huggingface_hub transformers==4.49.0 gradio_client==1.3.0 qwen-vl-utils==0.0.2 transformers-stream-generator==0.0.4 accelerate diffusers peft trimesh torch==2.4.0 torchvision==0.19.0 sentencepiece spaces requests safetensors edge-tts audiosegment asyncio scipy librosa pydub ffmpeg-python av