| huggingface_hub==0.25.2 | |
| descript-audio-codec | |
| torch>=2.0.0 | |
| transformers>=4.45.1,<4.47.0 | |
| librosa | |
| dacite | |
| boto3==1.35.36 | |
| s3fs | |
| torchvision | |
| torchaudio | |
| json_repair | |
| pandas | |
| pydantic | |
| vector_quantize_pytorch | |
| loguru | |
| pydub | |
| ruff==0.12.2 | |
| omegaconf | |
| click | |
| langid | |
| jieba | |
| accelerate>=0.26.0 | |
| gradio>=4.0.0 | |
| soundfile | |