add: absorb soprano_to_rvc as regular subdirectory

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).

soprano_to_rvc/requirements-rvc.txt

@@ -0,0 +1,89 @@
+# 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