cli.get("/api/v1/jobs/"+jobid).json()
|
| 112 |
+
if item["status"] in ("done","failed"):break
|
| 113 |
+
time.sleep(.08)
|
| 114 |
+
assert item["status"]=="done",item
|
| 115 |
+
mani=cli.get(f"/api/v1/projects/{project}").json()
|
| 116 |
+
assert set(mani["stems"])=={"harmonic","percussive","residual"}
|
| 117 |
+
assert cli.get(f"/api/v1/projects/{project}/wave/harmonic?points=64").status_code==200
|
| 118 |
+
bad=cli.post("/api/v1/jobs/mix",
|
| 119 |
+
json={"project_id":project,"tracks":{"imaginary":{"gain_db":2}}})
|
| 120 |
+
assert bad.status_code==422
|
| 121 |
+
start=cli.post("/api/v1/jobs/mix",json={"project_id":project,"tracks":{
|
| 122 |
+
"harmonic":{"gain_db":-3,"pan":-.45,"solo":True},
|
| 123 |
+
"percussive":{"gain_db":0,"mute":False}}})
|
| 124 |
+
assert start.status_code==202,start.text
|
| 125 |
+
jid=start.json()["id"]
|
| 126 |
+
for _ in range(100):
|
| 127 |
+
item=cli.get("/api/v1/jobs/"+jid).json()
|
| 128 |
+
if item["status"] in ("done","failed"):break
|
| 129 |
+
time.sleep(.08)
|
| 130 |
+
assert item["status"]=="done",item
|
| 131 |
+
result=cli.get(f"/api/v1/projects/{project}/mixer").json()["mixer"]
|
| 132 |
+
assert result["result"]["float_wav"]
|
| 133 |
+
mixfile=cli.get(f"/api/v1/projects/{project}/mixer/audio")
|
| 134 |
+
assert mixfile.status_code==200 and mixfile.content[:4]==b"RIFF"
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
def test_long_181_second_mix_without_duration_cutoff(tmp_path):
|
| 138 |
+
sr=8000
|
| 139 |
+
length=181*sr
|
| 140 |
+
src=tmp_path/"long.wav"
|
| 141 |
+
with sf.SoundFile(src,mode="w",samplerate=sr,channels=2,subtype="FLOAT") as out:
|
| 142 |
+
rng=np.random.default_rng(14)
|
| 143 |
+
for i in range(0,length,32768):
|
| 144 |
+
n=min(32768,length-i)
|
| 145 |
+
x=rng.standard_normal((n,2)).astype(np.float32)*.002
|
| 146 |
+
out.write(x)
|
| 147 |
+
report=render_mix({"one":src},{},tmp_path/"long_render.wav")
|
| 148 |
+
assert report["source_frames"]==length
|
| 149 |
+
assert sf.info(tmp_path/"long_render.wav").frames==length
|
| 150 |
+
assert report["peak_dbfs"]<0
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
def test_mixing_more_than_four_real_stems(tmp_path):
|
| 154 |
+
src,a,b=make_stems(tmp_path)
|
| 155 |
+
stems={f"layer_{i}":src["bass"] for i in range(7)}
|
| 156 |
+
report=render_mix(stems,{},tmp_path/"seven_stems.wav")
|
| 157 |
+
assert report["source_frames"]==a.shape[0]
|
| 158 |
+
assert report["peak_dbfs"]>-10
|
tests/test_bass.py
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""BASS-CORE regression tests with entirely synthetic input, no model download."""
|
| 2 |
+
import io
|
| 3 |
+
import json
|
| 4 |
+
import math
|
| 5 |
+
import time
|
| 6 |
+
import zipfile
|
| 7 |
+
|
| 8 |
+
import numpy as np
|
| 9 |
+
import pytest
|
| 10 |
+
import soundfile as sf
|
| 11 |
+
from fastapi.testclient import TestClient
|
| 12 |
+
|
| 13 |
+
from app.audio import sha256_file
|
| 14 |
+
from app.bass import BassParams, _transform, process_bass_file
|
| 15 |
+
from app.server import create_app
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
def make_audio(sr=8000, duration=2.0, stereo=True):
|
| 19 |
+
t = np.arange(int(sr * duration)) / sr
|
| 20 |
+
bass = .18 * np.sin(2 * np.pi * 55 * t)
|
| 21 |
+
kick = np.zeros_like(t)
|
| 22 |
+
for when in np.arange(.15, duration, .5):
|
| 23 |
+
pos = int(when * sr)
|
| 24 |
+
end = min(len(t), pos + int(sr * .12))
|
| 25 |
+
i = np.arange(end-pos) / sr
|
| 26 |
+
kick[pos:end] += .33 * np.sin(2*np.pi*(90 - 40*(i/.12))*i) * np.exp(-i*32)
|
| 27 |
+
high = .08 * np.sin(2 * np.pi * 900 * t)
|
| 28 |
+
mono = bass + kick + high
|
| 29 |
+
return np.column_stack((mono,mono*.9)) if stereo else mono[:,None]
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
def test_bass_stems_derive_from_original_and_synth_harmonics(tmp_path):
|
| 33 |
+
sr=8000
|
| 34 |
+
source=tmp_path/"source.wav"
|
| 35 |
+
x=make_audio()
|
| 36 |
+
sf.write(source,x,sr,subtype="FLOAT")
|
| 37 |
+
cfg=BassParams(kick_gain_db=3, bass_gain_db=2, sub_gain_db=3,
|
| 38 |
+
harmonics=.85, mono_below_hz=100, ceiling_dbfs=-1)
|
| 39 |
+
stems,report=process_bass_file(source,tmp_path/"bass",cfg,
|
| 40 |
+
chunk_frames=8192,context_frames=4096)
|
| 41 |
+
assert report["reconstruction_check"]["consistent"]
|
| 42 |
+
assert report["reconstruction_check"]["max_abs_error"] < 1e-9
|
| 43 |
+
assert report["created_harmonics_are_synthetic"] is True
|
| 44 |
+
assert report["mode"]=="dsp"
|
| 45 |
+
before,_=sf.read(tmp_path/"bass"/"bass_band.wav",always_2d=True)
|
| 46 |
+
kick,_=sf.read(tmp_path/"bass"/"kick_estimate.wav",always_2d=True)
|
| 47 |
+
line,_=sf.read(tmp_path/"bass"/"bassline_estimate.wav",always_2d=True)
|
| 48 |
+
other,_=sf.read(tmp_path/"bass"/"other_unprocessed.wav",always_2d=True)
|
| 49 |
+
mix,_=sf.read(tmp_path/"bass"/"mix_optimized.wav",always_2d=True)
|
| 50 |
+
harm,_=sf.read(tmp_path/"bass"/"harmonics_added.wav",always_2d=True)
|
| 51 |
+
assert np.max(np.abs(before-(kick+line))) < 1e-6
|
| 52 |
+
assert np.max(np.abs(x-(kick+line+other))) < 2e-6
|
| 53 |
+
assert np.max(np.abs(harm)) > 1e-6
|
| 54 |
+
assert not np.allclose(mix,x)
|
| 55 |
+
assert np.max(np.abs(mix)) <= 10**(-1/20) + 3e-6
|
| 56 |
+
assert len(stems)==7
|
| 57 |
+
assert all(sf.info(tmp_path/"bass"/v["master"]).frames == len(x) for v in stems.values())
|
| 58 |
+
assert all((tmp_path/"bass"/v["preview"]).exists() for v in stems.values())
|
| 59 |
+
assert len(report["first_chunk_spectrum"]["before"]) == 6
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
def test_bass_dry_and_invalid_model_stem_lengths(tmp_path):
|
| 63 |
+
x=make_audio(sr=8000,duration=.6)
|
| 64 |
+
tracks=_transform(x,8000,BassParams(wet=0,lowcut_hz=35),"dsp")
|
| 65 |
+
assert np.max(np.abs(tracks["mix_optimized"]-x)) < 1e-8
|
| 66 |
+
source=tmp_path/"input.wav"
|
| 67 |
+
wrong=tmp_path/"wrong.wav"
|
| 68 |
+
sf.write(source,x,8000)
|
| 69 |
+
sf.write(wrong,x[:-100],8000)
|
| 70 |
+
with pytest.raises(ValueError,match="match source"):
|
| 71 |
+
process_bass_file(source,tmp_path/"out", BassParams(),"hpss",
|
| 72 |
+
refs={"harmonic":wrong,"percussive":wrong})
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
def test_bass_api_dsp_hpss_and_zip_without_changing_original(tmp_path):
|
| 76 |
+
app=create_app(tmp_path/"store")
|
| 77 |
+
x=make_audio(duration=.8)
|
| 78 |
+
payload=io.BytesIO()
|
| 79 |
+
sf.write(payload,x,8000,format="WAV",subtype="FLOAT")
|
| 80 |
+
with TestClient(app) as c:
|
| 81 |
+
p=c.post("/api/v1/projects",json={"name":"Bass Lab"}).json()
|
| 82 |
+
pid=p["id"]
|
| 83 |
+
result=c.post("/api/v1/assets",data={"project_id":pid},
|
| 84 |
+
files={"file":("bass.wav",payload.getvalue(),"audio/wav")})
|
| 85 |
+
assert result.status_code==201,result.text
|
| 86 |
+
original_sha=result.json()["asset"]["sha256"]
|
| 87 |
+
assert c.get(f"/api/v1/projects/{pid}/bass").json()["bass"] is None
|
| 88 |
+
empty=c.get(f"/api/v1/projects/{pid}/bass/export")
|
| 89 |
+
assert empty.status_code==409
|
| 90 |
+
assert c.post("/api/v1/jobs/bass",json={
|
| 91 |
+
"project_id":pid,"source_mode":"hpss"}).status_code==409
|
| 92 |
+
assert c.post("/api/v1/jobs/bass",json={
|
| 93 |
+
"project_id":pid,"kick_gain_db":999}).status_code==422
|
| 94 |
+
job=c.post("/api/v1/jobs/bass",json={
|
| 95 |
+
"project_id":pid,"source_mode":"auto",
|
| 96 |
+
"kick_gain_db":2,"sub_gain_db":1,"harmonics":.6
|
| 97 |
+
})
|
| 98 |
+
assert job.status_code==202,job.text
|
| 99 |
+
for _ in range(160):
|
| 100 |
+
result=c.get(f"/api/v1/jobs/{job.json()['id']}").json()
|
| 101 |
+
if result["status"] in ("done","failed"):break
|
| 102 |
+
time.sleep(.05)
|
| 103 |
+
assert result["status"]=="done",result
|
| 104 |
+
bass=c.get(f"/api/v1/projects/{pid}/bass").json()["bass"]
|
| 105 |
+
assert bass["mode"]=="dsp"
|
| 106 |
+
assert bass["source_sha256"]==original_sha
|
| 107 |
+
assert bass["report"]["reconstruction_check"]["consistent"]
|
| 108 |
+
out=c.get(f"/api/v1/projects/{pid}/bass/audio/mix_optimized")
|
| 109 |
+
assert out.status_code==200
|
| 110 |
+
xx, sr=sf.read(io.BytesIO(out.content),always_2d=True)
|
| 111 |
+
assert sr==8000 and len(xx)==len(x)
|
| 112 |
+
preview=c.get(f"/api/v1/projects/{pid}/bass/audio/kick_estimate?preview=true")
|
| 113 |
+
assert preview.content[:4]==b"RIFF"
|
| 114 |
+
assert c.get(f"/api/v1/projects/{pid}/bass/audio/not_real").status_code==404
|
| 115 |
+
z=c.get(f"/api/v1/projects/{pid}/bass/export")
|
| 116 |
+
assert z.status_code==200
|
| 117 |
+
with zipfile.ZipFile(io.BytesIO(z.content)) as archive:
|
| 118 |
+
assert "bass_report.json" in archive.namelist()
|
| 119 |
+
assert "stems/mix_optimized.wav" in archive.namelist()
|
| 120 |
+
assert json.loads(archive.read("bass_report.json"))["mode"]=="dsp"
|
| 121 |
+
assert c.get(f"/api/v1/projects/{pid}").json()["asset"]["sha256"]==original_sha
|
| 122 |
+
|
| 123 |
+
# The existing HPSS engine is available, now test source routing.
|
| 124 |
+
job=c.post("/api/v1/jobs/separate",json={"project_id":pid,"model":"hpss"}).json()
|
| 125 |
+
for _ in range(160):
|
| 126 |
+
status=c.get(f"/api/v1/jobs/{job['id']}").json()
|
| 127 |
+
if status["status"] in ("done","failed"):break
|
| 128 |
+
time.sleep(.05)
|
| 129 |
+
assert status["status"]=="done",status
|
| 130 |
+
job=c.post("/api/v1/jobs/bass",json={"project_id":pid,"source_mode":"auto"}).json()
|
| 131 |
+
for _ in range(160):
|
| 132 |
+
status=c.get(f"/api/v1/jobs/{job['id']}").json()
|
| 133 |
+
if status["status"] in ("done","failed"):break
|
| 134 |
+
time.sleep(.05)
|
| 135 |
+
assert status["status"]=="done",status
|
| 136 |
+
assert c.get(f"/api/v1/projects/{pid}/bass").json()["bass"]["mode"]=="hpss"
|
| 137 |
+
root=tmp_path/"store"/pid
|
| 138 |
+
assert sha256_file(root/"source.wav")==original_sha
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def test_bass_streaming_over_180_seconds(tmp_path):
|
| 142 |
+
src=tmp_path/"long.wav"
|
| 143 |
+
with sf.SoundFile(src,"w",samplerate=8000,channels=1,subtype="PCM_16") as file:
|
| 144 |
+
file.seek(181*8000-1)
|
| 145 |
+
file.write([.1])
|
| 146 |
+
m,r=process_bass_file(src,tmp_path/"long_bass",BassParams(
|
| 147 |
+
crossover_hz=140,harmonics=0,lowcut_hz=20,mono_below_hz=0
|
| 148 |
+
), chunk_frames=131072)
|
| 149 |
+
assert r["reconstruction_check"]["consistent"],r
|
| 150 |
+
assert sf.info(tmp_path/"long_bass"/m["mix_optimized"]["master"]).frames == 181*8000
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
|
| 154 |
+
def test_bass_at_standard_music_rate_and_chunk_boundaries(tmp_path):
|
| 155 |
+
sr = 44100
|
| 156 |
+
samples = make_audio(sr=sr, duration=3.25)
|
| 157 |
+
src = tmp_path/"standard.wav"
|
| 158 |
+
sf.write(src,samples,sr,subtype="FLOAT")
|
| 159 |
+
outs, rep = process_bass_file(src,tmp_path/"standard_out",
|
| 160 |
+
BassParams(kick_gain_db=1.5,harmonics=.4),
|
| 161 |
+
chunk_frames=65536,context_frames=16384)
|
| 162 |
+
assert rep["reconstruction_check"]["consistent"]
|
| 163 |
+
bass,_=sf.read(tmp_path/"standard_out"/outs["bass_band"]["master"],always_2d=True)
|
| 164 |
+
assert np.isfinite(bass).all()
|
| 165 |
+
# Streaming does not create abrupt jumps across chunk boundaries.
|
| 166 |
+
jumps=np.max(np.abs(np.diff(bass,axis=0)),axis=1)
|
| 167 |
+
edges=[65536, 131072]
|
| 168 |
+
assert max(float(jumps[e-1]) for e in edges) < max(0.015,float(np.percentile(jumps,99.99))*4)
|
tests/test_noise.py
ADDED
|
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""NOISE-CORE Ω — regression against accidental removal of original music."""
|
| 2 |
+
import io
|
| 3 |
+
import json
|
| 4 |
+
import shutil
|
| 5 |
+
import time
|
| 6 |
+
import zipfile
|
| 7 |
+
|
| 8 |
+
import numpy as np
|
| 9 |
+
import pytest
|
| 10 |
+
import soundfile as sf
|
| 11 |
+
from fastapi.testclient import TestClient
|
| 12 |
+
|
| 13 |
+
from app.audio import sha256_file
|
| 14 |
+
from app.noise import RepairParams, inspect_noise_file, repair_noise_file
|
| 15 |
+
from app.server import create_app
|
| 16 |
+
from app.virtualbass import available, render_virtualbass
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def make_audio(sr=8000, duration=2.0, stereo=True, clicks=True):
|
| 20 |
+
t=np.arange(int(sr*duration))/sr
|
| 21 |
+
# Include low tone, middle tone and low-amplitude air frequencies.
|
| 22 |
+
pure=0.15*np.sin(2*np.pi*55*t)+.04*np.sin(2*np.pi*440*t)
|
| 23 |
+
pure+=.012*np.sin(2*np.pi*1200*t)
|
| 24 |
+
x=np.stack([pure,pure*.87],axis=1) if stereo else pure[:,None]
|
| 25 |
+
if clicks:
|
| 26 |
+
x[int(.540125*sr),0]+=.85
|
| 27 |
+
x[int(1.250125*sr),0]-=.8
|
| 28 |
+
return x
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
def await_job(client, jid, delay=.025, count=300):
|
| 32 |
+
for _ in range(count):
|
| 33 |
+
job=client.get(f"/api/v1/jobs/{jid}").json()
|
| 34 |
+
if job["status"] in ("done","failed"):
|
| 35 |
+
return job
|
| 36 |
+
time.sleep(delay)
|
| 37 |
+
pytest.fail(f"Timed out waiting for job {jid}")
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
def test_noise_scan_only_has_no_mutation_and_preserves_clean_music(tmp_path):
|
| 41 |
+
src=tmp_path/"music.wav"
|
| 42 |
+
x=make_audio(clicks=False)
|
| 43 |
+
sf.write(src,x,8000,subtype="FLOAT")
|
| 44 |
+
digest=sha256_file(src)
|
| 45 |
+
scan=inspect_noise_file(src)
|
| 46 |
+
assert scan["event_count"]==0
|
| 47 |
+
assert scan["mode"]=="inspect_only"
|
| 48 |
+
assert scan["auto_repair"] is False
|
| 49 |
+
assert scan["broadband_denoise_available"] is False
|
| 50 |
+
assert sha256_file(src)==digest
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def test_manually_approved_clicks_have_exact_difference_stem(tmp_path):
|
| 54 |
+
src=tmp_path/"click.wav"
|
| 55 |
+
x=make_audio()
|
| 56 |
+
sf.write(src,x,8000,subtype="FLOAT")
|
| 57 |
+
digest=sha256_file(src)
|
| 58 |
+
scan=inspect_noise_file(src)
|
| 59 |
+
positions=[e["sample"] for e in scan["events"]]
|
| 60 |
+
assert 4321 in positions and 10001 in positions, positions
|
| 61 |
+
assert scan["event_count"]==2
|
| 62 |
+
tracks,report=repair_noise_file(src,tmp_path/"processed",
|
| 63 |
+
[4321],RepairParams(strength=.8),
|
| 64 |
+
chunk_frames=3072)
|
| 65 |
+
assert report["changed_sample_frames"]==1
|
| 66 |
+
assert report["reconstruction_consistent"]
|
| 67 |
+
assert sha256_file(src)==digest
|
| 68 |
+
after,_=sf.read(tmp_path/"processed"/tracks["clean"]["master"],always_2d=True)
|
| 69 |
+
removed,_=sf.read(tmp_path/"processed"/tracks["difference"]["master"],always_2d=True)
|
| 70 |
+
original,_=sf.read(src,always_2d=True)
|
| 71 |
+
assert np.max(np.abs(after+removed-original))<7e-8
|
| 72 |
+
unaffected=np.ones(len(original),dtype=bool)
|
| 73 |
+
unaffected[4321]=False
|
| 74 |
+
assert np.max(np.abs(after[unaffected]-original[unaffected]))<7e-8
|
| 75 |
+
assert np.max(np.abs(removed[unaffected]))<1e-12
|
| 76 |
+
assert abs(removed[10001,0])<1e-12 # second, unapproved click not touched
|
| 77 |
+
assert np.max(np.abs(removed[4321]))>.4
|
| 78 |
+
for kind in ("clean","difference"):
|
| 79 |
+
assert sf.info(tmp_path/"processed"/tracks[kind]["preview"]).frames==len(x)
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
def test_no_selected_samples_renders_no_changes(tmp_path):
|
| 83 |
+
src=tmp_path/"music.wav"
|
| 84 |
+
sf.write(src,make_audio(),8000,subtype="FLOAT")
|
| 85 |
+
tracks,report=repair_noise_file(src,tmp_path/"render",[],
|
| 86 |
+
RepairParams(.5),chunk_frames=4096)
|
| 87 |
+
a,_=sf.read(src,always_2d=True)
|
| 88 |
+
b,_=sf.read(tmp_path/"render"/tracks["clean"]["master"],always_2d=True)
|
| 89 |
+
assert np.max(np.abs(a-b))<3e-8
|
| 90 |
+
assert report["changed_sample_frames"]==0
|
| 91 |
+
with pytest.raises(ValueError):
|
| 92 |
+
repair_noise_file(src,tmp_path/"wrong",[999999],RepairParams(.8))
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def test_noise_api_scan_approval_export_and_manifest(tmp_path):
|
| 96 |
+
x=make_audio()
|
| 97 |
+
buff=io.BytesIO()
|
| 98 |
+
sf.write(buff,x,8000,format="WAV",subtype="FLOAT")
|
| 99 |
+
app=create_app(tmp_path/"store")
|
| 100 |
+
with TestClient(app) as client:
|
| 101 |
+
pid=client.post("/api/v1/projects",json={"name":"NOISE Test"}).json()["id"]
|
| 102 |
+
assert client.post("/api/v1/jobs/noise/scan",
|
| 103 |
+
json={"project_id":pid}).status_code==409
|
| 104 |
+
assert client.post("/api/v1/assets",data={"project_id":pid},
|
| 105 |
+
files={"file":("music.wav",buff.getvalue(),"audio/wav")}).status_code==201
|
| 106 |
+
original_hash=client.get(f"/api/v1/projects/{pid}").json()["asset"]["sha256"]
|
| 107 |
+
assert client.post("/api/v1/jobs/noise/repair",
|
| 108 |
+
json={"project_id":pid,"approved_samples":[4321]}).status_code==409
|
| 109 |
+
scanjob=client.post("/api/v1/jobs/noise/scan",json={"project_id":pid})
|
| 110 |
+
assert scanjob.status_code==202
|
| 111 |
+
assert await_job(client,scanjob.json()["id"])["status"]=="done"
|
| 112 |
+
details=client.get(f"/api/v1/projects/{pid}/noise").json()["noise"]
|
| 113 |
+
assert details["scan"]["event_count"]==2
|
| 114 |
+
assert details["repair"] is None
|
| 115 |
+
assert client.post("/api/v1/jobs/noise/repair",
|
| 116 |
+
json={"project_id":pid,"approved_samples":[222]}).status_code==422
|
| 117 |
+
assert client.post("/api/v1/jobs/noise/repair",
|
| 118 |
+
json={"project_id":pid,"approved_samples":[]}).status_code==422
|
| 119 |
+
job=client.post("/api/v1/jobs/noise/repair",json={
|
| 120 |
+
"project_id":pid,"approved_samples":[4321],"strength":.8
|
| 121 |
+
})
|
| 122 |
+
assert job.status_code==202,job.text
|
| 123 |
+
assert await_job(client,job.json()["id"])["status"]=="done"
|
| 124 |
+
result=client.get(f"/api/v1/projects/{pid}/noise").json()["noise"]["repair"]
|
| 125 |
+
assert result["source_sha256"]==original_hash
|
| 126 |
+
assert result["report"]["changed_sample_frames"]==1
|
| 127 |
+
assert result["report"]["reconstruction_consistent"]
|
| 128 |
+
assert client.get(f"/api/v1/projects/{pid}/noise/audio/clean?preview=true").content[:4]==b"RIFF"
|
| 129 |
+
diff=client.get(f"/api/v1/projects/{pid}/noise/audio/difference")
|
| 130 |
+
assert diff.status_code==200
|
| 131 |
+
assert client.get(f"/api/v1/projects/{pid}/noise/audio/bad").status_code==404
|
| 132 |
+
packed=client.get(f"/api/v1/projects/{pid}/noise/export")
|
| 133 |
+
assert packed.status_code==200
|
| 134 |
+
with zipfile.ZipFile(io.BytesIO(packed.content)) as z:
|
| 135 |
+
assert "tracks/clean.wav" in z.namelist()
|
| 136 |
+
assert "tracks/difference.wav" in z.namelist()
|
| 137 |
+
assert json.loads(z.read("report.json"))["report"]["reconstruction_consistent"]
|
| 138 |
+
assert client.get(f"/api/v1/projects/{pid}").json()["asset"]["sha256"]==original_hash
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def test_noise_scan_longer_than_three_minutes(tmp_path):
|
| 142 |
+
source=tmp_path/"long.wav"
|
| 143 |
+
sr=8000; frames=sr*181
|
| 144 |
+
with sf.SoundFile(source,"w",samplerate=sr,channels=1,subtype="PCM_16") as wav:
|
| 145 |
+
wav.seek(frames-1);wav.write([0.])
|
| 146 |
+
result=inspect_noise_file(source)
|
| 147 |
+
assert result["input_frames"]==frames
|
| 148 |
+
assert result["samplerate"]==sr
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
@pytest.mark.skipif(not available(),reason="FFmpeg virtualbass not installed")
|
| 152 |
+
def test_virtualbass_2_1_without_stereo_mutation(tmp_path):
|
| 153 |
+
src=tmp_path/"stereo.wav"
|
| 154 |
+
sf.write(src,make_audio(clicks=False),8000,subtype="FLOAT")
|
| 155 |
+
sha=sha256_file(src)
|
| 156 |
+
result=render_virtualbass(src,tmp_path/"virtual.wav",250,1.)
|
| 157 |
+
a,s=sf.read(src,always_2d=True)
|
| 158 |
+
b,sb=sf.read(tmp_path/"virtual.wav",always_2d=True)
|
| 159 |
+
assert s==sb==8000 and b.shape==(a.shape[0],3)
|
| 160 |
+
assert np.max(np.abs(a-b[:,:2]))<1e-6
|
| 161 |
+
assert np.max(np.abs(b[:,2]))>.01
|
| 162 |
+
assert result["virtual_lfe_is_synthetic"] and result["left_right_max_abs_difference"]<1e-6
|
| 163 |
+
assert sha256_file(src)==sha
|
| 164 |
+
|
| 165 |
+
|
| 166 |
+
@pytest.mark.skipif(not available(),reason="FFmpeg virtualbass not installed")
|
| 167 |
+
def test_virtualbass_api_job_and_download(tmp_path):
|
| 168 |
+
source=io.BytesIO()
|
| 169 |
+
sf.write(source,make_audio(clicks=False),8000,format="WAV",subtype="FLOAT")
|
| 170 |
+
with TestClient(create_app(tmp_path/"db")) as c:
|
| 171 |
+
pid=c.post("/api/v1/projects",json={"name":"Virtual"}).json()["id"]
|
| 172 |
+
uploaded=c.post("/api/v1/assets",data={"project_id":pid},
|
| 173 |
+
files={"file":("virtual.wav",source.getvalue(),"audio/wav")})
|
| 174 |
+
sha=uploaded.json()["asset"]["sha256"]
|
| 175 |
+
bad=c.post("/api/v1/jobs/bass/virtual",
|
| 176 |
+
json={"project_id":pid,"cutoff_hz":2000})
|
| 177 |
+
assert bad.status_code==422
|
| 178 |
+
job=c.post("/api/v1/jobs/bass/virtual",
|
| 179 |
+
json={"project_id":pid,"cutoff_hz":250,"strength":1})
|
| 180 |
+
assert job.status_code==202,job.text
|
| 181 |
+
assert await_job(c,job.json()["id"],count=400)["status"]=="done"
|
| 182 |
+
result=c.get(f"/api/v1/projects/{pid}/virtualbass").json()["virtualbass"]
|
| 183 |
+
assert result["report"]["channels"]==3
|
| 184 |
+
output=c.get(f"/api/v1/projects/{pid}/virtualbass/audio")
|
| 185 |
+
assert output.status_code==200
|
| 186 |
+
assert sf.info(io.BytesIO(output.content)).channels==3
|
| 187 |
+
assert c.get(f"/api/v1/projects/{pid}").json()["asset"]["sha256"]==sha
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def test_noise_ui_routes_and_preserve_first_notice(tmp_path):
|
| 191 |
+
with TestClient(create_app(tmp_path/"tmp")) as client:
|
| 192 |
+
html=client.get("/").text
|
| 193 |
+
assert "PRESERVE FIRST" in html and "NOISE-CORE" in html
|
| 194 |
+
js=client.get("/static/app.js").text
|
| 195 |
+
assert "startNoiseScan" in js and "startNoiseRepair" in js
|
| 196 |
+
spec=client.get("/openapi.json").json()["paths"]
|
| 197 |
+
assert "/api/v1/jobs/noise/scan" in spec
|
| 198 |
+
assert "/api/v1/jobs/bass/virtual" in spec
|