speech-to-speech / requirements.txt
Rcarvalo's picture
Upload requirements.txt with huggingface_hub
94db0f7 verified
raw
history blame contribute delete
448 Bytes
# Install liquid-audio from GitHub
git+https://github.com/Liquid4All/liquid-audio.git
# Core dependencies for LFM2-Audio
accelerate>=1.10.1
einops>=0.8.1
librosa>=0.11.0
sentencepiece>=0.2.1
torch>=2.5.0
torchaudio>=2.5.0
transformers>=4.55.4
# Gradio and WebRTC for real-time streaming
gradio>=5.0.0
fastrtc[vad]>=0.0.30
# Optional: Flash Attention for better performance
# Uncomment if you have compatible GPU
# flash-attn --no-build-isolation