Description

Last Update : <t:1702941849:R> - Model URL Version RVC V2.0 - Pitch Extraction Algorithm RMVPE - Epochs - Steps 550 - 12.65 K - Dataset ~ 00:09:49 - Recommended Usage Cover - Search Feature Ratio 0.75 - Pitch Logic Pitch ( 12 = Man / 0 = Women ) - You can adjust if you found an better result - The model is trained with a dataset, where she sings very quietly and softly, which may explain why she can saturate if the referent voice gets too high. You can pitch her down if this happens, but it can distort the rendering (as you can see on the preview cover of "dango daikazoku", where she can saturate slightly because I set the pitch to 0). Previews Preview_Cover_1.wav *Base* : Youtube "Dango Daikazoku" (Acoustic Cover Clannad) (Adriana Figueroa & FamilyJules) - *Contains External Effects* : Yes - *Pitch* : 0 - *Feature Ratio* : 0.75 - Preview_Cover_2.wav *Contains External Effects* : Yes - *Pitch* 2 - *Feature Ratio* : 0.75