Pillow
transformers>=4.40.0
gradio>=4.45.0
pydantic==2.10.6
spaces
decord
torchaudio==2.3.1
torchvision==0.18.1
transformers==4.44.2
sentencepiece==0.2.0
vector-quantize-pytorch==1.18.5
vocos==0.1.0
accelerate==1.2.1
timm==0.9.10
soundfile==0.12.1
librosa==0.9.0
decord
moviepy
pydantic==2.10.6
markdown
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.3/flash_attn-2.7.3+cu12torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl