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/Dockerfile.rvc

@@ -0,0 +1,91 @@
+# Dockerfile.rvc - Multi-stage build for RVC API Server using host ROCm
+# Final image size target: <20GB (down from 85GB)
+# Python: 3.10.x | pip: 24.0 | PyTorch: 2.5.1+rocm6.2
+
+# ============================================================
+# STAGE 1: BUILD - Install all dependencies and compile extensions
+# ============================================================
+FROM ubuntu:22.04 AS builder
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=UTC
+
+# Install system dependencies and Python 3.10
+RUN apt-get update && apt-get install -y \
+    python3.10 \
+    python3.10-dev \
+    python3-pip \
+    git \
+    wget \
+    build-essential \
+    libsndfile1-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Make python3.10 the default
+RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1 && \
+    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
+
+WORKDIR /app
+
+# Copy requirements files
+COPY requirements-rvc.txt /app/
+
+# Install pip and Python dependencies
+# Install PyTorch 2.5.1+rocm6.2 from official wheel (supports gfx1030/RX 6800)
+RUN pip install --no-cache-dir pip==24.0 && \
+    pip install --no-cache-dir torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/rocm6.2 && \
+    pip install --no-cache-dir -r requirements-rvc.txt && \
+    pip uninstall -y apex || true && \
+    pip install --no-cache-dir numpy==1.23.5 scipy==1.15.3 numba==0.56.4
+
+# Copy RVC WebUI (models and code)
+COPY Retrieval-based-Voice-Conversion-WebUI/ /app/Retrieval-based-Voice-Conversion-WebUI/
+
+# Copy application files
+COPY soprano_rvc_api.py /app/
+COPY soprano_rvc_config.json /app/
+COPY rvc_config.json /app/
+COPY rvc_torch_patch.py /app/
+
+# ============================================================
+# STAGE 2: RUNTIME - Minimal runtime with only necessary files
+# ============================================================
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=UTC
+
+# Install only runtime dependencies (no build tools)
+RUN apt-get update && apt-get install -y \
+    python3.10 \
+    python3-pip \
+    libsndfile1 \
+    ffmpeg \
+    curl \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+
+# Make python3.10 the default
+RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1 && \
+    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
+
+WORKDIR /app
+
+# Copy installed Python packages from builder
+COPY --from=builder /usr/local/lib/python3.10 /usr/local/lib/python3.10
+
+# Copy application and models
+COPY --from=builder /app /app
+
+# Expose HTTP API port
+EXPOSE 8765
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
+    CMD curl -f http://localhost:8765/health || exit 1
+
+# Environment variable for Soprano server connection
+ENV SOPRANO_SERVER=tcp://soprano:5555
+
+# Run RVC API server
+CMD ["python", "soprano_rvc_api.py"]