Spaces:
Running
Running
| title: Wav2Lip CPU | |
| emoji: 👄 | |
| sdk: gradio | |
| sdk_version: 6.3.0 | |
| colorFrom: red | |
| colorTo: pink | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # Wav2Lip - CPU Lip Sync | |
| > **Based on [saifhassan/Wav2Lip-HD](https://github.com/saifhassan/Wav2Lip-HD)** | |
| > | |
| > CPU-only conversion for HuggingFace Spaces free tier (no GPU required). | |
| ## Features | |
| - **ONNX Wav2Lip model** (145MB) - runs on CPU | |
| - **OpenCV face detection** - no GPU needed | |
| - **Mouth-paste approach** - preserves original face quality | |
| - **Temporal smoothing** - reduces face bbox flickering | |
| ## How It Works | |
| 1. Detect face using OpenCV Haar Cascade | |
| 2. Crop and resize to 96x96 | |
| 3. Run Wav2Lip ONNX inference | |
| 4. Extract mouth region from output | |
| 5. Scale and paste onto original face | |
| 6. Feather blend at seam | |
| ## Limitations | |
| - Max 500 frames (~20 seconds at 25fps) | |
| - ~1-2 sec/frame on CPU | |
| - Best with frontal faces | |
| ## Credits | |
| - [Wav2Lip](https://github.com/Rudrabha/Wav2Lip) - Original model | |
| - [Wav2Lip-HD](https://github.com/saifhassan/Wav2Lip-HD) - HD approach | |
| - [bluefoxcreation/Wav2lip-Onnx](https://huggingface.co/bluefoxcreation/Wav2lip-Onnx) - ONNX models | |