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).
90 lines
1.7 KiB
Plaintext
90 lines
1.7 KiB
Plaintext
# RVC API Container Requirements (ROCm/Python 3.10.19)
|
|
# pip==24.0
|
|
# Generated from: .venv/bin/pip list --format=freeze
|
|
#
|
|
# Core dependencies
|
|
fastapi==0.128.0
|
|
uvicorn==0.40.0
|
|
pyzmq==27.1.0
|
|
numpy==1.23.5
|
|
pydantic==2.12.5
|
|
python-multipart==0.0.21
|
|
|
|
# Audio processing
|
|
librosa==0.10.2
|
|
soundfile==0.13.1
|
|
sounddevice==0.5.3
|
|
pydub==0.25.1
|
|
audioread==3.1.0
|
|
resampy==0.4.3
|
|
soxr==1.0.0
|
|
pyworld==0.3.2
|
|
praat-parselmouth==0.4.7
|
|
torchcrepe==0.0.23
|
|
torchfcpe==0.0.4
|
|
|
|
# Torch with ROCm 6.4 - PyTorch 2.5.1 (provided by base image rocm6.4)
|
|
# These are commented out since the base image already has them
|
|
# torch==2.5.1+rocm6.4
|
|
# torchaudio==2.5.1+rocm6.4
|
|
# torchvision==0.20.1+rocm6.4
|
|
|
|
# RVC dependencies
|
|
fairseq==0.12.2
|
|
faiss-cpu==1.7.3
|
|
gradio==3.48.0
|
|
gradio_client==0.6.1
|
|
|
|
# LMDeploy (for compatibility with soprano_rvc_api.py)
|
|
lmdeploy==0.11.1
|
|
transformers==4.57.3
|
|
tokenizers==0.22.2
|
|
huggingface-hub==0.36.0
|
|
safetensors==0.7.0
|
|
|
|
# Supporting libraries
|
|
accelerate==1.12.0
|
|
sentencepiece==0.2.1
|
|
protobuf==6.33.4
|
|
tiktoken==0.12.0
|
|
requests==2.32.5
|
|
tqdm==4.67.1
|
|
PyYAML==6.0.3
|
|
Jinja2==3.1.6
|
|
click==8.3.1
|
|
psutil==7.2.1
|
|
packaging==25.0
|
|
filelock==3.20.0
|
|
fsspec==2025.10.0
|
|
regex==2025.11.3
|
|
certifi==2026.1.4
|
|
charset-normalizer==3.4.4
|
|
urllib3==2.6.3
|
|
idna==3.11
|
|
|
|
# Additional dependencies
|
|
einops==0.8.1
|
|
peft==0.14.0
|
|
scipy==1.15.3
|
|
scikit-learn==1.7.2
|
|
matplotlib==3.10.8
|
|
pandas==2.3.3
|
|
av==16.1.0
|
|
pillow==10.4.0
|
|
omegaconf==2.0.6
|
|
hydra-core==1.0.7
|
|
python-dotenv==1.2.1
|
|
|
|
# Ray and distributed computing
|
|
ray==2.53.0
|
|
|
|
# Numba for performance (compatible with numpy 1.23.5)
|
|
numba==0.56.4
|
|
llvmlite==0.39.0
|
|
|
|
# NOTE: apex is incompatible and must be removed after pip install
|
|
# Remove with: pip uninstall -y apex
|
|
|
|
# Additional audio libraries
|
|
local-attention==1.11.2
|