Spaces:
Running on Zero
Running on Zero
Space card
Browse files
README.md
CHANGED
|
@@ -1,13 +1,45 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.29.1
|
| 8 |
-
python_version:
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: audio.cpp ZeroGPU
|
| 3 |
+
emoji: 🔊
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: pink
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 6.29.1
|
| 8 |
+
python_version: "3.10"
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
short_description: 100+ TTS, ASR, cloning and music models via audio.cpp
|
| 13 |
+
tags:
|
| 14 |
+
- audio
|
| 15 |
+
- text-to-speech
|
| 16 |
+
- speech-recognition
|
| 17 |
+
- voice-cloning
|
| 18 |
+
- ggml
|
| 19 |
+
- gguf
|
| 20 |
+
- zerogpu
|
| 21 |
---
|
| 22 |
|
| 23 |
+
# audio.cpp on ZeroGPU
|
| 24 |
+
|
| 25 |
+
A Gradio interface for [audio.cpp](https://github.com/0xShug0/audio.cpp), the native C++/ggml inference engine
|
| 26 |
+
for 100+ audio models: text to speech, voice cloning and voice design, speech recognition, forced alignment,
|
| 27 |
+
diarization, VAD, stem separation, voice conversion, restoration, and music or sound generation.
|
| 28 |
+
|
| 29 |
+
**How it runs.** On start-up the Space downloads the official audio.cpp CUDA 12.8 Linux prebuilt (the build used by
|
| 30 |
+
the project's Colab notebook) and NVIDIA's CUDA 12 runtime wheels. Each request starts `audiocpp_server` with a
|
| 31 |
+
one-model config inside a ZeroGPU call, posts to `/v1/tasks/run`, and stops it. Without a GPU the same binary runs on
|
| 32 |
+
CPU through a tiny `libcuda` stub (`stub/cuda_stub.c`).
|
| 33 |
+
|
| 34 |
+
**Inputs.** Type or paste text, load it from txt / md / srt / vtt / pdf / docx / epub / html / json files or a URL,
|
| 35 |
+
upload or record audio, drop any audio or video file (ffmpeg converts it), or pass audio URLs. Batch mode turns each
|
| 36 |
+
paragraph or line into its own clip, and audio tasks accept many files at once.
|
| 37 |
+
|
| 38 |
+
**Python tab.** Run Python with the `audiocpp_runtime` helpers, on ZeroGPU or CPU. Set the Space variable
|
| 39 |
+
`ALLOW_PYTHON=0` to disable it.
|
| 40 |
+
|
| 41 |
+
Environment variables: `AUDIOCPP_VERSION` (release tag, default `v0.9.0`), `MAX_GPU_SECONDS`, `MAX_BATCH`,
|
| 42 |
+
`AUDIOCPP_MODELS_DIR`, `ALLOW_PYTHON`.
|
| 43 |
+
|
| 44 |
+
Credits: audio.cpp by 0xShug0 and contributors (Apache-2.0). `model_params.json` comes from the project's WebUI
|
| 45 |
+
config. Model weights keep their original licenses.
|