Spaces:
Sleeping
Sleeping
| # ============ Common ============ | |
| numpy | |
| scipy | |
| pydub | |
| pyyaml | |
| onnxruntime>=1.15.0 | |
| gradio[mcp]>=4.0.0 | |
| # ============ Audiosplitter only ============ | |
| # ASR: faster-whisper (CTranslate2) | |
| faster-whisper>=1.0.0 | |
| # Clustering for diarization | |
| scikit-learn>=1.0.0 | |
| # ============ Voice Extractor only ============ | |
| setuptools | |
| # PyTorch CPU-only | |
| --extra-index-url https://download.pytorch.org/whl/cpu | |
| torch==2.5.1+cpu | |
| torchaudio==2.5.1+cpu | |
| # Audio | |
| soundfile==0.13.1 | |
| librosa==0.10.2.post1 | |
| ffmpeg-python==0.2.0 | |
| # ML models | |
| pyannote.audio==3.4.0 | |
| openai-whisper==20250625 | |
| speechbrain==1.0.2 | |
| silero-vad==5.1.2 | |
| # WeSpeaker | |
| wespeaker @ git+https://github.com/wenet-e2e/wespeaker.git | |
| # Deps | |
| s3prl==0.4.17 | |
| peft>=0.11.0 | |
| transformers>=4.40.0 | |
| pytorch-lightning==2.4.0 | |
| onnx==1.17.0 | |
| matplotlib==3.9.3 | |
| rich==14.0.0 | |
| tqdm==4.67.1 | |