VoiceClone-TTS / requirements.txt
ginipick's picture
Update requirements.txt
9470e0e verified
# Core dependencies
anyio==4.8.0
fastapi==0.116.1
gradio==5.16.0
httpx==0.28.1
huggingface-hub==0.28.1
numpy==2.2.6
safetensors==0.5.3
soundfile==0.13.1
typing-extensions==4.12.2
uvicorn==0.35.0
transformers==4.49.0
spaces
# PyTorch and related
torch==2.6.0
torchaudio==2.6.0
torchvision==0.21.0
# IMPORTANT: Install flash-attn BEFORE mamba-ssm
# flash-attn must be installed from wheel for speed
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
# Then install causal-conv1d
https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.5.0.post8/causal_conv1d-1.5.0.post8+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
# Finally install mamba-ssm (it needs flash-attn to be already installed)
https://github.com/state-spaces/mamba/releases/download/v2.2.4/mamba_ssm-2.2.4+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
# Zonos package
zonos @ git+https://github.com/Zyphra/Zonos.git
# Additional dependencies that might be needed
einops
ninja