Description

Last Update : <t:1704209301:R> - Model URL Version RVC V2.0 - Pitch Extraction Algorithm RMVPE - Epochs - Steps 800 - 2.4k - Dataset ~ 00:00:26 [ All VoiceLines ] - Recommended Usage Speech - Search Feature Ratio 0.75 (You can lower the feature ratio if the model has trouble pronouncing certain words.) - Pitch Logic Pitch ( 0 = Woman ) - You can adjust if you find better version Previews Preview_TTS.wav *Provide* : ElevenLabs - Sarah English TTS - *Contains External Effects* : No - *Pitch* : +0 - *Feature Ratio* : 0.75 - *Additional Info * : As you can see, with a 0.75 ratio, the model has a little trouble with certain pronunciations such as "two". - Preview_Cover.wav *Contains External Effects* : Yes - *Pitch* 4 - *Feature Ratio* : 0.50 - *Additional Info * : The model is not primarily designed for covers