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/setup_cuda_venv.sh

@@ -0,0 +1,69 @@
+#!/bin/bash
+# Setup CUDA venv for Soprano on GTX 1660
+
+set -e
+
+echo "Setting up CUDA environment for Soprano..."
+
+cd /home/koko210Serve/docker/miku-discord/soprano_to_rvc
+
+# Remove old venv if exists
+if [ -d ".venv-cuda" ]; then
+    echo "Removing old CUDA venv..."
+    rm -rf .venv-cuda
+fi
+
+# Create fresh venv with Python 3.11
+echo "Creating Python 3.11 venv..."
+python3.11 -m venv .venv-cuda
+
+# Activate CUDA venv
+source .venv-cuda/bin/activate
+
+echo "Upgrading pip..."
+pip install --upgrade pip
+
+echo "Step 1: Installing latest CUDA PyTorch..."
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+
+echo "Step 2: Installing Soprano from source with lmdeploy..."
+cd soprano
+pip install -e '.[lmdeploy]'
+cd ..
+
+echo "Step 3: Installing IPC libraries..."
+pip install redis pyzmq numpy
+
+echo "Step 4: Verifying CUDA setup..."
+python -c "
+import torch
+print(f'PyTorch version: {torch.__version__}')
+print(f'CUDA available: {torch.cuda.is_available()}')
+print(f'CUDA version: {torch.version.cuda}')
+print(f'Device count: {torch.cuda.device_count()}')
+if torch.cuda.is_available():
+    print(f'Device 0: {torch.cuda.get_device_name(0)}')
+"
+
+echo "Step 5: Testing Soprano..."
+python -c "
+from soprano import SopranoTTS
+print('✓ Soprano imported successfully')
+model = SopranoTTS(backend='lmdeploy', device='cuda', cache_size_mb=500, decoder_batch_size=2)
+print(f'✓ Soprano loaded on {model.device} using {model.backend} backend')
+"
+
+echo ""
+echo "========================================"
+echo "✓ CUDA environment setup complete!"
+echo "========================================"
+echo ""
+echo "GPU: NVIDIA GTX 1660 (6GB VRAM)"
+echo "Backend: lmdeploy"
+echo "Device: cuda:0"
+echo ""
+echo "NOTE: When running scripts, avoid running from"
+echo "the soprano_to_rvc directory due to the soprano/"
+echo "subdirectory shadowing the installed package."
+echo "Run from /tmp or remove current dir from sys.path"
+echo ""