restore all files

README.md

@@ -1,12 +1,201 @@
 ---
-title: Rvc Beatrice Voice Conversion
-emoji: 🚀
+title: RVC-v2 + Beatrice-v2 Voice Conversion + training
+emoji: 🎤
 colorFrom: red
-colorTo: red
+colorTo: yellow
 sdk: gradio
-sdk_version: 6.10.0
+python_version: "3.10"
+sdk_version: 6.3.0
 app_file: app.py
 pinned: false
+license: mit
+tags:
+  - voice-conversion
+  - rvc
+  - beatrice
+  - beatrice-v2
+  - audio
+  - mcp-server
+short_description: RVC-v2 Beatrice-v2 - CPU inference + training
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# RVC + Beatrice Voice Conversion
+
+**CPU Inference + Training** - Single-file app for HuggingFace Spaces.
+
+## Features
+
+- **Voice Conversion** - RVC v2 (.pth) + Beatrice v2 (.pt.gz)
+- **Training** - Train both model types (GPU recommended, CPU works but slow)
+- **Single File** - Everything in one `app.py`
+- **CLI Support** - Command-line interface for batch processing
+
+## Voice Conversion
+
+1. Upload source audio (any format)
+2. Select **Model Type**: RVC v2 or Beatrice v2
+3. Upload model file (.pth for RVC, .pt.gz for Beatrice)
+4. Adjust pitch shift if needed
+5. Click Convert
+
+**Default model:** [audo/Benee-RVC](https://huggingface.co/audo/Benee-RVC) (RVC v2)
+
+## Training
+
+1. Select **Trainer**: RVC v2 or Beatrice v2
+2. Upload training audio (10+ minutes recommended)
+3. Enter model name
+4. Adjust epochs and batch size
+5. Click Start Training
+
+**Note:** CPU training works but is slow. For faster training, clone locally with CUDA GPU.
+
+## Compatibility
+
+- **RVC v1** (256-dim HuBERT) - with f0 or no-f0
+- **RVC v2** (768-dim HuBERT) - with f0 or no-f0
+- **Beatrice v2** - 16kHz input, 24kHz output, per-speaker VQ
+- **Index retrieval** (.index files) for RVC voice matching
+
+Model version and f0 flag are auto-detected from the checkpoint.
+
+Find models: [HuggingFace](https://huggingface.co/models?search=rvc) | [Weights.gg](https://weights.gg)
+
+---
+
+## API
+
+### Python Client - Voice Conversion
+
+```python
+from gradio_client import Client, handle_file
+
+client = Client("Luminia/rvc-voice-conversion")
+
+# RVC v2 inference
+result = client.predict(
+    source_audio=handle_file("voice.wav"),
+    model_type="RVC v2",
+    model_file=handle_file("model.pth"),
+    index_file=None,                  # Optional .index file
+    beatrice_model_file=None,         # Not used for RVC
+    beatrice_target_speaker=0,        # Not used for RVC
+    beatrice_formant_shift=0.0,       # Not used for RVC
+    pitch_shift=0,                    # -12 to 12 semitones
+    f0_method="pm",                   # "pm" or "harvest"
+    index_rate=0.75,                  # 0-1, voice retrieval strength
+    protect=0.33,                     # 0-0.5, voiceless consonant protection
+    api_name="/convert"
+)
+print(result)  # (output_path, status_message)
+
+# Beatrice v2 inference
+result = client.predict(
+    source_audio=handle_file("voice.wav"),
+    model_type="Beatrice v2",
+    model_file=None,                  # Not used for Beatrice
+    index_file=None,                  # Not used for Beatrice
+    beatrice_model_file=handle_file("beatrice_model.pt.gz"),
+    beatrice_target_speaker=0,        # Speaker index
+    beatrice_formant_shift=0.0,       # -2 to 2
+    pitch_shift=0,                    # -12 to 12 semitones
+    f0_method="pm",                   # Ignored for Beatrice
+    index_rate=0.75,                  # Ignored for Beatrice
+    protect=0.33,                     # Ignored for Beatrice
+    api_name="/convert"
+)
+print(result)  # (output_path, status_message)
+```
+
+### Python Client - Training
+
+```python
+from gradio_client import Client, handle_file
+
+client = Client("Luminia/rvc-voice-conversion")
+
+# RVC v2 training
+result = client.predict(
+    trainer="RVC v2",
+    train_audio=handle_file("voice.wav"),
+    train_model_name="my_voice",
+    train_epochs=50,                  # 50-500
+    train_batch=2,                    # Batch size
+    train_sr=40000,                   # 32000, 40000, or 48000
+    beatrice_epochs=30,               # Ignored for RVC
+    beatrice_batch=8,                 # Ignored for RVC
+    beatrice_resume=False,            # Ignored for RVC
+    api_name="/train"
+)
+print(result)  # (model_path, status_log)
+
+# Beatrice v2 training
+result = client.predict(
+    trainer="Beatrice v2",
+    train_audio=handle_file("voice.wav"),
+    train_model_name="my_voice",
+    train_epochs=50,                  # Ignored for Beatrice
+    train_batch=2,                    # Ignored for Beatrice
+    train_sr=40000,                   # Ignored for Beatrice
+    beatrice_epochs=30,               # 20-50 recommended
+    beatrice_batch=8,                 # Batch size
+    beatrice_resume=False,            # Resume from checkpoint
+    api_name="/train"
+)
+print(result)  # (model_path, status_log)
+```
+
+### MCP (Model Context Protocol)
+
+This Space supports MCP for AI assistants (Claude Desktop, Cursor, VS Code).
+
+1. Click **MCP** badge → **Add to MCP tools**
+2. The `convert` and `train` tools become available
+
+**MCP Config:**
+```json
+{
+  "mcpServers": {
+    "rvc": {"url": "https://luminia-rvc-voice-conversion.hf.space/gradio_api/mcp/"}
+  }
+}
+```
+
+---
+
+## CLI Usage
+
+### Inference
+```bash
+# RVC v2
+python app.py infer -i voice.wav -m model.pth -o output.wav
+
+# Beatrice v2 (auto-detected from .pt.gz extension)
+python app.py infer -i voice.wav -m beatrice_model.pt.gz -o output.wav
+
+# With pitch shift
+python app.py infer -i voice.wav -m model.pth -p 2 -o output.wav
+
+# Beatrice with speaker/formant options
+python app.py infer -i voice.wav -m beatrice.pt.gz --speaker 0 --formant-shift 1.0 -o output.wav
+```
+
+### Training
+```bash
+# RVC v2 training
+python app.py train -a voice.mp3 -o ./my_model --epochs 100
+
+# Beatrice v2 training
+python app.py train-beatrice -a voice.mp3 -o ./beatrice_model --epochs 30
+
+# Beatrice resume training
+python app.py train-beatrice -a voice.mp3 -o ./beatrice_model --epochs 30 --resume
+```
+
+---
+
+- Local real-time model usage: https://huggingface.co/wok000/vcclient000/tree/main 
+
+## Credits
+
+Based on [RVC-Project](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)-[Mangio-UI-Fork](https://github.com/Mangio621/Mangio-RVC-Fork), [Applio](https://github.com/IAHispano/Applio) data processing, and [Beatrice v2](https://huggingface.co/fierce-cats/beatrice-trainer)

gitignore

@@ -0,0 +1,19 @@
+__pycache__/
+*.pyc
+*.wav
+*.flac
+*.mp3
+*.index
+*.pth
+nul
+
+# Test/training artifacts
+test_*/
+train_*/
+F_p340_*/
+beatrice_test/
+
+# Dev scripts
+detect_noise.py
+test_applio_ab.py
+app_beatrice.py

requirements-training.txt

@@ -0,0 +1,32 @@
+# RVC Training Requirements (CUDA GPU required)
+# Run: pip install -r requirements-training.txt
+
+# PyTorch with CUDA (install separately based on your CUDA version)
+# pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
+
+# Core
+numpy
+scipy
+librosa
+soundfile
+praat-parselmouth
+
+# Training
+fairseq
+pyworld
+faiss-gpu  # Use faiss-cpu if no GPU
+torchcrepe
+
+# F0 extraction
+onnxruntime-gpu  # Use onnxruntime for CPU
+
+# Web UI
+gradio>=4.0.0
+
+# Utils
+tqdm
+tensorboard
+ffmpeg-python
+
+# For model export
+onnx

requirements.txt

@@ -0,0 +1,13 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch
+torchaudio
+gradio>=6.0.0
+numpy
+librosa
+soundfile
+huggingface_hub
+transformers
+praat-parselmouth
+pyworld
+faiss-cpu
+scipy