| transformers==4.51.3 | |
| pydantic==2.11.4 | |
| numpy==2.2.5 | |
| torch==2.6.0 | |
| torchaudio==2.6.0 | |
| torchvision==0.21.0 | |
| fastapi==0.115.12 | |
| uvicorn==0.34.2 | |
| librosa==0.11.0 | |
| openai-whisper==20240930 | |
| soundfile==0.13.1 | |
| accelerate==1.6.0 | |
| voxcpm | |
| git+https://github.com/sarulab-speech/UTMOSv2.git | |