| torch | |
| torchaudio | |
| soundfile | |
| transformers | |
| bitsandbytes>0.37.0 | |
| vinorm | |
| cached_path | |
| huggingface_hub | |
| gradio | |
| accelerate>=0.33.0 | |
| click | |
| datasets | |
| ema_pytorch>=0.5.2 | |
| gradio>=3.45.2 | |
| hydra-core>=1.3.0 | |
| jieba | |
| librosa | |
| matplotlib | |
| numpy<=1.26.4 | |
| pydub | |
| pypinyin | |
| safetensors | |
| soundfile | |
| tomli | |
| torchdiffeq | |
| tqdm>=4.65.0 | |
| transformers_stream_generator | |
| vocos | |
| wandb | |
| x_transformers>=1.31.14 |