torch>=2.1.0
torchaudio>=2.1.0
torchvision>=0.16.0
# packaging # often a dep of others
# ninja # often a dep of others
uvicorn
gradio>=3.50.2 # Keep Gradio, LLaMA-Omni2 uses it. Update if a newer version is needed.
einops
transformers>=4.36.2 # Or a version compatible with LLaMA-Omni2 and Whisper
accelerate
bitsandbytes # If LLaMA-Omni2 makes use of it for 4/8bit loading
sentencepiece
protobuf
openai-whisper
shortuuid
pydub
ffmpeg-python
huggingface_hub # For downloading models from HF Hub

# fairseq and flash-attn are removed, expected to be handled by LLaMA-Omni2's setup via `pip install -e .` in Dockerfile