Description

Before Start I've tried to improve the dataset quality as much as possible, but even after that there's still a robotic quality, especially when you breathe (otherwise the voice fidelity is pretty good despite the dataset size). - If I can remove it, a new version will be released. Last Update : <t:1702139249:R> - Model URL Version RVC V2.0 - Pitch Extraction Algorithm RMVPE - Epochs - Steps 1.0k - 5.0 K - Dataset ~ 00:01:09 ( Raw Files ) - Recommended Usage Cover - Search Feature Ratio 0.75 - Pitch Default Logic Pitch ( 0 = Man / 12 = Women ) - You can adjust if you found an better result Previews Preview_Cover.wav *Contains External Effects* : Yes - *Pitch* : 0 - *Feature Ratio* : 0.75