Voice conversion pipeline (Soprano TTS → RVC) with Docker support. Previously tracked as bare gitlink; removed .git/ directories and absorbed into main repo for unified tracking. Includes: Soprano TTS, RVC WebUI integration, Docker configs, WebSocket API, and benchmark scripts. Updated .gitignore to exclude large model weights (*.pth, *.pt, *.onnx, *.index). 287 files (3.1GB of ML weights properly excluded via gitignore).
12 lines
443 B
Plaintext
12 lines
443 B
Plaintext
# Constraints to prevent pip from upgrading PyTorch during requirements install
|
|
# The base image rocm/pytorch:rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.5.1 has:
|
|
# - torch 2.5.1+git8420923 (ROCm 6.4 build)
|
|
# - torchvision 0.20.1a0+04d8fc4
|
|
|
|
# Pin torch to exact version from base image to prevent upgrades
|
|
torch==2.5.1+git8420923
|
|
torchvision==0.20.1a0+04d8fc4
|
|
|
|
# Prevent standard torchaudio (we'll install ROCm version separately)
|
|
torchaudio
|