Merge pull request #1 from SiliconLanguage/copilot/scaffold-open-asr-model-explorer
Browse files- .gitignore +6 -0
- README.md +228 -2
- backend/Dockerfile +49 -0
- backend/app.py +413 -0
- backend/requirements.txt +13 -0
- docker-compose.yml +61 -0
- frontend/Dockerfile +28 -0
- frontend/index.html +14 -0
- frontend/nginx.conf +42 -0
- frontend/package-lock.json +0 -0
- frontend/package.json +28 -0
- frontend/src/App.jsx +207 -0
- frontend/src/components/AudioRecorder.jsx +114 -0
- frontend/src/components/MetricsDashboard.jsx +63 -0
- frontend/src/components/ModelSelector.jsx +56 -0
- frontend/src/components/TranscriptDisplay.jsx +59 -0
- frontend/src/index.css +456 -0
- frontend/src/main.jsx +10 -0
- frontend/src/services/inferenceRouter.js +187 -0
- frontend/src/workers/webgpu.worker.js +221 -0
- frontend/vite.config.js +24 -0
.gitignore
CHANGED
|
@@ -1,3 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Byte-compiled / optimized / DLL files
|
| 2 |
__pycache__/
|
| 3 |
*.py[codz]
|
|
|
|
| 1 |
+
# Node / frontend
|
| 2 |
+
node_modules/
|
| 3 |
+
frontend/node_modules/
|
| 4 |
+
frontend/dist/
|
| 5 |
+
frontend/.vite/
|
| 6 |
+
|
| 7 |
# Byte-compiled / optimized / DLL files
|
| 8 |
__pycache__/
|
| 9 |
*.py[codz]
|
README.md
CHANGED
|
@@ -1,2 +1,228 @@
|
|
| 1 |
-
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Open-ASR Model Explorer
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: purple
|
| 6 |
+
sdk: docker
|
| 7 |
+
app_port: 8000
|
| 8 |
+
pinned: false
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Open-ASR Model Explorer
|
| 12 |
+
|
| 13 |
+
[](https://huggingface.co/spaces)
|
| 14 |
+
[](https://python.org)
|
| 15 |
+
[](https://fastapi.tiangolo.com)
|
| 16 |
+
[](https://react.dev)
|
| 17 |
+
[](https://vllm.ai)
|
| 18 |
+
|
| 19 |
+
A hybrid inference testbed for evaluating top open-source ASR models (Cohere, Qwen3-ASR, IBM Granite) featuring vLLM server-side routing and transformers.js WebGPU client-side inference.
|
| 20 |
+
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
## Architecture
|
| 24 |
+
|
| 25 |
+
```
|
| 26 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 27 |
+
β Browser (React/Vite) β
|
| 28 |
+
β β
|
| 29 |
+
β ββββββββββββββββ Strategy Router ββββββββββββββββ β
|
| 30 |
+
β β Model Select ββββββββββββββββββββΊ β InferRouter β β
|
| 31 |
+
β ββββββββββββββββ ββββββββ¬ββββββββ β
|
| 32 |
+
β β β
|
| 33 |
+
β ββββββββββββββββββββ΄βββββββ β
|
| 34 |
+
β β β β
|
| 35 |
+
β "WebGPU" in name? else β
|
| 36 |
+
β β β β
|
| 37 |
+
β ββββββββΌβββββββ ββββββββββΌββ β
|
| 38 |
+
β β WebWorker β β fetch() β β
|
| 39 |
+
β β (transforms β β SSE β β
|
| 40 |
+
β β .js ONNX) β ββββββ¬ββββββ β
|
| 41 |
+
β β LocalAgrmt2 β β β
|
| 42 |
+
β ββββββββ¬βββββββ β β
|
| 43 |
+
β β β β
|
| 44 |
+
β ββββββββββββββββββββββββββΌββββββββββββββββββββΌβββββββ β
|
| 45 |
+
β β Metrics Dashboard β β
|
| 46 |
+
β β TTFT Β· ITL Β· RTFx β β
|
| 47 |
+
β βββββββββββββββββββββββββββββββββββββββββββββββββββββ β
|
| 48 |
+
ββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββ
|
| 49 |
+
β HTTP POST (multipart/SSE)
|
| 50 |
+
ββββββββββββΌβββββββββββ
|
| 51 |
+
β FastAPI Backend β
|
| 52 |
+
β β
|
| 53 |
+
β Audio Normaliser β
|
| 54 |
+
β (pad/truncate 30s) β
|
| 55 |
+
β β β
|
| 56 |
+
β ββββββββΌββββββββ β
|
| 57 |
+
β β vLLM Engine β β
|
| 58 |
+
β β chunked β β
|
| 59 |
+
β β prefill β β
|
| 60 |
+
β β max_tokens β β
|
| 61 |
+
β β =2048 β β
|
| 62 |
+
β β gpu_util β β
|
| 63 |
+
β β =0.88 β β
|
| 64 |
+
β ββββββββββββββββ β
|
| 65 |
+
βββββββββββββββββββββββ
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
### Strategy-Based Routing
|
| 69 |
+
|
| 70 |
+
| Model | Execution Mode | Description |
|
| 71 |
+
|---|---|---|
|
| 72 |
+
| `Cohere-transcribe-03-2026` | **Server (vLLM)** | Routes to FastAPI backend |
|
| 73 |
+
| `Qwen3-ASR-1.7B` | **Server (vLLM)** | Routes to FastAPI backend |
|
| 74 |
+
| `ibm-granite/granite-4.0-1b-speech` | **Server (vLLM)** | Routes to FastAPI backend |
|
| 75 |
+
| `Cohere-Transcribe-WebGPU` | **Client (WebGPU)** | Runs in-browser via transformers.js |
|
| 76 |
+
| `Whisper-Large-v3-Turbo-WebGPU` | **Client (WebGPU)** | Whisper Large v3 Turbo in-browser via transformers.js |
|
| 77 |
+
|
| 78 |
+
### WebGPU Client-Side Features
|
| 79 |
+
- **Zero-server transcription** β audio never leaves the browser
|
| 80 |
+
- **Persistent ONNX cache** β model weights cached via the browser Cache API
|
| 81 |
+
- **LocalAgreement-2 streaming** β unconfirmed partial hypotheses are held back until two consecutive passes agree on a prefix
|
| 82 |
+
|
| 83 |
+
### Backend vLLM Configuration
|
| 84 |
+
- **Chunked Prefill** β `enable_chunked_prefill=True` prevents long audio prefills from starving decode steps
|
| 85 |
+
- **Pre-batching normalisation** β all audio padded/truncated to 30 s before entering the scheduler
|
| 86 |
+
- **Resource constraints** β `max_num_batched_tokens=2048`, `gpu_memory_utilization=0.88`
|
| 87 |
+
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
## Project Structure
|
| 91 |
+
|
| 92 |
+
```
|
| 93 |
+
model-explorer-open-asr/
|
| 94 |
+
βββ docker-compose.yml # Full-stack orchestration (backend + frontend)
|
| 95 |
+
βββ backend/
|
| 96 |
+
β βββ app.py # FastAPI application with vLLM integration
|
| 97 |
+
β βββ requirements.txt # Python dependencies
|
| 98 |
+
β βββ Dockerfile # CUDA 12.1 container image
|
| 99 |
+
βββ frontend/
|
| 100 |
+
βββ Dockerfile # Multi-stage Vite build β Nginx serve
|
| 101 |
+
βββ nginx.conf # Nginx: API proxy + SSE streaming + SPA fallback
|
| 102 |
+
βββ index.html
|
| 103 |
+
βββ package.json
|
| 104 |
+
βββ vite.config.js
|
| 105 |
+
βββ src/
|
| 106 |
+
βββ main.jsx
|
| 107 |
+
βββ App.jsx
|
| 108 |
+
βββ index.css
|
| 109 |
+
βββ components/
|
| 110 |
+
β βββ ModelSelector.jsx
|
| 111 |
+
β βββ AudioRecorder.jsx
|
| 112 |
+
β βββ MetricsDashboard.jsx
|
| 113 |
+
β βββ TranscriptDisplay.jsx
|
| 114 |
+
βββ services/
|
| 115 |
+
β βββ inferenceRouter.js # Strategy-based routing logic
|
| 116 |
+
βββ workers/
|
| 117 |
+
βββ webgpu.worker.js # transformers.js + LocalAgreement-2
|
| 118 |
+
```
|
| 119 |
+
|
| 120 |
+
---
|
| 121 |
+
|
| 122 |
+
## Metrics
|
| 123 |
+
|
| 124 |
+
| Metric | Definition |
|
| 125 |
+
|---|---|
|
| 126 |
+
| **TTFT** (Time-to-First-Token) | Time from request submission to the first generated token |
|
| 127 |
+
| **ITL** (Inter-Token Latency) | Mean time between successive tokens during the decode phase |
|
| 128 |
+
| **RTFx** (Real-Time Factor) | `audio_duration / processing_time` β values > 1 indicate faster-than-real-time |
|
| 129 |
+
|
| 130 |
+
---
|
| 131 |
+
|
| 132 |
+
## Local Development
|
| 133 |
+
|
| 134 |
+
### Prerequisites
|
| 135 |
+
- Node.js β₯ 18
|
| 136 |
+
- Python 3.11
|
| 137 |
+
- (Optional) NVIDIA GPU with CUDA 12.1 for vLLM inference
|
| 138 |
+
|
| 139 |
+
### Backend
|
| 140 |
+
|
| 141 |
+
```bash
|
| 142 |
+
cd backend
|
| 143 |
+
python -m venv .venv && source .venv/bin/activate
|
| 144 |
+
pip install -r requirements.txt
|
| 145 |
+
uvicorn app:app --reload --host 0.0.0.0 --port 8000
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
The API will be available at `http://localhost:8000`.
|
| 149 |
+
Swagger docs: `http://localhost:8000/docs`
|
| 150 |
+
|
| 151 |
+
### Frontend
|
| 152 |
+
|
| 153 |
+
```bash
|
| 154 |
+
cd frontend
|
| 155 |
+
npm install
|
| 156 |
+
npm run dev
|
| 157 |
+
```
|
| 158 |
+
|
| 159 |
+
The UI will be available at `http://localhost:5173`.
|
| 160 |
+
API requests are proxied to `http://localhost:8000` via Vite's dev proxy.
|
| 161 |
+
|
| 162 |
+
---
|
| 163 |
+
|
| 164 |
+
## Docker Setup
|
| 165 |
+
|
| 166 |
+
### Backend only
|
| 167 |
+
|
| 168 |
+
```bash
|
| 169 |
+
cd backend
|
| 170 |
+
docker build -t open-asr-backend .
|
| 171 |
+
docker run --gpus all -p 8000:8000 \
|
| 172 |
+
-v $HOME/.cache/huggingface:/hf_cache \
|
| 173 |
+
open-asr-backend
|
| 174 |
+
```
|
| 175 |
+
|
| 176 |
+
### Full stack with Docker Compose
|
| 177 |
+
|
| 178 |
+
```bash
|
| 179 |
+
# From repo root
|
| 180 |
+
docker compose up --build
|
| 181 |
+
```
|
| 182 |
+
|
| 183 |
+
The UI will be available at `http://localhost:3000` and the API at `http://localhost:8000`.
|
| 184 |
+
|
| 185 |
+
---
|
| 186 |
+
|
| 187 |
+
## Deploy to Hugging Face Spaces
|
| 188 |
+
|
| 189 |
+
1. Fork this repository.
|
| 190 |
+
2. Create a new Space at [huggingface.co/new-space](https://huggingface.co/new-space) with the **Docker** SDK.
|
| 191 |
+
3. Set the following Space secrets:
|
| 192 |
+
- `HF_TOKEN` β your Hugging Face token (for gated model downloads)
|
| 193 |
+
4. Push your fork β Spaces will automatically build the Docker image and start the server.
|
| 194 |
+
|
| 195 |
+
[](https://huggingface.co/spaces)
|
| 196 |
+
|
| 197 |
+
---
|
| 198 |
+
|
| 199 |
+
## API Reference
|
| 200 |
+
|
| 201 |
+
### `POST /transcribe`
|
| 202 |
+
Upload audio for full (non-streaming) transcription.
|
| 203 |
+
|
| 204 |
+
| Field | Type | Description |
|
| 205 |
+
|---|---|---|
|
| 206 |
+
| `audio` | `File` | Audio file (wav, mp3, ogg, flac, webm) |
|
| 207 |
+
| `model` | `string` | Model key, e.g. `Qwen3-ASR-1.7B` |
|
| 208 |
+
|
| 209 |
+
Response:
|
| 210 |
+
```json
|
| 211 |
+
{
|
| 212 |
+
"transcript": "Hello, world!",
|
| 213 |
+
"model": "Qwen3-ASR-1.7B",
|
| 214 |
+
"ttft_ms": 123.4,
|
| 215 |
+
"itl_ms": 8.2,
|
| 216 |
+
"rtfx": 4.56
|
| 217 |
+
}
|
| 218 |
+
```
|
| 219 |
+
|
| 220 |
+
### `POST /transcribe/stream`
|
| 221 |
+
Same as above but returns **Server-Sent Events** with token-by-token streaming.
|
| 222 |
+
|
| 223 |
+
### `GET /health`
|
| 224 |
+
Returns `{ "status": "ok", "loaded_models": [...] }`.
|
| 225 |
+
|
| 226 |
+
### `GET /models`
|
| 227 |
+
Returns the list of available server-side model keys.
|
| 228 |
+
|
backend/Dockerfile
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ββ Base image: CUDA 12.1 + cuDNN 8 for PyTorch & vLLM ββββββββββββββββββββββ
|
| 2 |
+
FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
|
| 3 |
+
|
| 4 |
+
LABEL maintainer="Open-ASR Model Explorer"
|
| 5 |
+
LABEL description="FastAPI backend for hybrid ASR inference testbed (vLLM server-side routing)"
|
| 6 |
+
|
| 7 |
+
# ββ System dependencies βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 8 |
+
ENV DEBIAN_FRONTEND=noninteractive
|
| 9 |
+
RUN apt-get update && apt-get install -y --no-install-recommends \
|
| 10 |
+
python3.11 \
|
| 11 |
+
python3.11-dev \
|
| 12 |
+
python3-pip \
|
| 13 |
+
libsndfile1 \
|
| 14 |
+
ffmpeg \
|
| 15 |
+
git \
|
| 16 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 17 |
+
|
| 18 |
+
# Ensure `python` and `pip` resolve to 3.11
|
| 19 |
+
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 \
|
| 20 |
+
&& update-alternatives --install /usr/bin/pip pip /usr/bin/pip3 1
|
| 21 |
+
|
| 22 |
+
# ββ Working directory βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 23 |
+
WORKDIR /app
|
| 24 |
+
|
| 25 |
+
# ββ Install Python dependencies βββββββββββββββββββββββββββββββββββββββββββββββ
|
| 26 |
+
# Copy requirements first to leverage Docker layer caching
|
| 27 |
+
COPY requirements.txt .
|
| 28 |
+
RUN pip install --no-cache-dir --upgrade pip \
|
| 29 |
+
&& pip install --no-cache-dir -r requirements.txt
|
| 30 |
+
|
| 31 |
+
# ββ Copy application source βββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 32 |
+
COPY app.py .
|
| 33 |
+
|
| 34 |
+
# ββ Runtime environment variables βββββββββββββββββββββββββββββββββββββββββββββ
|
| 35 |
+
# vLLM: disable usage statistics ping
|
| 36 |
+
ENV VLLM_NO_USAGE_STATS=1
|
| 37 |
+
# Hugging Face model cache directory (mount a volume here for persistence)
|
| 38 |
+
ENV HF_HOME=/hf_cache
|
| 39 |
+
ENV TRANSFORMERS_CACHE=/hf_cache
|
| 40 |
+
|
| 41 |
+
# ββ Expose FastAPI port βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 42 |
+
EXPOSE 8000
|
| 43 |
+
|
| 44 |
+
# ββ Health check ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 45 |
+
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
|
| 46 |
+
CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"
|
| 47 |
+
|
| 48 |
+
# ββ Start server ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 49 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]
|
backend/app.py
ADDED
|
@@ -0,0 +1,413 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Open-ASR Model Explorer β FastAPI backend
|
| 3 |
+
Handles server-side (vLLM) transcription requests.
|
| 4 |
+
Strategy-based routing:
|
| 5 |
+
- Models with "WebGPU" in the name β handled client-side (transformers.js)
|
| 6 |
+
- All other models β routed here via POST /transcribe
|
| 7 |
+
"""
|
| 8 |
+
|
| 9 |
+
from __future__ import annotations
|
| 10 |
+
|
| 11 |
+
import io
|
| 12 |
+
import time
|
| 13 |
+
import logging
|
| 14 |
+
from contextlib import asynccontextmanager
|
| 15 |
+
from typing import AsyncGenerator
|
| 16 |
+
|
| 17 |
+
import numpy as np
|
| 18 |
+
import soundfile as sf
|
| 19 |
+
import librosa
|
| 20 |
+
import torch
|
| 21 |
+
|
| 22 |
+
from fastapi import FastAPI, File, Form, HTTPException, UploadFile
|
| 23 |
+
from fastapi.middleware.cors import CORSMiddleware
|
| 24 |
+
from fastapi.responses import StreamingResponse
|
| 25 |
+
from pydantic import BaseModel
|
| 26 |
+
|
| 27 |
+
# ---------------------------------------------------------------------------
|
| 28 |
+
# Logging
|
| 29 |
+
# ---------------------------------------------------------------------------
|
| 30 |
+
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
| 31 |
+
logger = logging.getLogger(__name__)
|
| 32 |
+
|
| 33 |
+
# ---------------------------------------------------------------------------
|
| 34 |
+
# Supported server-side models
|
| 35 |
+
# ---------------------------------------------------------------------------
|
| 36 |
+
SUPPORTED_MODELS: dict[str, str] = {
|
| 37 |
+
"Cohere-transcribe-03-2026": "CohereForAI/c4ai-command-r-plus",
|
| 38 |
+
"Qwen3-ASR-1.7B": "Qwen/Qwen3-ASR-1.7B",
|
| 39 |
+
"ibm-granite/granite-4.0-1b-speech": "ibm-granite/granite-4.0-1b-speech",
|
| 40 |
+
}
|
| 41 |
+
|
| 42 |
+
# Target sample rate expected by Whisper-style models
|
| 43 |
+
TARGET_SR = 16_000
|
| 44 |
+
# Pad / truncate all audio to this many samples (30 s at 16 kHz)
|
| 45 |
+
MAX_AUDIO_SAMPLES = TARGET_SR * 30
|
| 46 |
+
|
| 47 |
+
# ---------------------------------------------------------------------------
|
| 48 |
+
# vLLM engine β loaded lazily on first request to keep startup fast in dev
|
| 49 |
+
# ---------------------------------------------------------------------------
|
| 50 |
+
_vllm_engines: dict[str, object] = {}
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
def _get_engine(model_key: str):
|
| 54 |
+
"""Return (or lazily create) the vLLM AsyncLLMEngine for *model_key*."""
|
| 55 |
+
if model_key in _vllm_engines:
|
| 56 |
+
return _vllm_engines[model_key]
|
| 57 |
+
|
| 58 |
+
try:
|
| 59 |
+
from vllm import AsyncEngineArgs, AsyncLLMEngine # type: ignore
|
| 60 |
+
|
| 61 |
+
hf_model = SUPPORTED_MODELS[model_key]
|
| 62 |
+
logger.info("Loading vLLM engine for %s (%s)β¦", model_key, hf_model)
|
| 63 |
+
|
| 64 |
+
engine_args = AsyncEngineArgs(
|
| 65 |
+
model=hf_model,
|
| 66 |
+
# ββ Chunked prefill prevents long audio prefills from starving
|
| 67 |
+
# decode steps of other in-flight requests.
|
| 68 |
+
enable_chunked_prefill=True,
|
| 69 |
+
max_num_batched_tokens=2048,
|
| 70 |
+
# ββ Reserve ample KV-cache space while keeping GPU busy.
|
| 71 |
+
gpu_memory_utilization=0.88,
|
| 72 |
+
# ββ Async streaming for token-by-token delivery.
|
| 73 |
+
disable_log_requests=False,
|
| 74 |
+
)
|
| 75 |
+
engine = AsyncLLMEngine.from_engine_args(engine_args)
|
| 76 |
+
_vllm_engines[model_key] = engine
|
| 77 |
+
logger.info("Engine ready for %s", model_key)
|
| 78 |
+
return engine
|
| 79 |
+
except ImportError:
|
| 80 |
+
logger.warning(
|
| 81 |
+
"vLLM not available β returning mock engine for development."
|
| 82 |
+
)
|
| 83 |
+
return None
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
# ---------------------------------------------------------------------------
|
| 87 |
+
# Audio pre-processing helpers
|
| 88 |
+
# ---------------------------------------------------------------------------
|
| 89 |
+
|
| 90 |
+
def _load_audio_bytes(data: bytes) -> np.ndarray:
|
| 91 |
+
"""Decode audio bytes β mono float32 NumPy array at TARGET_SR."""
|
| 92 |
+
with io.BytesIO(data) as buf:
|
| 93 |
+
waveform, sr = sf.read(buf, dtype="float32", always_2d=False)
|
| 94 |
+
# Resample if necessary
|
| 95 |
+
if sr != TARGET_SR:
|
| 96 |
+
waveform = librosa.resample(waveform, orig_sr=sr, target_sr=TARGET_SR)
|
| 97 |
+
# Convert stereo β mono
|
| 98 |
+
if waveform.ndim == 2:
|
| 99 |
+
waveform = waveform.mean(axis=1)
|
| 100 |
+
return waveform
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
def _pad_or_truncate(waveform: np.ndarray) -> np.ndarray:
|
| 104 |
+
"""
|
| 105 |
+
Pre-batching normalisation: pad (with zeros) or truncate to MAX_AUDIO_SAMPLES.
|
| 106 |
+
This ensures all tensors entering the vLLM scheduler share a uniform shape.
|
| 107 |
+
"""
|
| 108 |
+
if len(waveform) >= MAX_AUDIO_SAMPLES:
|
| 109 |
+
return waveform[:MAX_AUDIO_SAMPLES]
|
| 110 |
+
pad_width = MAX_AUDIO_SAMPLES - len(waveform)
|
| 111 |
+
return np.pad(waveform, (0, pad_width), mode="constant", constant_values=0.0)
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
# ---------------------------------------------------------------------------
|
| 115 |
+
# Response schemas
|
| 116 |
+
# ---------------------------------------------------------------------------
|
| 117 |
+
|
| 118 |
+
class TranscribeResponse(BaseModel):
|
| 119 |
+
transcript: str
|
| 120 |
+
model: str
|
| 121 |
+
# Performance metrics
|
| 122 |
+
ttft_ms: float # Time-to-First-Token (ms)
|
| 123 |
+
itl_ms: float # Mean Inter-Token Latency (ms)
|
| 124 |
+
rtfx: float # Real-Time Factor = audio_duration / processing_time
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
# ---------------------------------------------------------------------------
|
| 128 |
+
# Application lifespan
|
| 129 |
+
# ---------------------------------------------------------------------------
|
| 130 |
+
|
| 131 |
+
@asynccontextmanager
|
| 132 |
+
async def lifespan(_app: FastAPI) -> AsyncGenerator[None, None]:
|
| 133 |
+
logger.info("Open-ASR Model Explorer backend starting up.")
|
| 134 |
+
yield
|
| 135 |
+
logger.info("Open-ASR Model Explorer backend shutting down.")
|
| 136 |
+
_vllm_engines.clear()
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
# ---------------------------------------------------------------------------
|
| 140 |
+
# FastAPI app
|
| 141 |
+
# ---------------------------------------------------------------------------
|
| 142 |
+
|
| 143 |
+
app = FastAPI(
|
| 144 |
+
title="Open-ASR Model Explorer",
|
| 145 |
+
description=(
|
| 146 |
+
"Hybrid inference testbed for evaluating open-source speech-to-text models. "
|
| 147 |
+
"Server-side route uses vLLM with chunked prefill and GPU memory optimisation."
|
| 148 |
+
),
|
| 149 |
+
version="1.0.0",
|
| 150 |
+
lifespan=lifespan,
|
| 151 |
+
)
|
| 152 |
+
|
| 153 |
+
app.add_middleware(
|
| 154 |
+
CORSMiddleware,
|
| 155 |
+
allow_origins=["*"], # tighten for production
|
| 156 |
+
allow_credentials=True,
|
| 157 |
+
allow_methods=["*"],
|
| 158 |
+
allow_headers=["*"],
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
|
| 162 |
+
# ---------------------------------------------------------------------------
|
| 163 |
+
# Health check
|
| 164 |
+
# ---------------------------------------------------------------------------
|
| 165 |
+
|
| 166 |
+
@app.get("/health")
|
| 167 |
+
async def health() -> dict:
|
| 168 |
+
return {"status": "ok", "loaded_models": list(_vllm_engines.keys())}
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
# ---------------------------------------------------------------------------
|
| 172 |
+
# List available server-side models
|
| 173 |
+
# ---------------------------------------------------------------------------
|
| 174 |
+
|
| 175 |
+
@app.get("/models")
|
| 176 |
+
async def list_models() -> dict:
|
| 177 |
+
return {"models": list(SUPPORTED_MODELS.keys())}
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
# ---------------------------------------------------------------------------
|
| 181 |
+
# Main transcription endpoint
|
| 182 |
+
# ---------------------------------------------------------------------------
|
| 183 |
+
|
| 184 |
+
@app.post("/transcribe", response_model=TranscribeResponse)
|
| 185 |
+
async def transcribe(
|
| 186 |
+
audio: UploadFile = File(..., description="Audio file (wav/mp3/ogg/flacβ¦)"),
|
| 187 |
+
model: str = Form(..., description="Model key, e.g. 'Qwen3-ASR-1.7B'"),
|
| 188 |
+
) -> TranscribeResponse:
|
| 189 |
+
"""
|
| 190 |
+
Transcribe *audio* using the selected server-side model via vLLM.
|
| 191 |
+
|
| 192 |
+
Metrics returned
|
| 193 |
+
----------------
|
| 194 |
+
ttft_ms β time from request receipt to first generated token
|
| 195 |
+
itl_ms β mean inter-token latency across the decode phase
|
| 196 |
+
rtfx β audio_duration / total_processing_time (higher is better)
|
| 197 |
+
"""
|
| 198 |
+
if "WebGPU" in model:
|
| 199 |
+
raise HTTPException(
|
| 200 |
+
status_code=400,
|
| 201 |
+
detail="WebGPU models are handled client-side. Do not send them to this endpoint.",
|
| 202 |
+
)
|
| 203 |
+
if model not in SUPPORTED_MODELS:
|
| 204 |
+
raise HTTPException(
|
| 205 |
+
status_code=404,
|
| 206 |
+
detail=f"Unknown model '{model}'. Available: {list(SUPPORTED_MODELS.keys())}",
|
| 207 |
+
)
|
| 208 |
+
|
| 209 |
+
# ββ 1. Decode & normalise audio ββββββββββββββββββββββββββββββββββββββββββ
|
| 210 |
+
raw_bytes = await audio.read()
|
| 211 |
+
try:
|
| 212 |
+
waveform = _load_audio_bytes(raw_bytes)
|
| 213 |
+
except Exception as exc:
|
| 214 |
+
raise HTTPException(status_code=422, detail=f"Cannot decode audio: {exc}") from exc
|
| 215 |
+
|
| 216 |
+
audio_duration_s = len(waveform) / TARGET_SR
|
| 217 |
+
waveform_padded = _pad_or_truncate(waveform)
|
| 218 |
+
|
| 219 |
+
# ββ 2. Attempt vLLM inference ββββββββββββββββββββββββββββββββββββββββββββ
|
| 220 |
+
engine = _get_engine(model)
|
| 221 |
+
request_start = time.perf_counter()
|
| 222 |
+
|
| 223 |
+
if engine is not None:
|
| 224 |
+
transcript, ttft_ms, itl_ms = await _run_vllm(engine, waveform_padded, model)
|
| 225 |
+
else:
|
| 226 |
+
# Development fallback when vLLM / GPU is unavailable
|
| 227 |
+
transcript, ttft_ms, itl_ms = await _mock_transcribe(waveform_padded, model)
|
| 228 |
+
|
| 229 |
+
total_time_s = time.perf_counter() - request_start
|
| 230 |
+
rtfx = audio_duration_s / total_time_s if total_time_s > 0 else 0.0
|
| 231 |
+
|
| 232 |
+
return TranscribeResponse(
|
| 233 |
+
transcript=transcript,
|
| 234 |
+
model=model,
|
| 235 |
+
ttft_ms=round(ttft_ms, 2),
|
| 236 |
+
itl_ms=round(itl_ms, 2),
|
| 237 |
+
rtfx=round(rtfx, 4),
|
| 238 |
+
)
|
| 239 |
+
|
| 240 |
+
|
| 241 |
+
# ---------------------------------------------------------------------------
|
| 242 |
+
# vLLM streaming helper
|
| 243 |
+
# ---------------------------------------------------------------------------
|
| 244 |
+
|
| 245 |
+
async def _run_vllm(
|
| 246 |
+
engine,
|
| 247 |
+
waveform: np.ndarray,
|
| 248 |
+
model_key: str,
|
| 249 |
+
) -> tuple[str, float, float]:
|
| 250 |
+
"""
|
| 251 |
+
Run vLLM inference; return (transcript, ttft_ms, mean_itl_ms).
|
| 252 |
+
|
| 253 |
+
The waveform is serialised as a base64-encoded prompt for models that
|
| 254 |
+
accept audio tokens. For text-only models this path issues a simple
|
| 255 |
+
ASR-formatted text prompt.
|
| 256 |
+
"""
|
| 257 |
+
import asyncio
|
| 258 |
+
from vllm import SamplingParams # type: ignore
|
| 259 |
+
|
| 260 |
+
sampling_params = SamplingParams(temperature=0.0, max_tokens=512)
|
| 261 |
+
|
| 262 |
+
# Minimal prompt β actual audio-token injection depends on model tokeniser
|
| 263 |
+
prompt = f"<|audio_bos|><|AUDIO|><|audio_eos|>Transcribe the speech."
|
| 264 |
+
|
| 265 |
+
request_id = f"asr-{time.time_ns()}"
|
| 266 |
+
token_timestamps: list[float] = []
|
| 267 |
+
first_token_time: float | None = None
|
| 268 |
+
request_start = time.perf_counter()
|
| 269 |
+
|
| 270 |
+
result_generator = engine.generate(prompt, sampling_params, request_id)
|
| 271 |
+
full_text = ""
|
| 272 |
+
|
| 273 |
+
async for request_output in result_generator:
|
| 274 |
+
now = time.perf_counter()
|
| 275 |
+
if first_token_time is None and request_output.outputs:
|
| 276 |
+
first_token_time = now
|
| 277 |
+
token_timestamps.append(now)
|
| 278 |
+
if request_output.outputs:
|
| 279 |
+
full_text = request_output.outputs[0].text
|
| 280 |
+
|
| 281 |
+
ttft_ms = (first_token_time - request_start) * 1000 if first_token_time else 0.0
|
| 282 |
+
if len(token_timestamps) > 1:
|
| 283 |
+
gaps = [
|
| 284 |
+
(token_timestamps[i] - token_timestamps[i - 1]) * 1000
|
| 285 |
+
for i in range(1, len(token_timestamps))
|
| 286 |
+
]
|
| 287 |
+
itl_ms = float(np.mean(gaps))
|
| 288 |
+
else:
|
| 289 |
+
itl_ms = 0.0
|
| 290 |
+
|
| 291 |
+
return full_text, ttft_ms, itl_ms
|
| 292 |
+
|
| 293 |
+
|
| 294 |
+
# ---------------------------------------------------------------------------
|
| 295 |
+
# Mock transcription fallback (development without GPU)
|
| 296 |
+
# ---------------------------------------------------------------------------
|
| 297 |
+
|
| 298 |
+
async def _mock_transcribe(
|
| 299 |
+
waveform: np.ndarray,
|
| 300 |
+
model_key: str,
|
| 301 |
+
) -> tuple[str, float, float]:
|
| 302 |
+
"""Return a placeholder transcript for local development without a GPU."""
|
| 303 |
+
import asyncio
|
| 304 |
+
|
| 305 |
+
await asyncio.sleep(0.1) # simulate small latency
|
| 306 |
+
duration_s = len(waveform) / TARGET_SR
|
| 307 |
+
transcript = (
|
| 308 |
+
f"[Mock transcript β {model_key}] "
|
| 309 |
+
f"Audio duration: {duration_s:.1f}s. "
|
| 310 |
+
"Deploy with GPU and vLLM for real transcription."
|
| 311 |
+
)
|
| 312 |
+
ttft_ms = 42.0
|
| 313 |
+
itl_ms = 8.5
|
| 314 |
+
return transcript, ttft_ms, itl_ms
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
# ---------------------------------------------------------------------------
|
| 318 |
+
# Streaming transcription endpoint (SSE)
|
| 319 |
+
# ---------------------------------------------------------------------------
|
| 320 |
+
|
| 321 |
+
@app.post("/transcribe/stream")
|
| 322 |
+
async def transcribe_stream(
|
| 323 |
+
audio: UploadFile = File(...),
|
| 324 |
+
model: str = Form(...),
|
| 325 |
+
) -> StreamingResponse:
|
| 326 |
+
"""
|
| 327 |
+
Server-Sent Events endpoint that streams tokens as they are generated.
|
| 328 |
+
Each event carries a JSON payload:
|
| 329 |
+
{"token": "...", "ttft_ms": ..., "done": false}
|
| 330 |
+
The final event has "done": true and includes all metrics.
|
| 331 |
+
"""
|
| 332 |
+
if "WebGPU" in model:
|
| 333 |
+
raise HTTPException(status_code=400, detail="WebGPU models run client-side.")
|
| 334 |
+
if model not in SUPPORTED_MODELS:
|
| 335 |
+
raise HTTPException(status_code=404, detail=f"Unknown model '{model}'.")
|
| 336 |
+
|
| 337 |
+
raw_bytes = await audio.read()
|
| 338 |
+
try:
|
| 339 |
+
waveform = _load_audio_bytes(raw_bytes)
|
| 340 |
+
except Exception as exc:
|
| 341 |
+
raise HTTPException(status_code=422, detail=f"Cannot decode audio: {exc}") from exc
|
| 342 |
+
|
| 343 |
+
audio_duration_s = len(waveform) / TARGET_SR
|
| 344 |
+
waveform_padded = _pad_or_truncate(waveform)
|
| 345 |
+
engine = _get_engine(model)
|
| 346 |
+
|
| 347 |
+
async def event_generator() -> AsyncGenerator[str, None]:
|
| 348 |
+
import json
|
| 349 |
+
|
| 350 |
+
request_start = time.perf_counter()
|
| 351 |
+
first_token_time: float | None = None
|
| 352 |
+
token_timestamps: list[float] = []
|
| 353 |
+
full_text = ""
|
| 354 |
+
|
| 355 |
+
if engine is not None:
|
| 356 |
+
from vllm import SamplingParams # type: ignore
|
| 357 |
+
|
| 358 |
+
sampling_params = SamplingParams(temperature=0.0, max_tokens=512)
|
| 359 |
+
prompt = "<|audio_bos|><|AUDIO|><|audio_eos|>Transcribe the speech."
|
| 360 |
+
request_id = f"asr-stream-{time.time_ns()}"
|
| 361 |
+
|
| 362 |
+
async for output in engine.generate(prompt, sampling_params, request_id):
|
| 363 |
+
now = time.perf_counter()
|
| 364 |
+
if first_token_time is None and output.outputs:
|
| 365 |
+
first_token_time = now
|
| 366 |
+
ttft_ms = (first_token_time - request_start) * 1000
|
| 367 |
+
yield f"data: {json.dumps({'token': '', 'ttft_ms': round(ttft_ms, 2), 'done': False})}\n\n"
|
| 368 |
+
token_timestamps.append(now)
|
| 369 |
+
if output.outputs:
|
| 370 |
+
new_text = output.outputs[0].text
|
| 371 |
+
delta = new_text[len(full_text):]
|
| 372 |
+
full_text = new_text
|
| 373 |
+
if delta:
|
| 374 |
+
yield f"data: {json.dumps({'token': delta, 'ttft_ms': None, 'done': False})}\n\n"
|
| 375 |
+
else:
|
| 376 |
+
# Mock streaming
|
| 377 |
+
import asyncio
|
| 378 |
+
|
| 379 |
+
words = (
|
| 380 |
+
f"[Mock β {model}] Audio {audio_duration_s:.1f}s. "
|
| 381 |
+
"No GPU available."
|
| 382 |
+
).split()
|
| 383 |
+
first_token_time = time.perf_counter()
|
| 384 |
+
ttft_ms = (first_token_time - request_start) * 1000
|
| 385 |
+
yield f"data: {json.dumps({'token': '', 'ttft_ms': round(ttft_ms, 2), 'done': False})}\n\n"
|
| 386 |
+
for word in words:
|
| 387 |
+
token_timestamps.append(time.perf_counter())
|
| 388 |
+
full_text += word + " "
|
| 389 |
+
yield f"data: {json.dumps({'token': word + ' ', 'ttft_ms': None, 'done': False})}\n\n"
|
| 390 |
+
await asyncio.sleep(0.05)
|
| 391 |
+
|
| 392 |
+
total_time_s = time.perf_counter() - request_start
|
| 393 |
+
rtfx = audio_duration_s / total_time_s if total_time_s > 0 else 0.0
|
| 394 |
+
if len(token_timestamps) > 1:
|
| 395 |
+
gaps = [
|
| 396 |
+
(token_timestamps[i] - token_timestamps[i - 1]) * 1000
|
| 397 |
+
for i in range(1, len(token_timestamps))
|
| 398 |
+
]
|
| 399 |
+
itl_ms = float(np.mean(gaps))
|
| 400 |
+
else:
|
| 401 |
+
itl_ms = 0.0
|
| 402 |
+
|
| 403 |
+
final_payload = json.dumps({
|
| 404 |
+
"token": "",
|
| 405 |
+
"ttft_ms": None,
|
| 406 |
+
"itl_ms": round(itl_ms, 2),
|
| 407 |
+
"rtfx": round(rtfx, 4),
|
| 408 |
+
"transcript": full_text.strip(),
|
| 409 |
+
"done": True,
|
| 410 |
+
})
|
| 411 |
+
yield f"data: {final_payload}\n\n"
|
| 412 |
+
|
| 413 |
+
return StreamingResponse(event_generator(), media_type="text/event-stream")
|
backend/requirements.txt
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
fastapi==0.120.4
|
| 2 |
+
uvicorn[standard]==0.32.1
|
| 3 |
+
python-multipart==0.0.22
|
| 4 |
+
vllm==0.18.0
|
| 5 |
+
torch==2.6.0
|
| 6 |
+
torchaudio==2.6.0
|
| 7 |
+
numpy==1.26.4
|
| 8 |
+
soundfile==0.12.1
|
| 9 |
+
librosa==0.10.2
|
| 10 |
+
httpx==0.28.1
|
| 11 |
+
pydantic==2.10.4
|
| 12 |
+
pydantic-settings==2.7.0
|
| 13 |
+
starlette==0.49.1
|
docker-compose.yml
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Open-ASR Model Explorer β Docker Compose
|
| 2 |
+
# Usage:
|
| 3 |
+
# docker compose up --build # start both services
|
| 4 |
+
# docker compose up --build backend # backend only
|
| 5 |
+
# docker compose down -v # stop and remove volumes
|
| 6 |
+
#
|
| 7 |
+
# The frontend is served by Nginx on http://localhost:3000.
|
| 8 |
+
# The backend FastAPI API is available directly on http://localhost:8000.
|
| 9 |
+
# Nginx proxies /api/* β http://backend:8000/* so the UI calls /api/β¦ .
|
| 10 |
+
|
| 11 |
+
services:
|
| 12 |
+
|
| 13 |
+
# ββ FastAPI + vLLM backend ββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 14 |
+
backend:
|
| 15 |
+
build:
|
| 16 |
+
context: ./backend
|
| 17 |
+
dockerfile: Dockerfile
|
| 18 |
+
ports:
|
| 19 |
+
- "8000:8000"
|
| 20 |
+
volumes:
|
| 21 |
+
# Persist downloaded HuggingFace model weights across container restarts.
|
| 22 |
+
- hf_cache:/hf_cache
|
| 23 |
+
environment:
|
| 24 |
+
- HF_HOME=/hf_cache
|
| 25 |
+
- TRANSFORMERS_CACHE=/hf_cache
|
| 26 |
+
# Uncomment and set HF_TOKEN if you access gated models on HuggingFace
|
| 27 |
+
# (e.g. Cohere-transcribe-03-2026 or IBM Granite may require acceptance
|
| 28 |
+
# of model terms before download).
|
| 29 |
+
# - HF_TOKEN=${HF_TOKEN}
|
| 30 |
+
# GPU access β requires the NVIDIA Container Toolkit.
|
| 31 |
+
# Remove the `deploy` block entirely if running CPU-only.
|
| 32 |
+
deploy:
|
| 33 |
+
resources:
|
| 34 |
+
reservations:
|
| 35 |
+
devices:
|
| 36 |
+
- driver: nvidia
|
| 37 |
+
count: all
|
| 38 |
+
capabilities: [gpu]
|
| 39 |
+
restart: unless-stopped
|
| 40 |
+
healthcheck:
|
| 41 |
+
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
|
| 42 |
+
interval: 30s
|
| 43 |
+
timeout: 10s
|
| 44 |
+
start_period: 60s
|
| 45 |
+
retries: 3
|
| 46 |
+
|
| 47 |
+
# ββ React / Nginx frontend ββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 48 |
+
frontend:
|
| 49 |
+
build:
|
| 50 |
+
context: ./frontend
|
| 51 |
+
dockerfile: Dockerfile
|
| 52 |
+
ports:
|
| 53 |
+
- "3000:80"
|
| 54 |
+
depends_on:
|
| 55 |
+
backend:
|
| 56 |
+
condition: service_healthy
|
| 57 |
+
restart: unless-stopped
|
| 58 |
+
|
| 59 |
+
volumes:
|
| 60 |
+
# Named volume for HuggingFace model weight cache.
|
| 61 |
+
hf_cache:
|
frontend/Dockerfile
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ββ Stage 1: build the Vite / React app ββββββββββββββββββββββββββββββββββββββ
|
| 2 |
+
FROM node:20-alpine AS builder
|
| 3 |
+
|
| 4 |
+
WORKDIR /app
|
| 5 |
+
|
| 6 |
+
# Install dependencies first to leverage Docker layer caching
|
| 7 |
+
COPY package.json package-lock.json ./
|
| 8 |
+
RUN npm ci --ignore-scripts
|
| 9 |
+
|
| 10 |
+
# Copy source and build
|
| 11 |
+
COPY . .
|
| 12 |
+
RUN npm run build
|
| 13 |
+
|
| 14 |
+
# ββ Stage 2: serve the built assets with Nginx ββββββββββββββββββββββββββββββββ
|
| 15 |
+
FROM nginx:1.27-alpine
|
| 16 |
+
|
| 17 |
+
# Replace the default config with our custom one
|
| 18 |
+
COPY nginx.conf /etc/nginx/conf.d/default.conf
|
| 19 |
+
|
| 20 |
+
# Copy the compiled app
|
| 21 |
+
COPY --from=builder /app/dist /usr/share/nginx/html
|
| 22 |
+
|
| 23 |
+
EXPOSE 80
|
| 24 |
+
|
| 25 |
+
HEALTHCHECK --interval=15s --timeout=5s --start-period=5s --retries=3 \
|
| 26 |
+
CMD wget -qO- http://localhost:80/ || exit 1
|
| 27 |
+
|
| 28 |
+
CMD ["nginx", "-g", "daemon off;"]
|
frontend/index.html
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!DOCTYPE html>
|
| 2 |
+
<html lang="en">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="UTF-8" />
|
| 5 |
+
<link rel="icon" type="image/svg+xml" href="/vite.svg" />
|
| 6 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
| 7 |
+
<title>Open-ASR Model Explorer</title>
|
| 8 |
+
<meta name="description" content="Hybrid inference testbed for evaluating open-source speech-to-text models" />
|
| 9 |
+
</head>
|
| 10 |
+
<body>
|
| 11 |
+
<div id="root"></div>
|
| 12 |
+
<script type="module" src="/src/main.jsx"></script>
|
| 13 |
+
</body>
|
| 14 |
+
</html>
|
frontend/nginx.conf
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
server {
|
| 2 |
+
listen 80;
|
| 3 |
+
server_name _;
|
| 4 |
+
|
| 5 |
+
root /usr/share/nginx/html;
|
| 6 |
+
index index.html;
|
| 7 |
+
|
| 8 |
+
# ββ API proxy β FastAPI backend βββββββββββββββββββββββββββββββββββββββββ
|
| 9 |
+
# Strips the /api prefix before forwarding so the backend routes stay clean.
|
| 10 |
+
location /api/ {
|
| 11 |
+
proxy_pass http://backend:8000/;
|
| 12 |
+
proxy_http_version 1.1;
|
| 13 |
+
|
| 14 |
+
proxy_set_header Host $host;
|
| 15 |
+
proxy_set_header X-Real-IP $remote_addr;
|
| 16 |
+
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
| 17 |
+
proxy_set_header X-Forwarded-Proto $scheme;
|
| 18 |
+
|
| 19 |
+
# SSE / chunked streaming: disable all buffering so tokens reach the
|
| 20 |
+
# browser as soon as the backend writes them.
|
| 21 |
+
proxy_set_header Connection '';
|
| 22 |
+
proxy_buffering off;
|
| 23 |
+
proxy_cache off;
|
| 24 |
+
chunked_transfer_encoding on;
|
| 25 |
+
|
| 26 |
+
# Generous timeouts for long transcription jobs.
|
| 27 |
+
proxy_read_timeout 600s;
|
| 28 |
+
proxy_send_timeout 600s;
|
| 29 |
+
}
|
| 30 |
+
|
| 31 |
+
# ββ Static assets with long-lived cache ββββββββββββββββββββββββββββββββ
|
| 32 |
+
location ~* \.(js|css|wasm|woff2?|ttf|ico|png|svg)$ {
|
| 33 |
+
expires 1y;
|
| 34 |
+
add_header Cache-Control "public, immutable";
|
| 35 |
+
try_files $uri =404;
|
| 36 |
+
}
|
| 37 |
+
|
| 38 |
+
# ββ SPA fallback β all unmatched routes serve index.html βββββββββββββββ
|
| 39 |
+
location / {
|
| 40 |
+
try_files $uri $uri/ /index.html;
|
| 41 |
+
}
|
| 42 |
+
}
|
frontend/package-lock.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
frontend/package.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "open-asr-model-explorer",
|
| 3 |
+
"version": "1.0.0",
|
| 4 |
+
"description": "Hybrid inference testbed for evaluating open-source speech-to-text models",
|
| 5 |
+
"private": true,
|
| 6 |
+
"type": "module",
|
| 7 |
+
"scripts": {
|
| 8 |
+
"dev": "vite",
|
| 9 |
+
"build": "vite build",
|
| 10 |
+
"preview": "vite preview",
|
| 11 |
+
"lint": "eslint src --ext .js,.jsx --report-unused-disable-directives --max-warnings 0"
|
| 12 |
+
},
|
| 13 |
+
"dependencies": {
|
| 14 |
+
"react": "^18.3.1",
|
| 15 |
+
"react-dom": "^18.3.1",
|
| 16 |
+
"@xenova/transformers": "^2.17.2"
|
| 17 |
+
},
|
| 18 |
+
"devDependencies": {
|
| 19 |
+
"@types/react": "^18.3.3",
|
| 20 |
+
"@types/react-dom": "^18.3.0",
|
| 21 |
+
"@vitejs/plugin-react": "^4.3.1",
|
| 22 |
+
"eslint": "^8.57.0",
|
| 23 |
+
"eslint-plugin-react": "^7.34.3",
|
| 24 |
+
"eslint-plugin-react-hooks": "^4.6.2",
|
| 25 |
+
"eslint-plugin-react-refresh": "^0.4.7",
|
| 26 |
+
"vite": "^5.3.4"
|
| 27 |
+
}
|
| 28 |
+
}
|
frontend/src/App.jsx
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* App.jsx
|
| 3 |
+
* Root component for the Open-ASR Model Explorer.
|
| 4 |
+
*
|
| 5 |
+
* Orchestrates:
|
| 6 |
+
* - Model selection (strategy-based routing)
|
| 7 |
+
* - Audio capture / upload
|
| 8 |
+
* - Transcription dispatch via inferenceRouter
|
| 9 |
+
* - Live transcript streaming (LocalAgreement-2 for WebGPU)
|
| 10 |
+
* - Metrics dashboard
|
| 11 |
+
*/
|
| 12 |
+
|
| 13 |
+
import { useState, useCallback, useRef } from 'react';
|
| 14 |
+
import ModelSelector from './components/ModelSelector';
|
| 15 |
+
import AudioRecorder from './components/AudioRecorder';
|
| 16 |
+
import MetricsDashboard from './components/MetricsDashboard';
|
| 17 |
+
import TranscriptDisplay from './components/TranscriptDisplay';
|
| 18 |
+
import { route } from './services/inferenceRouter';
|
| 19 |
+
|
| 20 |
+
export default function App() {
|
| 21 |
+
const [model, setModel] = useState('Cohere-transcribe-03-2026');
|
| 22 |
+
const [audioFile, setAudioFile] = useState(null);
|
| 23 |
+
const [status, setStatus] = useState('idle'); // idle | loading | streaming | done | error
|
| 24 |
+
const [errorMsg, setErrorMsg] = useState(null);
|
| 25 |
+
|
| 26 |
+
// Transcript state
|
| 27 |
+
const [stableText, setStableText] = useState('');
|
| 28 |
+
const [unstableText, setUnstableText] = useState('');
|
| 29 |
+
|
| 30 |
+
// Metrics state
|
| 31 |
+
const [metrics, setMetrics] = useState(null);
|
| 32 |
+
const [transcribeMode, setTranscribeMode] = useState(null);
|
| 33 |
+
|
| 34 |
+
const abortRef = useRef(false);
|
| 35 |
+
|
| 36 |
+
const isRunning = status === 'loading' || status === 'streaming';
|
| 37 |
+
|
| 38 |
+
// ββ Progress callback from inferenceRouter βββββββββββββββββββββββββββββββββ
|
| 39 |
+
const handleProgress = useCallback((data) => {
|
| 40 |
+
if (abortRef.current) return;
|
| 41 |
+
setStatus('streaming');
|
| 42 |
+
|
| 43 |
+
if ('stable' in data) {
|
| 44 |
+
// WebGPU LocalAgreement-2 update
|
| 45 |
+
setStableText(data.stable ?? '');
|
| 46 |
+
setUnstableText(data.unstable ?? '');
|
| 47 |
+
} else if ('token' in data) {
|
| 48 |
+
// Server-side SSE token
|
| 49 |
+
setStableText((prev) => prev + (data.token ?? ''));
|
| 50 |
+
}
|
| 51 |
+
|
| 52 |
+
if (data.ttft_ms != null) {
|
| 53 |
+
setMetrics((prev) => ({ ...prev, ttft_ms: data.ttft_ms }));
|
| 54 |
+
}
|
| 55 |
+
}, []);
|
| 56 |
+
|
| 57 |
+
// ββ Submit handler βββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 58 |
+
async function handleSubmit() {
|
| 59 |
+
if (!audioFile) {
|
| 60 |
+
alert('Please provide audio first (upload a file or use the recorder).');
|
| 61 |
+
return;
|
| 62 |
+
}
|
| 63 |
+
|
| 64 |
+
abortRef.current = false;
|
| 65 |
+
setStatus('loading');
|
| 66 |
+
setErrorMsg(null);
|
| 67 |
+
setStableText('');
|
| 68 |
+
setUnstableText('');
|
| 69 |
+
setMetrics(null);
|
| 70 |
+
setTranscribeMode(null);
|
| 71 |
+
|
| 72 |
+
try {
|
| 73 |
+
const result = await route(model, audioFile, handleProgress);
|
| 74 |
+
|
| 75 |
+
if (abortRef.current) return;
|
| 76 |
+
|
| 77 |
+
setStableText(result.transcript);
|
| 78 |
+
setUnstableText('');
|
| 79 |
+
setMetrics({
|
| 80 |
+
ttft_ms: result.ttft_ms,
|
| 81 |
+
itl_ms: result.itl_ms,
|
| 82 |
+
rtfx: result.rtfx,
|
| 83 |
+
});
|
| 84 |
+
setTranscribeMode(result.mode);
|
| 85 |
+
setStatus('done');
|
| 86 |
+
} catch (err) {
|
| 87 |
+
if (!abortRef.current) {
|
| 88 |
+
setErrorMsg(String(err));
|
| 89 |
+
setStatus('error');
|
| 90 |
+
}
|
| 91 |
+
}
|
| 92 |
+
}
|
| 93 |
+
|
| 94 |
+
function handleStop() {
|
| 95 |
+
abortRef.current = true;
|
| 96 |
+
setStatus('idle');
|
| 97 |
+
}
|
| 98 |
+
|
| 99 |
+
function handleClear() {
|
| 100 |
+
setStableText('');
|
| 101 |
+
setUnstableText('');
|
| 102 |
+
setMetrics(null);
|
| 103 |
+
setTranscribeMode(null);
|
| 104 |
+
setStatus('idle');
|
| 105 |
+
setErrorMsg(null);
|
| 106 |
+
}
|
| 107 |
+
|
| 108 |
+
return (
|
| 109 |
+
<div className="app">
|
| 110 |
+
{/* ββ Header ββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */}
|
| 111 |
+
<header className="app-header">
|
| 112 |
+
<div className="header-title-row">
|
| 113 |
+
<span className="header-icon">π</span>
|
| 114 |
+
<h1 className="header-title">Open-ASR Model Explorer</h1>
|
| 115 |
+
</div>
|
| 116 |
+
<p className="header-subtitle">
|
| 117 |
+
Hybrid inference testbed Β· vLLM server-side & WebGPU client-side
|
| 118 |
+
</p>
|
| 119 |
+
</header>
|
| 120 |
+
|
| 121 |
+
<main className="app-main">
|
| 122 |
+
<div className="card">
|
| 123 |
+
{/* ββ Model selection ββββββββββββββββββββββββββββββββββββββββββ */}
|
| 124 |
+
<ModelSelector value={model} onChange={setModel} disabled={isRunning} />
|
| 125 |
+
|
| 126 |
+
{/* ββ Audio input ββββββββββββββββββββββββββββββββββββββββββββββ */}
|
| 127 |
+
<section className="section">
|
| 128 |
+
<h2 className="section-title">Audio Input</h2>
|
| 129 |
+
<AudioRecorder onAudioReady={setAudioFile} disabled={isRunning} />
|
| 130 |
+
</section>
|
| 131 |
+
|
| 132 |
+
{/* ββ Action buttons βββββββββββββββββββββββββββββββββββββββββββ */}
|
| 133 |
+
<div className="action-row">
|
| 134 |
+
<button
|
| 135 |
+
className="btn btn-primary btn-large"
|
| 136 |
+
onClick={handleSubmit}
|
| 137 |
+
disabled={isRunning || !audioFile}
|
| 138 |
+
>
|
| 139 |
+
{status === 'loading' ? (
|
| 140 |
+
<>
|
| 141 |
+
<span className="spinner-inline" /> Loading modelβ¦
|
| 142 |
+
</>
|
| 143 |
+
) : status === 'streaming' ? (
|
| 144 |
+
<>
|
| 145 |
+
<span className="spinner-inline" /> Transcribingβ¦
|
| 146 |
+
</>
|
| 147 |
+
) : (
|
| 148 |
+
'βΆ Transcribe'
|
| 149 |
+
)}
|
| 150 |
+
</button>
|
| 151 |
+
|
| 152 |
+
{isRunning && (
|
| 153 |
+
<button className="btn btn-secondary" onClick={handleStop}>
|
| 154 |
+
βΉ Stop
|
| 155 |
+
</button>
|
| 156 |
+
)}
|
| 157 |
+
|
| 158 |
+
{(status === 'done' || status === 'error') && (
|
| 159 |
+
<button className="btn btn-ghost" onClick={handleClear}>
|
| 160 |
+
π Clear
|
| 161 |
+
</button>
|
| 162 |
+
)}
|
| 163 |
+
</div>
|
| 164 |
+
</div>
|
| 165 |
+
|
| 166 |
+
{/* ββ Error banner βββββββββββββββββββββββββββββββββββββββββββββββ */}
|
| 167 |
+
{status === 'error' && errorMsg && (
|
| 168 |
+
<div className="error-banner" role="alert">
|
| 169 |
+
<strong>Error:</strong> {errorMsg}
|
| 170 |
+
</div>
|
| 171 |
+
)}
|
| 172 |
+
|
| 173 |
+
{/* ββ Transcript output ββββββββββββββββββββββββββββββββββββββββ */}
|
| 174 |
+
{(stableText || unstableText || isRunning) && (
|
| 175 |
+
<div className="card">
|
| 176 |
+
<TranscriptDisplay
|
| 177 |
+
stable={stableText}
|
| 178 |
+
unstable={unstableText}
|
| 179 |
+
loading={status === 'loading'}
|
| 180 |
+
mode={model.includes('WebGPU') ? 'webgpu' : 'server'}
|
| 181 |
+
/>
|
| 182 |
+
</div>
|
| 183 |
+
)}
|
| 184 |
+
|
| 185 |
+
{/* ββ Metrics dashboard βββββββββββββββββββββββββββββββββββββββ */}
|
| 186 |
+
{(metrics || status === 'done') && (
|
| 187 |
+
<div className="card">
|
| 188 |
+
<MetricsDashboard metrics={metrics} mode={transcribeMode} />
|
| 189 |
+
</div>
|
| 190 |
+
)}
|
| 191 |
+
</main>
|
| 192 |
+
|
| 193 |
+
<footer className="app-footer">
|
| 194 |
+
<p>
|
| 195 |
+
Open-ASR Model Explorer Β·{' '}
|
| 196 |
+
<a
|
| 197 |
+
href="https://huggingface.co/spaces"
|
| 198 |
+
target="_blank"
|
| 199 |
+
rel="noopener noreferrer"
|
| 200 |
+
>
|
| 201 |
+
π€ Hugging Face Spaces
|
| 202 |
+
</a>
|
| 203 |
+
</p>
|
| 204 |
+
</footer>
|
| 205 |
+
</div>
|
| 206 |
+
);
|
| 207 |
+
}
|
frontend/src/components/AudioRecorder.jsx
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* AudioRecorder.jsx
|
| 3 |
+
* Provides two audio input modes:
|
| 4 |
+
* 1. File upload β user selects a local audio file
|
| 5 |
+
* 2. Live record β uses MediaRecorder to capture microphone audio
|
| 6 |
+
*
|
| 7 |
+
* Calls onAudioReady(File) when audio is available.
|
| 8 |
+
*/
|
| 9 |
+
|
| 10 |
+
import { useRef, useState } from 'react';
|
| 11 |
+
|
| 12 |
+
const SUPPORTED_TYPES = ['audio/wav', 'audio/mpeg', 'audio/ogg', 'audio/flac', 'audio/webm'];
|
| 13 |
+
|
| 14 |
+
export default function AudioRecorder({ onAudioReady, disabled }) {
|
| 15 |
+
const [recording, setRecording] = useState(false);
|
| 16 |
+
const [audioUrl, setAudioUrl] = useState(null);
|
| 17 |
+
const [fileName, setFileName] = useState(null);
|
| 18 |
+
const mediaRecorderRef = useRef(null);
|
| 19 |
+
const chunksRef = useRef([]);
|
| 20 |
+
|
| 21 |
+
// ββ File upload ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 22 |
+
function handleFileChange(e) {
|
| 23 |
+
const file = e.target.files?.[0];
|
| 24 |
+
if (!file) return;
|
| 25 |
+
setFileName(file.name);
|
| 26 |
+
setAudioUrl(URL.createObjectURL(file));
|
| 27 |
+
onAudioReady(file);
|
| 28 |
+
}
|
| 29 |
+
|
| 30 |
+
// ββ Microphone recording βββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 31 |
+
async function startRecording() {
|
| 32 |
+
try {
|
| 33 |
+
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
|
| 34 |
+
const mimeType = MediaRecorder.isTypeSupported('audio/webm;codecs=opus')
|
| 35 |
+
? 'audio/webm;codecs=opus'
|
| 36 |
+
: 'audio/webm';
|
| 37 |
+
|
| 38 |
+
const recorder = new MediaRecorder(stream, { mimeType });
|
| 39 |
+
chunksRef.current = [];
|
| 40 |
+
|
| 41 |
+
recorder.addEventListener('dataavailable', (e) => {
|
| 42 |
+
if (e.data.size > 0) chunksRef.current.push(e.data);
|
| 43 |
+
});
|
| 44 |
+
|
| 45 |
+
recorder.addEventListener('stop', () => {
|
| 46 |
+
stream.getTracks().forEach((t) => t.stop());
|
| 47 |
+
const blob = new Blob(chunksRef.current, { type: mimeType });
|
| 48 |
+
const file = new File([blob], 'recording.webm', { type: mimeType });
|
| 49 |
+
const url = URL.createObjectURL(blob);
|
| 50 |
+
setAudioUrl(url);
|
| 51 |
+
setFileName('recording.webm');
|
| 52 |
+
onAudioReady(file);
|
| 53 |
+
});
|
| 54 |
+
|
| 55 |
+
recorder.start(100); // collect data every 100 ms
|
| 56 |
+
mediaRecorderRef.current = recorder;
|
| 57 |
+
setRecording(true);
|
| 58 |
+
} catch (err) {
|
| 59 |
+
console.error('Microphone access denied:', err);
|
| 60 |
+
alert('Could not access microphone. Please allow microphone permissions.');
|
| 61 |
+
}
|
| 62 |
+
}
|
| 63 |
+
|
| 64 |
+
function stopRecording() {
|
| 65 |
+
mediaRecorderRef.current?.stop();
|
| 66 |
+
setRecording(false);
|
| 67 |
+
}
|
| 68 |
+
|
| 69 |
+
return (
|
| 70 |
+
<div className="audio-recorder">
|
| 71 |
+
<div className="recorder-row">
|
| 72 |
+
{/* File upload */}
|
| 73 |
+
<label className="btn btn-secondary" title="Upload an audio file">
|
| 74 |
+
π Upload Audio
|
| 75 |
+
<input
|
| 76 |
+
type="file"
|
| 77 |
+
accept={SUPPORTED_TYPES.join(',')}
|
| 78 |
+
onChange={handleFileChange}
|
| 79 |
+
disabled={disabled || recording}
|
| 80 |
+
style={{ display: 'none' }}
|
| 81 |
+
/>
|
| 82 |
+
</label>
|
| 83 |
+
|
| 84 |
+
{/* Record button */}
|
| 85 |
+
{recording ? (
|
| 86 |
+
<button className="btn btn-danger" onClick={stopRecording} disabled={disabled}>
|
| 87 |
+
βΉ Stop Recording
|
| 88 |
+
</button>
|
| 89 |
+
) : (
|
| 90 |
+
<button className="btn btn-primary" onClick={startRecording} disabled={disabled}>
|
| 91 |
+
π Record
|
| 92 |
+
</button>
|
| 93 |
+
)}
|
| 94 |
+
</div>
|
| 95 |
+
|
| 96 |
+
{/* Filename display */}
|
| 97 |
+
{fileName && (
|
| 98 |
+
<p className="file-name" title={fileName}>
|
| 99 |
+
π {fileName}
|
| 100 |
+
</p>
|
| 101 |
+
)}
|
| 102 |
+
|
| 103 |
+
{/* Playback β only render audio element if URL is a safe blob: URL */}
|
| 104 |
+
{audioUrl && audioUrl.startsWith('blob:') && (
|
| 105 |
+
<audio
|
| 106 |
+
className="audio-player"
|
| 107 |
+
controls
|
| 108 |
+
src={audioUrl}
|
| 109 |
+
key={audioUrl}
|
| 110 |
+
/>
|
| 111 |
+
)}
|
| 112 |
+
</div>
|
| 113 |
+
);
|
| 114 |
+
}
|
frontend/src/components/MetricsDashboard.jsx
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* MetricsDashboard.jsx
|
| 3 |
+
* Displays the three core performance metrics after each transcription run:
|
| 4 |
+
*
|
| 5 |
+
* TTFT Time-to-First-Token β latency from request to first generated token (ms)
|
| 6 |
+
* ITL Inter-Token Latency β mean time between tokens during the decode phase (ms)
|
| 7 |
+
* RTFx Real-Time Factor β audio_duration / processing_time (higher = faster)
|
| 8 |
+
*/
|
| 9 |
+
|
| 10 |
+
function MetricCard({ label, value, unit, description, highlight }) {
|
| 11 |
+
return (
|
| 12 |
+
<div className={`metric-card ${highlight ? 'metric-card--highlight' : ''}`} title={description}>
|
| 13 |
+
<span className="metric-label">{label}</span>
|
| 14 |
+
<span className="metric-value">
|
| 15 |
+
{value != null ? value : 'β'}
|
| 16 |
+
{value != null && <span className="metric-unit">{unit}</span>}
|
| 17 |
+
</span>
|
| 18 |
+
<span className="metric-desc">{description}</span>
|
| 19 |
+
</div>
|
| 20 |
+
);
|
| 21 |
+
}
|
| 22 |
+
|
| 23 |
+
export default function MetricsDashboard({ metrics, mode }) {
|
| 24 |
+
const { ttft_ms, itl_ms, rtfx } = metrics ?? {};
|
| 25 |
+
|
| 26 |
+
return (
|
| 27 |
+
<div className="metrics-dashboard">
|
| 28 |
+
<h3 className="metrics-title">
|
| 29 |
+
Performance Metrics
|
| 30 |
+
{mode && (
|
| 31 |
+
<span
|
| 32 |
+
className="metrics-mode-badge"
|
| 33 |
+
style={{ backgroundColor: mode === 'webgpu' ? '#059669' : '#4f46e5' }}
|
| 34 |
+
>
|
| 35 |
+
{mode === 'webgpu' ? 'WebGPU' : 'vLLM'}
|
| 36 |
+
</span>
|
| 37 |
+
)}
|
| 38 |
+
</h3>
|
| 39 |
+
<div className="metrics-grid">
|
| 40 |
+
<MetricCard
|
| 41 |
+
label="TTFT"
|
| 42 |
+
value={ttft_ms != null ? ttft_ms.toFixed(1) : null}
|
| 43 |
+
unit=" ms"
|
| 44 |
+
description="Time-to-First-Token: latency from request submission to the first generated token"
|
| 45 |
+
highlight={ttft_ms != null && ttft_ms < 200}
|
| 46 |
+
/>
|
| 47 |
+
<MetricCard
|
| 48 |
+
label="ITL"
|
| 49 |
+
value={itl_ms != null ? itl_ms.toFixed(1) : null}
|
| 50 |
+
unit=" ms"
|
| 51 |
+
description="Inter-Token Latency: mean time between successive tokens during the decode phase"
|
| 52 |
+
/>
|
| 53 |
+
<MetricCard
|
| 54 |
+
label="RTFx"
|
| 55 |
+
value={rtfx != null ? rtfx.toFixed(2) : null}
|
| 56 |
+
unit="Γ"
|
| 57 |
+
description="Real-Time Factor: audio duration Γ· processing time (>1.0 = faster than real-time)"
|
| 58 |
+
highlight={rtfx != null && rtfx > 1}
|
| 59 |
+
/>
|
| 60 |
+
</div>
|
| 61 |
+
</div>
|
| 62 |
+
);
|
| 63 |
+
}
|
frontend/src/components/ModelSelector.jsx
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* ModelSelector.jsx
|
| 3 |
+
* Dropdown for choosing the ASR model.
|
| 4 |
+
* Models containing "WebGPU" are tagged as "Client-Side (WebGPU)";
|
| 5 |
+
* others are tagged as "Server-Side (vLLM)".
|
| 6 |
+
*/
|
| 7 |
+
|
| 8 |
+
const MODELS = [
|
| 9 |
+
{ id: 'Cohere-transcribe-03-2026', label: 'Cohere Transcribe 03-2026', mode: 'server' },
|
| 10 |
+
{ id: 'Qwen3-ASR-1.7B', label: 'Qwen3-ASR 1.7B', mode: 'server' },
|
| 11 |
+
{ id: 'ibm-granite/granite-4.0-1b-speech', label: 'IBM Granite 4.0 1B Speech', mode: 'server' },
|
| 12 |
+
{ id: 'Cohere-Transcribe-WebGPU', label: 'Cohere Transcribe (WebGPU)', mode: 'webgpu' },
|
| 13 |
+
{ id: 'Whisper-Large-v3-Turbo-WebGPU', label: 'Whisper Large v3 Turbo (WebGPU)', mode: 'webgpu' },
|
| 14 |
+
];
|
| 15 |
+
|
| 16 |
+
const BADGE = {
|
| 17 |
+
server: { label: 'vLLM Β· Server-Side', color: '#4f46e5' },
|
| 18 |
+
webgpu: { label: 'WebGPU Β· Client-Side', color: '#059669' },
|
| 19 |
+
};
|
| 20 |
+
|
| 21 |
+
export default function ModelSelector({ value, onChange, disabled }) {
|
| 22 |
+
const selected = MODELS.find((m) => m.id === value) ?? MODELS[0];
|
| 23 |
+
const badge = BADGE[selected.mode];
|
| 24 |
+
|
| 25 |
+
return (
|
| 26 |
+
<div className="model-selector">
|
| 27 |
+
<label htmlFor="model-select" className="label">
|
| 28 |
+
Model
|
| 29 |
+
</label>
|
| 30 |
+
<div className="select-row">
|
| 31 |
+
<select
|
| 32 |
+
id="model-select"
|
| 33 |
+
value={value}
|
| 34 |
+
onChange={(e) => onChange(e.target.value)}
|
| 35 |
+
disabled={disabled}
|
| 36 |
+
className="select"
|
| 37 |
+
>
|
| 38 |
+
{MODELS.map((m) => (
|
| 39 |
+
<option key={m.id} value={m.id}>
|
| 40 |
+
{m.label}
|
| 41 |
+
</option>
|
| 42 |
+
))}
|
| 43 |
+
</select>
|
| 44 |
+
<span
|
| 45 |
+
className="badge"
|
| 46 |
+
style={{ backgroundColor: badge.color }}
|
| 47 |
+
title={selected.mode === 'webgpu' ? 'Runs entirely in the browser β no audio leaves your device' : 'Routes audio to the FastAPI/vLLM backend'}
|
| 48 |
+
>
|
| 49 |
+
{badge.label}
|
| 50 |
+
</span>
|
| 51 |
+
</div>
|
| 52 |
+
</div>
|
| 53 |
+
);
|
| 54 |
+
}
|
| 55 |
+
|
| 56 |
+
export { MODELS };
|
frontend/src/components/TranscriptDisplay.jsx
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* TranscriptDisplay.jsx
|
| 3 |
+
* Shows the live and final transcription output.
|
| 4 |
+
*
|
| 5 |
+
* During streaming:
|
| 6 |
+
* - `stable` text is rendered normally
|
| 7 |
+
* - `unstable` text is rendered dimmed/italic (LocalAgreement-2 unconfirmed prefix)
|
| 8 |
+
*
|
| 9 |
+
* Props:
|
| 10 |
+
* stable {string} β confirmed transcript text
|
| 11 |
+
* unstable {string} β pending / unconfirmed suffix
|
| 12 |
+
* loading {bool} β show a spinner while waiting for the first token
|
| 13 |
+
* mode {string} β 'webgpu' | 'server'
|
| 14 |
+
*/
|
| 15 |
+
|
| 16 |
+
export default function TranscriptDisplay({ stable, unstable, loading, mode }) {
|
| 17 |
+
const isEmpty = !stable && !unstable && !loading;
|
| 18 |
+
|
| 19 |
+
return (
|
| 20 |
+
<div className="transcript-display">
|
| 21 |
+
<div className="transcript-header">
|
| 22 |
+
<span className="transcript-title">Transcript</span>
|
| 23 |
+
{mode && (
|
| 24 |
+
<span className="transcript-mode">
|
| 25 |
+
{mode === 'webgpu' ? 'π Local (WebGPU)' : 'βοΈ Server (vLLM)'}
|
| 26 |
+
</span>
|
| 27 |
+
)}
|
| 28 |
+
</div>
|
| 29 |
+
|
| 30 |
+
<div className="transcript-body" aria-live="polite" aria-label="Transcription output">
|
| 31 |
+
{loading && !stable && !unstable && (
|
| 32 |
+
<span className="transcript-loading">
|
| 33 |
+
<span className="spinner" aria-hidden="true" />
|
| 34 |
+
Waiting for first tokenβ¦
|
| 35 |
+
</span>
|
| 36 |
+
)}
|
| 37 |
+
|
| 38 |
+
{isEmpty && !loading && (
|
| 39 |
+
<span className="transcript-placeholder">
|
| 40 |
+
Transcription will appear here after you submit audio.
|
| 41 |
+
</span>
|
| 42 |
+
)}
|
| 43 |
+
|
| 44 |
+
{/* Stable (confirmed) text */}
|
| 45 |
+
{stable && <span className="transcript-stable">{stable}</span>}
|
| 46 |
+
|
| 47 |
+
{/* Unstable (unconfirmed) text β LocalAgreement-2 pending prefix */}
|
| 48 |
+
{unstable && (
|
| 49 |
+
<span
|
| 50 |
+
className="transcript-unstable"
|
| 51 |
+
title="Partial hypothesis β not yet confirmed by LocalAgreement-2"
|
| 52 |
+
>
|
| 53 |
+
{unstable}
|
| 54 |
+
</span>
|
| 55 |
+
)}
|
| 56 |
+
</div>
|
| 57 |
+
</div>
|
| 58 |
+
);
|
| 59 |
+
}
|
frontend/src/index.css
ADDED
|
@@ -0,0 +1,456 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/* βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 2 |
+
Open-ASR Model Explorer β Global Styles
|
| 3 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 4 |
+
|
| 5 |
+
/* ββ Reset / base ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 6 |
+
*, *::before, *::after {
|
| 7 |
+
box-sizing: border-box;
|
| 8 |
+
margin: 0;
|
| 9 |
+
padding: 0;
|
| 10 |
+
}
|
| 11 |
+
|
| 12 |
+
:root {
|
| 13 |
+
--color-bg: #0f172a;
|
| 14 |
+
--color-surface: #1e293b;
|
| 15 |
+
--color-border: #334155;
|
| 16 |
+
--color-text: #f1f5f9;
|
| 17 |
+
--color-text-muted: #94a3b8;
|
| 18 |
+
--color-primary: #6366f1;
|
| 19 |
+
--color-primary-hover: #4f46e5;
|
| 20 |
+
--color-success: #10b981;
|
| 21 |
+
--color-danger: #ef4444;
|
| 22 |
+
--color-warning: #f59e0b;
|
| 23 |
+
--radius: 0.75rem;
|
| 24 |
+
--radius-sm: 0.375rem;
|
| 25 |
+
--shadow: 0 4px 24px rgba(0,0,0,0.4);
|
| 26 |
+
font-size: 16px;
|
| 27 |
+
}
|
| 28 |
+
|
| 29 |
+
body {
|
| 30 |
+
font-family: 'Inter', 'Segoe UI', system-ui, -apple-system, sans-serif;
|
| 31 |
+
background: var(--color-bg);
|
| 32 |
+
color: var(--color-text);
|
| 33 |
+
min-height: 100vh;
|
| 34 |
+
line-height: 1.6;
|
| 35 |
+
}
|
| 36 |
+
|
| 37 |
+
/* ββ App shell βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 38 |
+
.app {
|
| 39 |
+
display: flex;
|
| 40 |
+
flex-direction: column;
|
| 41 |
+
min-height: 100vh;
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
.app-header {
|
| 45 |
+
background: linear-gradient(135deg, #1e1b4b 0%, #0f172a 100%);
|
| 46 |
+
border-bottom: 1px solid var(--color-border);
|
| 47 |
+
padding: 2rem 1.5rem 1.5rem;
|
| 48 |
+
text-align: center;
|
| 49 |
+
}
|
| 50 |
+
|
| 51 |
+
.header-title-row {
|
| 52 |
+
display: flex;
|
| 53 |
+
align-items: center;
|
| 54 |
+
justify-content: center;
|
| 55 |
+
gap: 0.75rem;
|
| 56 |
+
margin-bottom: 0.5rem;
|
| 57 |
+
}
|
| 58 |
+
|
| 59 |
+
.header-icon {
|
| 60 |
+
font-size: 2rem;
|
| 61 |
+
}
|
| 62 |
+
|
| 63 |
+
.header-title {
|
| 64 |
+
font-size: 1.875rem;
|
| 65 |
+
font-weight: 700;
|
| 66 |
+
background: linear-gradient(90deg, #a5b4fc, #818cf8);
|
| 67 |
+
-webkit-background-clip: text;
|
| 68 |
+
-webkit-text-fill-color: transparent;
|
| 69 |
+
background-clip: text;
|
| 70 |
+
}
|
| 71 |
+
|
| 72 |
+
.header-subtitle {
|
| 73 |
+
color: var(--color-text-muted);
|
| 74 |
+
font-size: 0.9rem;
|
| 75 |
+
}
|
| 76 |
+
|
| 77 |
+
.app-main {
|
| 78 |
+
flex: 1;
|
| 79 |
+
max-width: 860px;
|
| 80 |
+
width: 100%;
|
| 81 |
+
margin: 2rem auto;
|
| 82 |
+
padding: 0 1rem;
|
| 83 |
+
display: flex;
|
| 84 |
+
flex-direction: column;
|
| 85 |
+
gap: 1.5rem;
|
| 86 |
+
}
|
| 87 |
+
|
| 88 |
+
.app-footer {
|
| 89 |
+
text-align: center;
|
| 90 |
+
padding: 1.5rem;
|
| 91 |
+
color: var(--color-text-muted);
|
| 92 |
+
font-size: 0.85rem;
|
| 93 |
+
border-top: 1px solid var(--color-border);
|
| 94 |
+
}
|
| 95 |
+
|
| 96 |
+
.app-footer a {
|
| 97 |
+
color: #818cf8;
|
| 98 |
+
text-decoration: none;
|
| 99 |
+
}
|
| 100 |
+
|
| 101 |
+
.app-footer a:hover {
|
| 102 |
+
text-decoration: underline;
|
| 103 |
+
}
|
| 104 |
+
|
| 105 |
+
/* ββ Card ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 106 |
+
.card {
|
| 107 |
+
background: var(--color-surface);
|
| 108 |
+
border: 1px solid var(--color-border);
|
| 109 |
+
border-radius: var(--radius);
|
| 110 |
+
padding: 1.5rem;
|
| 111 |
+
box-shadow: var(--shadow);
|
| 112 |
+
display: flex;
|
| 113 |
+
flex-direction: column;
|
| 114 |
+
gap: 1.25rem;
|
| 115 |
+
}
|
| 116 |
+
|
| 117 |
+
/* ββ Section βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 118 |
+
.section {
|
| 119 |
+
display: flex;
|
| 120 |
+
flex-direction: column;
|
| 121 |
+
gap: 0.75rem;
|
| 122 |
+
}
|
| 123 |
+
|
| 124 |
+
.section-title {
|
| 125 |
+
font-size: 0.875rem;
|
| 126 |
+
font-weight: 600;
|
| 127 |
+
text-transform: uppercase;
|
| 128 |
+
letter-spacing: 0.05em;
|
| 129 |
+
color: var(--color-text-muted);
|
| 130 |
+
}
|
| 131 |
+
|
| 132 |
+
/* ββ Labels ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 133 |
+
.label {
|
| 134 |
+
font-size: 0.875rem;
|
| 135 |
+
font-weight: 500;
|
| 136 |
+
color: var(--color-text-muted);
|
| 137 |
+
display: block;
|
| 138 |
+
margin-bottom: 0.25rem;
|
| 139 |
+
}
|
| 140 |
+
|
| 141 |
+
/* ββ Buttons βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 142 |
+
.btn {
|
| 143 |
+
display: inline-flex;
|
| 144 |
+
align-items: center;
|
| 145 |
+
justify-content: center;
|
| 146 |
+
gap: 0.5rem;
|
| 147 |
+
padding: 0.5rem 1.25rem;
|
| 148 |
+
border-radius: var(--radius-sm);
|
| 149 |
+
border: none;
|
| 150 |
+
font-size: 0.9rem;
|
| 151 |
+
font-weight: 500;
|
| 152 |
+
cursor: pointer;
|
| 153 |
+
transition: background 0.15s, transform 0.1s;
|
| 154 |
+
user-select: none;
|
| 155 |
+
}
|
| 156 |
+
|
| 157 |
+
.btn:disabled {
|
| 158 |
+
opacity: 0.5;
|
| 159 |
+
cursor: not-allowed;
|
| 160 |
+
transform: none !important;
|
| 161 |
+
}
|
| 162 |
+
|
| 163 |
+
.btn:not(:disabled):hover {
|
| 164 |
+
transform: translateY(-1px);
|
| 165 |
+
}
|
| 166 |
+
|
| 167 |
+
.btn-primary {
|
| 168 |
+
background: var(--color-primary);
|
| 169 |
+
color: #fff;
|
| 170 |
+
}
|
| 171 |
+
|
| 172 |
+
.btn-primary:not(:disabled):hover {
|
| 173 |
+
background: var(--color-primary-hover);
|
| 174 |
+
}
|
| 175 |
+
|
| 176 |
+
.btn-secondary {
|
| 177 |
+
background: var(--color-border);
|
| 178 |
+
color: var(--color-text);
|
| 179 |
+
}
|
| 180 |
+
|
| 181 |
+
.btn-secondary:not(:disabled):hover {
|
| 182 |
+
background: #475569;
|
| 183 |
+
}
|
| 184 |
+
|
| 185 |
+
.btn-danger {
|
| 186 |
+
background: var(--color-danger);
|
| 187 |
+
color: #fff;
|
| 188 |
+
}
|
| 189 |
+
|
| 190 |
+
.btn-ghost {
|
| 191 |
+
background: transparent;
|
| 192 |
+
color: var(--color-text-muted);
|
| 193 |
+
border: 1px solid var(--color-border);
|
| 194 |
+
}
|
| 195 |
+
|
| 196 |
+
.btn-ghost:not(:disabled):hover {
|
| 197 |
+
background: var(--color-surface);
|
| 198 |
+
color: var(--color-text);
|
| 199 |
+
}
|
| 200 |
+
|
| 201 |
+
.btn-large {
|
| 202 |
+
padding: 0.75rem 2rem;
|
| 203 |
+
font-size: 1rem;
|
| 204 |
+
}
|
| 205 |
+
|
| 206 |
+
/* ββ Action row ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 207 |
+
.action-row {
|
| 208 |
+
display: flex;
|
| 209 |
+
gap: 0.75rem;
|
| 210 |
+
flex-wrap: wrap;
|
| 211 |
+
}
|
| 212 |
+
|
| 213 |
+
/* ββ ModelSelector βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 214 |
+
.model-selector {
|
| 215 |
+
display: flex;
|
| 216 |
+
flex-direction: column;
|
| 217 |
+
gap: 0.375rem;
|
| 218 |
+
}
|
| 219 |
+
|
| 220 |
+
.select-row {
|
| 221 |
+
display: flex;
|
| 222 |
+
align-items: center;
|
| 223 |
+
gap: 0.75rem;
|
| 224 |
+
flex-wrap: wrap;
|
| 225 |
+
}
|
| 226 |
+
|
| 227 |
+
.select {
|
| 228 |
+
flex: 1;
|
| 229 |
+
min-width: 200px;
|
| 230 |
+
background: var(--color-bg);
|
| 231 |
+
border: 1px solid var(--color-border);
|
| 232 |
+
border-radius: var(--radius-sm);
|
| 233 |
+
color: var(--color-text);
|
| 234 |
+
padding: 0.5rem 0.75rem;
|
| 235 |
+
font-size: 0.95rem;
|
| 236 |
+
cursor: pointer;
|
| 237 |
+
outline: none;
|
| 238 |
+
transition: border-color 0.15s;
|
| 239 |
+
}
|
| 240 |
+
|
| 241 |
+
.select:focus {
|
| 242 |
+
border-color: var(--color-primary);
|
| 243 |
+
}
|
| 244 |
+
|
| 245 |
+
.badge {
|
| 246 |
+
display: inline-flex;
|
| 247 |
+
align-items: center;
|
| 248 |
+
padding: 0.25rem 0.75rem;
|
| 249 |
+
border-radius: 9999px;
|
| 250 |
+
font-size: 0.75rem;
|
| 251 |
+
font-weight: 600;
|
| 252 |
+
color: #fff;
|
| 253 |
+
white-space: nowrap;
|
| 254 |
+
cursor: help;
|
| 255 |
+
}
|
| 256 |
+
|
| 257 |
+
/* ββ AudioRecorder βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 258 |
+
.audio-recorder {
|
| 259 |
+
display: flex;
|
| 260 |
+
flex-direction: column;
|
| 261 |
+
gap: 0.75rem;
|
| 262 |
+
}
|
| 263 |
+
|
| 264 |
+
.recorder-row {
|
| 265 |
+
display: flex;
|
| 266 |
+
gap: 0.75rem;
|
| 267 |
+
flex-wrap: wrap;
|
| 268 |
+
}
|
| 269 |
+
|
| 270 |
+
.file-name {
|
| 271 |
+
font-size: 0.8rem;
|
| 272 |
+
color: var(--color-text-muted);
|
| 273 |
+
overflow: hidden;
|
| 274 |
+
text-overflow: ellipsis;
|
| 275 |
+
white-space: nowrap;
|
| 276 |
+
max-width: 100%;
|
| 277 |
+
}
|
| 278 |
+
|
| 279 |
+
.audio-player {
|
| 280 |
+
width: 100%;
|
| 281 |
+
border-radius: var(--radius-sm);
|
| 282 |
+
accent-color: var(--color-primary);
|
| 283 |
+
}
|
| 284 |
+
|
| 285 |
+
/* ββ TranscriptDisplay βββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 286 |
+
.transcript-display {
|
| 287 |
+
display: flex;
|
| 288 |
+
flex-direction: column;
|
| 289 |
+
gap: 0.5rem;
|
| 290 |
+
}
|
| 291 |
+
|
| 292 |
+
.transcript-header {
|
| 293 |
+
display: flex;
|
| 294 |
+
align-items: center;
|
| 295 |
+
justify-content: space-between;
|
| 296 |
+
gap: 0.5rem;
|
| 297 |
+
}
|
| 298 |
+
|
| 299 |
+
.transcript-title {
|
| 300 |
+
font-size: 0.875rem;
|
| 301 |
+
font-weight: 600;
|
| 302 |
+
text-transform: uppercase;
|
| 303 |
+
letter-spacing: 0.05em;
|
| 304 |
+
color: var(--color-text-muted);
|
| 305 |
+
}
|
| 306 |
+
|
| 307 |
+
.transcript-mode {
|
| 308 |
+
font-size: 0.75rem;
|
| 309 |
+
color: var(--color-text-muted);
|
| 310 |
+
}
|
| 311 |
+
|
| 312 |
+
.transcript-body {
|
| 313 |
+
background: var(--color-bg);
|
| 314 |
+
border: 1px solid var(--color-border);
|
| 315 |
+
border-radius: var(--radius-sm);
|
| 316 |
+
padding: 1rem;
|
| 317 |
+
min-height: 120px;
|
| 318 |
+
font-size: 1rem;
|
| 319 |
+
line-height: 1.7;
|
| 320 |
+
word-break: break-word;
|
| 321 |
+
}
|
| 322 |
+
|
| 323 |
+
.transcript-stable {
|
| 324 |
+
color: var(--color-text);
|
| 325 |
+
}
|
| 326 |
+
|
| 327 |
+
.transcript-unstable {
|
| 328 |
+
color: var(--color-text-muted);
|
| 329 |
+
font-style: italic;
|
| 330 |
+
}
|
| 331 |
+
|
| 332 |
+
.transcript-placeholder {
|
| 333 |
+
color: #475569;
|
| 334 |
+
font-style: italic;
|
| 335 |
+
}
|
| 336 |
+
|
| 337 |
+
.transcript-loading {
|
| 338 |
+
display: inline-flex;
|
| 339 |
+
align-items: center;
|
| 340 |
+
gap: 0.5rem;
|
| 341 |
+
color: var(--color-text-muted);
|
| 342 |
+
}
|
| 343 |
+
|
| 344 |
+
/* ββ MetricsDashboard ββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 345 |
+
.metrics-dashboard {
|
| 346 |
+
display: flex;
|
| 347 |
+
flex-direction: column;
|
| 348 |
+
gap: 1rem;
|
| 349 |
+
}
|
| 350 |
+
|
| 351 |
+
.metrics-title {
|
| 352 |
+
font-size: 1rem;
|
| 353 |
+
font-weight: 600;
|
| 354 |
+
display: flex;
|
| 355 |
+
align-items: center;
|
| 356 |
+
gap: 0.5rem;
|
| 357 |
+
}
|
| 358 |
+
|
| 359 |
+
.metrics-mode-badge {
|
| 360 |
+
font-size: 0.7rem;
|
| 361 |
+
padding: 0.2rem 0.6rem;
|
| 362 |
+
border-radius: 9999px;
|
| 363 |
+
color: #fff;
|
| 364 |
+
font-weight: 700;
|
| 365 |
+
}
|
| 366 |
+
|
| 367 |
+
.metrics-grid {
|
| 368 |
+
display: grid;
|
| 369 |
+
grid-template-columns: repeat(3, 1fr);
|
| 370 |
+
gap: 1rem;
|
| 371 |
+
}
|
| 372 |
+
|
| 373 |
+
@media (max-width: 600px) {
|
| 374 |
+
.metrics-grid {
|
| 375 |
+
grid-template-columns: 1fr;
|
| 376 |
+
}
|
| 377 |
+
}
|
| 378 |
+
|
| 379 |
+
.metric-card {
|
| 380 |
+
background: var(--color-bg);
|
| 381 |
+
border: 1px solid var(--color-border);
|
| 382 |
+
border-radius: var(--radius-sm);
|
| 383 |
+
padding: 1rem;
|
| 384 |
+
display: flex;
|
| 385 |
+
flex-direction: column;
|
| 386 |
+
gap: 0.25rem;
|
| 387 |
+
cursor: help;
|
| 388 |
+
transition: border-color 0.15s;
|
| 389 |
+
}
|
| 390 |
+
|
| 391 |
+
.metric-card--highlight {
|
| 392 |
+
border-color: var(--color-success);
|
| 393 |
+
}
|
| 394 |
+
|
| 395 |
+
.metric-label {
|
| 396 |
+
font-size: 0.75rem;
|
| 397 |
+
font-weight: 700;
|
| 398 |
+
text-transform: uppercase;
|
| 399 |
+
letter-spacing: 0.1em;
|
| 400 |
+
color: var(--color-text-muted);
|
| 401 |
+
}
|
| 402 |
+
|
| 403 |
+
.metric-value {
|
| 404 |
+
font-size: 1.875rem;
|
| 405 |
+
font-weight: 700;
|
| 406 |
+
color: var(--color-text);
|
| 407 |
+
line-height: 1.2;
|
| 408 |
+
}
|
| 409 |
+
|
| 410 |
+
.metric-unit {
|
| 411 |
+
font-size: 0.9rem;
|
| 412 |
+
font-weight: 400;
|
| 413 |
+
color: var(--color-text-muted);
|
| 414 |
+
}
|
| 415 |
+
|
| 416 |
+
.metric-desc {
|
| 417 |
+
font-size: 0.75rem;
|
| 418 |
+
color: #475569;
|
| 419 |
+
line-height: 1.4;
|
| 420 |
+
}
|
| 421 |
+
|
| 422 |
+
/* ββ Error banner ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 423 |
+
.error-banner {
|
| 424 |
+
background: rgba(239, 68, 68, 0.1);
|
| 425 |
+
border: 1px solid rgba(239, 68, 68, 0.4);
|
| 426 |
+
border-radius: var(--radius-sm);
|
| 427 |
+
padding: 0.75rem 1rem;
|
| 428 |
+
color: #fca5a5;
|
| 429 |
+
font-size: 0.9rem;
|
| 430 |
+
}
|
| 431 |
+
|
| 432 |
+
/* ββ Spinners ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ */
|
| 433 |
+
@keyframes spin {
|
| 434 |
+
to { transform: rotate(360deg); }
|
| 435 |
+
}
|
| 436 |
+
|
| 437 |
+
.spinner {
|
| 438 |
+
display: inline-block;
|
| 439 |
+
width: 1.25rem;
|
| 440 |
+
height: 1.25rem;
|
| 441 |
+
border: 2px solid rgba(255,255,255,0.2);
|
| 442 |
+
border-top-color: #fff;
|
| 443 |
+
border-radius: 50%;
|
| 444 |
+
animation: spin 0.7s linear infinite;
|
| 445 |
+
vertical-align: middle;
|
| 446 |
+
}
|
| 447 |
+
|
| 448 |
+
.spinner-inline {
|
| 449 |
+
display: inline-block;
|
| 450 |
+
width: 1rem;
|
| 451 |
+
height: 1rem;
|
| 452 |
+
border: 2px solid rgba(255,255,255,0.3);
|
| 453 |
+
border-top-color: #fff;
|
| 454 |
+
border-radius: 50%;
|
| 455 |
+
animation: spin 0.7s linear infinite;
|
| 456 |
+
}
|
frontend/src/main.jsx
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import React from 'react'
|
| 2 |
+
import ReactDOM from 'react-dom/client'
|
| 3 |
+
import App from './App.jsx'
|
| 4 |
+
import './index.css'
|
| 5 |
+
|
| 6 |
+
ReactDOM.createRoot(document.getElementById('root')).render(
|
| 7 |
+
<React.StrictMode>
|
| 8 |
+
<App />
|
| 9 |
+
</React.StrictMode>,
|
| 10 |
+
)
|
frontend/src/services/inferenceRouter.js
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* inferenceRouter.js
|
| 3 |
+
* βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 4 |
+
* Strategy-based routing:
|
| 5 |
+
* - Model name contains "WebGPU" β client-side via WebWorker (transformers.js)
|
| 6 |
+
* - All other models β server-side via FastAPI / vLLM
|
| 7 |
+
*
|
| 8 |
+
* Exports:
|
| 9 |
+
* route(model, audioBuffer, onProgress) β Promise<TranscribeResult>
|
| 10 |
+
*
|
| 11 |
+
* TranscribeResult = { transcript, ttft_ms, itl_ms, rtfx, mode }
|
| 12 |
+
*/
|
| 13 |
+
|
| 14 |
+
// ββ WebGPU / WebWorker client βββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 15 |
+
|
| 16 |
+
let workerInstance = null;
|
| 17 |
+
let workerReadyResolve = null;
|
| 18 |
+
let workerReadyReject = null; // companion reject for the load promise
|
| 19 |
+
const pendingCallbacks = new Map(); // id β { resolve, reject, onProgress }
|
| 20 |
+
|
| 21 |
+
function getWorker() {
|
| 22 |
+
if (workerInstance) return workerInstance;
|
| 23 |
+
|
| 24 |
+
// Vite's ?worker syntax creates an ES-module Worker automatically
|
| 25 |
+
workerInstance = new Worker(
|
| 26 |
+
new URL('../workers/webgpu.worker.js', import.meta.url),
|
| 27 |
+
{ type: 'module' }
|
| 28 |
+
);
|
| 29 |
+
|
| 30 |
+
workerInstance.addEventListener('message', (event) => {
|
| 31 |
+
const { type, id, stable, unstable, transcript, ttft_ms, itl_ms, rtfx, message } = event.data;
|
| 32 |
+
|
| 33 |
+
// ββ Load lifecycle messages βββββββββββββββββββββββββββββββββββββββββββββ
|
| 34 |
+
if (type === 'ready' && workerReadyResolve) {
|
| 35 |
+
const res = workerReadyResolve;
|
| 36 |
+
workerReadyResolve = null;
|
| 37 |
+
workerReadyReject = null;
|
| 38 |
+
res();
|
| 39 |
+
return;
|
| 40 |
+
}
|
| 41 |
+
|
| 42 |
+
// A null id means the error came from loadModel(), not a transcription.
|
| 43 |
+
if (type === 'error' && id == null) {
|
| 44 |
+
const rej = workerReadyReject;
|
| 45 |
+
workerReadyResolve = null;
|
| 46 |
+
workerReadyReject = null;
|
| 47 |
+
rej?.(new Error(message ?? 'Model failed to load'));
|
| 48 |
+
return;
|
| 49 |
+
}
|
| 50 |
+
|
| 51 |
+
// ββ Transcription lifecycle messages ββββββββββββββββββββββββββββββββββββ
|
| 52 |
+
const cb = pendingCallbacks.get(id);
|
| 53 |
+
if (!cb) return;
|
| 54 |
+
|
| 55 |
+
switch (type) {
|
| 56 |
+
case 'progress':
|
| 57 |
+
cb.onProgress?.({ stable, unstable });
|
| 58 |
+
break;
|
| 59 |
+
case 'result':
|
| 60 |
+
pendingCallbacks.delete(id);
|
| 61 |
+
cb.resolve({ transcript, ttft_ms, itl_ms, rtfx, mode: 'webgpu' });
|
| 62 |
+
break;
|
| 63 |
+
case 'error':
|
| 64 |
+
pendingCallbacks.delete(id);
|
| 65 |
+
cb.reject(new Error(message));
|
| 66 |
+
break;
|
| 67 |
+
}
|
| 68 |
+
});
|
| 69 |
+
|
| 70 |
+
return workerInstance;
|
| 71 |
+
}
|
| 72 |
+
|
| 73 |
+
async function ensureModelLoaded(modelId) {
|
| 74 |
+
const worker = getWorker();
|
| 75 |
+
return new Promise((resolve, reject) => {
|
| 76 |
+
workerReadyResolve = resolve;
|
| 77 |
+
workerReadyReject = reject;
|
| 78 |
+
worker.postMessage({ type: 'load', model: modelId });
|
| 79 |
+
});
|
| 80 |
+
}
|
| 81 |
+
|
| 82 |
+
async function routeWebGPU(modelId, audioBuffer, onProgress) {
|
| 83 |
+
await ensureModelLoaded(modelId);
|
| 84 |
+
const worker = getWorker();
|
| 85 |
+
const id = crypto.randomUUID();
|
| 86 |
+
return new Promise((resolve, reject) => {
|
| 87 |
+
pendingCallbacks.set(id, { resolve, reject, onProgress });
|
| 88 |
+
worker.postMessage({ type: 'transcribe', audio: audioBuffer, id }, [audioBuffer.buffer]);
|
| 89 |
+
});
|
| 90 |
+
}
|
| 91 |
+
|
| 92 |
+
// ββ Server-side / vLLM client βββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 93 |
+
|
| 94 |
+
async function routeServer(modelId, audioFile, onProgress) {
|
| 95 |
+
const form = new FormData();
|
| 96 |
+
form.append('audio', audioFile);
|
| 97 |
+
form.append('model', modelId);
|
| 98 |
+
|
| 99 |
+
// Use streaming endpoint for token-by-token delivery
|
| 100 |
+
const response = await fetch('/api/transcribe/stream', {
|
| 101 |
+
method: 'POST',
|
| 102 |
+
body: form,
|
| 103 |
+
});
|
| 104 |
+
|
| 105 |
+
if (!response.ok) {
|
| 106 |
+
const err = await response.json().catch(() => ({ detail: response.statusText }));
|
| 107 |
+
throw new Error(err.detail ?? `HTTP ${response.status}`);
|
| 108 |
+
}
|
| 109 |
+
|
| 110 |
+
const reader = response.body.getReader();
|
| 111 |
+
const decoder = new TextDecoder();
|
| 112 |
+
let buffer = '';
|
| 113 |
+
let finalResult = null;
|
| 114 |
+
|
| 115 |
+
try {
|
| 116 |
+
while (true) {
|
| 117 |
+
const { value, done } = await reader.read();
|
| 118 |
+
if (done) break;
|
| 119 |
+
buffer += decoder.decode(value, { stream: true });
|
| 120 |
+
|
| 121 |
+
// Parse Server-Sent Events
|
| 122 |
+
const events = buffer.split('\n\n');
|
| 123 |
+
buffer = events.pop() ?? '';
|
| 124 |
+
|
| 125 |
+
for (const event of events) {
|
| 126 |
+
const dataLine = event.split('\n').find((l) => l.startsWith('data: '));
|
| 127 |
+
if (!dataLine) continue;
|
| 128 |
+
try {
|
| 129 |
+
const payload = JSON.parse(dataLine.slice(6));
|
| 130 |
+
if (payload.done) {
|
| 131 |
+
finalResult = payload;
|
| 132 |
+
} else if (payload.token) {
|
| 133 |
+
onProgress?.({ token: payload.token, ttft_ms: payload.ttft_ms });
|
| 134 |
+
} else if (payload.ttft_ms != null) {
|
| 135 |
+
onProgress?.({ ttft_ms: payload.ttft_ms });
|
| 136 |
+
}
|
| 137 |
+
} catch {
|
| 138 |
+
// ignore malformed SSE frames
|
| 139 |
+
}
|
| 140 |
+
}
|
| 141 |
+
}
|
| 142 |
+
} finally {
|
| 143 |
+
// Always release the reader so the underlying HTTP connection can be
|
| 144 |
+
// returned to the pool. This prevents stream leaks when an exception
|
| 145 |
+
// is thrown mid-stream (e.g. network error or component unmount).
|
| 146 |
+
reader.cancel();
|
| 147 |
+
}
|
| 148 |
+
|
| 149 |
+
if (!finalResult) throw new Error('Stream ended without a final result.');
|
| 150 |
+
|
| 151 |
+
return {
|
| 152 |
+
transcript: finalResult.transcript,
|
| 153 |
+
ttft_ms: finalResult.ttft_ms,
|
| 154 |
+
itl_ms: finalResult.itl_ms,
|
| 155 |
+
rtfx: finalResult.rtfx,
|
| 156 |
+
mode: 'server',
|
| 157 |
+
};
|
| 158 |
+
}
|
| 159 |
+
|
| 160 |
+
// ββ Public router βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 161 |
+
|
| 162 |
+
/**
|
| 163 |
+
* Route transcription to the appropriate execution mode.
|
| 164 |
+
*
|
| 165 |
+
* @param {string} modelId Selected model name
|
| 166 |
+
* @param {File|Float32Array} audio Audio source
|
| 167 |
+
* @param {function} [onProgress] Called with partial results during streaming
|
| 168 |
+
* @returns {Promise<{transcript:string, ttft_ms:number, itl_ms:number, rtfx:number, mode:string}>}
|
| 169 |
+
*/
|
| 170 |
+
export async function route(modelId, audio, onProgress) {
|
| 171 |
+
if (modelId.includes('WebGPU')) {
|
| 172 |
+
// Ensure we have a Float32Array of 16 kHz samples
|
| 173 |
+
const audioBuffer = audio instanceof Float32Array ? audio : await fileToFloat32(audio);
|
| 174 |
+
return routeWebGPU(modelId, audioBuffer, onProgress);
|
| 175 |
+
}
|
| 176 |
+
// Server-side: pass the raw File for multipart upload
|
| 177 |
+
return routeServer(modelId, audio, onProgress);
|
| 178 |
+
}
|
| 179 |
+
|
| 180 |
+
// ββ Helper: decode File β Float32Array at 16 kHz ββββββββββββββββββββββββββββββ
|
| 181 |
+
|
| 182 |
+
async function fileToFloat32(file) {
|
| 183 |
+
const arrayBuffer = await file.arrayBuffer();
|
| 184 |
+
const audioCtx = new AudioContext({ sampleRate: 16000 });
|
| 185 |
+
const decoded = await audioCtx.decodeAudioData(arrayBuffer);
|
| 186 |
+
return decoded.getChannelData(0); // mono, 16 kHz
|
| 187 |
+
}
|
frontend/src/workers/webgpu.worker.js
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/**
|
| 2 |
+
* webgpu.worker.js
|
| 3 |
+
* βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 4 |
+
* Runs entirely inside a WebWorker context.
|
| 5 |
+
* Responsibilities:
|
| 6 |
+
* 1. Load a transformers.js Whisper pipeline (WebGPU backend).
|
| 7 |
+
* 2. Cache ONNX model weights in the browser via the Cache API for fast
|
| 8 |
+
* subsequent cold-starts.
|
| 9 |
+
* 3. Implement a "LocalAgreement-2" style streaming stabilisation algorithm
|
| 10 |
+
* that withholds partial hypotheses until at least two consecutive
|
| 11 |
+
* decoding passes agree on a prefix, preventing jittery live output.
|
| 12 |
+
*
|
| 13 |
+
* Message protocol (worker β main thread):
|
| 14 |
+
* { type: 'load', model: string }
|
| 15 |
+
* { type: 'transcribe', audio: Float32Array, id: string }
|
| 16 |
+
* { type: 'abort', id: string }
|
| 17 |
+
*
|
| 18 |
+
* Message protocol (worker β main thread):
|
| 19 |
+
* { type: 'ready' }
|
| 20 |
+
* { type: 'progress', id, text: string, stable: bool }
|
| 21 |
+
* { type: 'result', id, transcript: string, ttft_ms, itl_ms, rtfx }
|
| 22 |
+
* { type: 'error', id, message: string }
|
| 23 |
+
*/
|
| 24 |
+
|
| 25 |
+
import { pipeline, env } from '@xenova/transformers';
|
| 26 |
+
|
| 27 |
+
// ββ Cache configuration βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 28 |
+
// Point transformers.js at the Cache Storage API so ONNX weights survive
|
| 29 |
+
// page reloads without re-downloading from the CDN.
|
| 30 |
+
// useBrowserCache relies on the Cache Storage API which is only available in
|
| 31 |
+
// secure contexts (HTTPS or localhost); it is a no-op if the API is absent.
|
| 32 |
+
env.useBrowserCache = typeof caches !== 'undefined';
|
| 33 |
+
env.allowLocalModels = false;
|
| 34 |
+
|
| 35 |
+
// ββ State βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 36 |
+
/** @type {import('@xenova/transformers').Pipeline | null} */
|
| 37 |
+
let asr = null;
|
| 38 |
+
let loadedModelId = null;
|
| 39 |
+
const abortedIds = new Set();
|
| 40 |
+
|
| 41 |
+
// ββ LocalAgreement-2 helpers ββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 42 |
+
/**
|
| 43 |
+
* Returns the longest common prefix (token-level) shared by *a* and *b*.
|
| 44 |
+
* @param {string[]} a
|
| 45 |
+
* @param {string[]} b
|
| 46 |
+
* @returns {string[]}
|
| 47 |
+
*/
|
| 48 |
+
function longestCommonPrefix(a, b) {
|
| 49 |
+
const len = Math.min(a.length, b.length);
|
| 50 |
+
let i = 0;
|
| 51 |
+
while (i < len && a[i] === b[i]) i++;
|
| 52 |
+
return a.slice(0, i);
|
| 53 |
+
}
|
| 54 |
+
|
| 55 |
+
/**
|
| 56 |
+
* LocalAgreement-2 stabiliser.
|
| 57 |
+
*
|
| 58 |
+
* Keeps a sliding window of the last two hypotheses. Only the prefix
|
| 59 |
+
* agreed upon by *both* is emitted as "stable" text. The remainder is
|
| 60 |
+
* surfaced as an unstable suffix so the UI can render it in a dimmed style.
|
| 61 |
+
*/
|
| 62 |
+
class LocalAgreement2 {
|
| 63 |
+
constructor() {
|
| 64 |
+
this.prev = /** @type {string[]} */ ([]);
|
| 65 |
+
this.stableTokens = /** @type {string[]} */ ([]);
|
| 66 |
+
}
|
| 67 |
+
|
| 68 |
+
/**
|
| 69 |
+
* Feed in the latest hypothesis tokens.
|
| 70 |
+
* @param {string[]} current Current hypothesis split into tokens
|
| 71 |
+
* @returns {{ stable: string, unstable: string }}
|
| 72 |
+
*/
|
| 73 |
+
update(current) {
|
| 74 |
+
const agreed = longestCommonPrefix(this.prev, current);
|
| 75 |
+
// Extend the stable set with newly confirmed tokens, but never claim more
|
| 76 |
+
// stable tokens than actually exist in the current hypothesis. Capping at
|
| 77 |
+
// current.length prevents stale over-commitment when the model produces a
|
| 78 |
+
// shorter hypothesis (e.g. at the start of a new audio chunk), which would
|
| 79 |
+
// otherwise show confirmed text that is no longer in the active hypothesis.
|
| 80 |
+
const newStableLen = Math.min(
|
| 81 |
+
Math.max(agreed.length, this.stableTokens.length),
|
| 82 |
+
current.length,
|
| 83 |
+
);
|
| 84 |
+
this.stableTokens = current.slice(0, newStableLen);
|
| 85 |
+
this.prev = current;
|
| 86 |
+
const stable = this.stableTokens.join('');
|
| 87 |
+
const unstable = current.slice(this.stableTokens.length).join('');
|
| 88 |
+
return { stable, unstable };
|
| 89 |
+
}
|
| 90 |
+
|
| 91 |
+
reset() {
|
| 92 |
+
this.prev = [];
|
| 93 |
+
this.stableTokens = [];
|
| 94 |
+
}
|
| 95 |
+
}
|
| 96 |
+
|
| 97 |
+
// ββ Model loading βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 98 |
+
async function loadModel(modelId) {
|
| 99 |
+
if (asr && loadedModelId === modelId) {
|
| 100 |
+
self.postMessage({ type: 'ready' });
|
| 101 |
+
return;
|
| 102 |
+
}
|
| 103 |
+
try {
|
| 104 |
+
self.postMessage({ type: 'loading', modelId });
|
| 105 |
+
try {
|
| 106 |
+
// Prefer WebGPU (fp16) for maximum throughput.
|
| 107 |
+
asr = await pipeline('automatic-speech-recognition', modelId, {
|
| 108 |
+
device: 'webgpu',
|
| 109 |
+
dtype: 'fp16',
|
| 110 |
+
});
|
| 111 |
+
} catch {
|
| 112 |
+
// WebGPU unavailable (non-secure context, old browser, no GPU) β
|
| 113 |
+
// fall back to WASM fp32 so the app still works.
|
| 114 |
+
self.postMessage({ type: 'loading', modelId, fallback: 'wasm' });
|
| 115 |
+
asr = await pipeline('automatic-speech-recognition', modelId, {
|
| 116 |
+
device: 'wasm',
|
| 117 |
+
dtype: 'fp32',
|
| 118 |
+
});
|
| 119 |
+
}
|
| 120 |
+
loadedModelId = modelId;
|
| 121 |
+
self.postMessage({ type: 'ready' });
|
| 122 |
+
} catch (err) {
|
| 123 |
+
// Reset state so a subsequent load attempt can retry cleanly.
|
| 124 |
+
asr = null;
|
| 125 |
+
loadedModelId = null;
|
| 126 |
+
self.postMessage({ type: 'error', id: null, message: String(err) });
|
| 127 |
+
}
|
| 128 |
+
}
|
| 129 |
+
|
| 130 |
+
// ββ Transcription βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 131 |
+
async function transcribe(audio, id) {
|
| 132 |
+
if (!asr) {
|
| 133 |
+
self.postMessage({ type: 'error', id, message: 'Model not loaded. Send a load message first.' });
|
| 134 |
+
return;
|
| 135 |
+
}
|
| 136 |
+
|
| 137 |
+
const la2 = new LocalAgreement2();
|
| 138 |
+
const t0 = performance.now();
|
| 139 |
+
let firstTokenTime = null;
|
| 140 |
+
const tokenTimestamps = [];
|
| 141 |
+
|
| 142 |
+
try {
|
| 143 |
+
// transformers.js callback_function fires after each generated token
|
| 144 |
+
const result = await asr(audio, {
|
| 145 |
+
return_timestamps: true,
|
| 146 |
+
chunk_length_s: 30,
|
| 147 |
+
stride_length_s: 5,
|
| 148 |
+
callback_function: (beams) => {
|
| 149 |
+
if (abortedIds.has(id)) throw new Error('ABORTED');
|
| 150 |
+
|
| 151 |
+
const now = performance.now();
|
| 152 |
+
if (firstTokenTime === null) firstTokenTime = now;
|
| 153 |
+
tokenTimestamps.push(now);
|
| 154 |
+
|
| 155 |
+
// Extract hypothesis text from the first beam
|
| 156 |
+
const hypothesis = beams[0]?.output_token_ids ?? [];
|
| 157 |
+
const decoded = asr.tokenizer
|
| 158 |
+
? asr.tokenizer.decode(hypothesis, { skip_special_tokens: true })
|
| 159 |
+
: (beams[0]?.text ?? '');
|
| 160 |
+
|
| 161 |
+
// Split on whitespace boundaries, preserving leading space within each word
|
| 162 |
+
// to allow correct reconstruction. Use non-capturing split to avoid empty strings.
|
| 163 |
+
const tokens = decoded.match(/\S+\s*/g) ?? [];
|
| 164 |
+
const { stable, unstable } = la2.update(tokens);
|
| 165 |
+
|
| 166 |
+
self.postMessage({ type: 'progress', id, stable, unstable });
|
| 167 |
+
},
|
| 168 |
+
});
|
| 169 |
+
|
| 170 |
+
if (abortedIds.has(id)) {
|
| 171 |
+
abortedIds.delete(id);
|
| 172 |
+
return;
|
| 173 |
+
}
|
| 174 |
+
|
| 175 |
+
const t1 = performance.now();
|
| 176 |
+
const totalMs = t1 - t0;
|
| 177 |
+
const audioDurationS = audio.length / 16000;
|
| 178 |
+
const ttftMs = firstTokenTime !== null ? firstTokenTime - t0 : 0;
|
| 179 |
+
let itlMs = 0;
|
| 180 |
+
if (tokenTimestamps.length > 1) {
|
| 181 |
+
const gaps = tokenTimestamps
|
| 182 |
+
.slice(1)
|
| 183 |
+
.map((ts, i) => ts - tokenTimestamps[i]);
|
| 184 |
+
itlMs = gaps.reduce((s, g) => s + g, 0) / gaps.length;
|
| 185 |
+
}
|
| 186 |
+
const rtfx = audioDurationS / (totalMs / 1000);
|
| 187 |
+
|
| 188 |
+
self.postMessage({
|
| 189 |
+
type: 'result',
|
| 190 |
+
id,
|
| 191 |
+
transcript: typeof result.text === 'string' ? result.text : result.text ?? '',
|
| 192 |
+
ttft_ms: Math.round(ttftMs * 100) / 100,
|
| 193 |
+
itl_ms: Math.round(itlMs * 100) / 100,
|
| 194 |
+
rtfx: Math.round(rtfx * 10000) / 10000,
|
| 195 |
+
});
|
| 196 |
+
} catch (err) {
|
| 197 |
+
if (String(err).includes('ABORTED')) {
|
| 198 |
+
abortedIds.delete(id);
|
| 199 |
+
} else {
|
| 200 |
+
self.postMessage({ type: 'error', id, message: String(err) });
|
| 201 |
+
}
|
| 202 |
+
}
|
| 203 |
+
}
|
| 204 |
+
|
| 205 |
+
// ββ Message handler βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 206 |
+
self.addEventListener('message', async (event) => {
|
| 207 |
+
const { type, model, audio, id } = event.data;
|
| 208 |
+
switch (type) {
|
| 209 |
+
case 'load':
|
| 210 |
+
await loadModel(model);
|
| 211 |
+
break;
|
| 212 |
+
case 'transcribe':
|
| 213 |
+
await transcribe(audio, id);
|
| 214 |
+
break;
|
| 215 |
+
case 'abort':
|
| 216 |
+
abortedIds.add(id);
|
| 217 |
+
break;
|
| 218 |
+
default:
|
| 219 |
+
self.postMessage({ type: 'error', id: null, message: `Unknown message type: ${type}` });
|
| 220 |
+
}
|
| 221 |
+
});
|
frontend/vite.config.js
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import { defineConfig } from 'vite'
|
| 2 |
+
import react from '@vitejs/plugin-react'
|
| 3 |
+
|
| 4 |
+
// https://vitejs.dev/config/
|
| 5 |
+
export default defineConfig({
|
| 6 |
+
plugins: [react()],
|
| 7 |
+
worker: {
|
| 8 |
+
format: 'es',
|
| 9 |
+
},
|
| 10 |
+
server: {
|
| 11 |
+
port: 5173,
|
| 12 |
+
proxy: {
|
| 13 |
+
'/api': {
|
| 14 |
+
target: 'http://localhost:8000',
|
| 15 |
+
changeOrigin: true,
|
| 16 |
+
rewrite: (path) => path.replace(/^\/api/, ''),
|
| 17 |
+
},
|
| 18 |
+
},
|
| 19 |
+
},
|
| 20 |
+
optimizeDeps: {
|
| 21 |
+
// transformers.js uses dynamic imports; exclude it from pre-bundling
|
| 22 |
+
exclude: ['@xenova/transformers'],
|
| 23 |
+
},
|
| 24 |
+
})
|