|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- Hibernates |
|
|
- HVC-Audio-Convert |
|
|
|
|
|
pipeline_tag: audio-to-audio |
|
|
--- |
|
|
|
|
|
# HVC-Audio-Convert Base Models |
|
|
|
|
|
## Overview |
|
|
These models serve as the foundational components for HVC-Audio-Convert (Soft-VC Voice Conversion), an advanced voice conversion framework that combines SoftVC feature extraction with the VITS (Conditional Variational Autoencoder with Adversarial Learning) architecture. |
|
|
|
|
|
## Key Features |
|
|
- High-quality voice conversion capabilities |
|
|
- Pre-trained on diverse vocal datasets |
|
|
- Supports cross-lingual voice conversion |
|
|
- Compatible with HVC-Audio-Convert v4.0 and newer |
|
|
|
|
|
## Technical Details |
|
|
- **Architecture**: Based on VITS (Conditional Variational Autoencoder) |
|
|
- **Feature Extraction**: Hibernates content encoder |
|
|
- **Training Data**: Curated multi-speaker datasets |
|
|
- **Model Format**: PyTorch checkpoints |
|
|
|
|
|
## Usage |
|
|
1. Download the desired base model |
|
|
2. Use with HVC-Audio-Convert framework |
|
|
3. Fine-tune on target voice data |
|
|
4. Perform voice conversion |
|
|
|
|
|
## Requirements |
|
|
- HVC-Audio-Convert framework |
|
|
- Python 3.8+ |
|
|
- PyTorch 1.13.0+ |
|
|
- CUDA compatible GPU (recommended) |
|
|
|
|
|
## License |
|
|
This project is licensed under the Apache License 2.0 - see the LICENSE file for details. |
|
|
|
|
|
## Citation |
|
|
If you use these models in your research, please cite: |
|
|
|
