torch==2.4.0 torchaudio==2.4.0 torchvision==0.19.0 face_alignment==1.3.0 imageio==2.19.3 imageio-ffmpeg==0.4.7 librosa==0.8.0 numba==0.56.4 resampy==0.3.1 pydub==0.25.1 scipy kornia==0.6.8 tqdm yacs==0.1.8 pyyaml joblib==1.1.0 scikit-image==0.19.3 basicsr @ git+https://github.com/XPixelGroup/BasicSR.git@8d56e3a045f9fb3e1d8872f92ee4a4f07f886b0a facexlib dlib-bin gfpgan av safetensors gradio soundfile transformers bitsandbytes>0.37.0 vinorm cached_path huggingface_hub accelerate>=0.33.0 click datasets ema_pytorch>=0.5.2 hydra-core>=1.3.0 jieba matplotlib pypinyin tomli torchdiffeq transformers_stream_generator vocos wandb x_transformers>=1.31.14 # f5-tts spaces soxr ffmpeg