av==11.0.0 einops flashy>=0.0.1 hydra-core>=1.1 hydra_colorlog julius num2words numpy<2.0.0 sentencepiece spacy>=3.6.1 torch==2.1.0 torchaudio<2.1.2,>=2.0.0 huggingface_hub tqdm transformers>=4.31.0 xformers<0.0.23 demucs librosa soundfile gradio torchmetrics encodec protobuf torchvision==0.16.0 torchtext==0.16.0 pesq pystoi [dev] coverage flake8 mypy pdoc3 pytest [wm] audioseal