Description

Download until overtraining was suspected and with an approximately 25 minutes Japanese decent-quality dataset from Youtube. Haven't tried other methods but rmvpe and mangio seems good. Bear in mind that when the vocal/acapella's pitch is too high or low, the voice will break terribly, otherwise it should work fine. You can try to mix both rmvpe and mangio audio outputs to get the best result, because in some places, mangio works better than rvmpe and vice versa. My recommended settings: (This is just my own experience, you can go wild as you like) - Search feature ratio/Feature retrieval rate: 0.6-0.8. - Protect voiceless consonants and breath sounds: 0.2-0.4. - Hop Length (For Mangio): 128-512.