Description

Usual Info: ================================= Dataset is around 5 mins. Speech was tested using Elevenlabs with the Josh model. You will need to transpose most likely. I tested with -12. Just play around with it to get the deepness right. WARNING: SONGS WILL BE LOUD! RVC Setting: ================================= * Search Feature Ratio: 0.5 - 1 * Volume Envelope: 0.5 * Protect Voiceless Consonants: 0.5 (Disable) * Resample Audio - 0 or 48000 (Only if you need to, but it isn't necessary.) Model