[UPDATED] Doraemon (RVC v2, rmvpe, 425 epochs, 24000 steps) AI Voice Model

[UPDATED] Doraemon (RVC v2, rmvpe, 425 epochs, 24000 steps)

Created: October 12, 2023

Download link: https://huggingface.co/Daruni/DoraemonRVC2/resolve/main/Doraemon425.zip

Trained 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.

Additional Details:

Tags: RVC, Japanese, Anime Character, RVC V2, Fictional Character

Download Link: https://huggingface.co/Daruni/DoraemonRVC2/resolve/main/Doraemon425.zip Hosted on Hugging Face

Convert this model in EasyAIVoice

Sample deck

Pitch previews

Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.

samples ready

female base · pitch 0 Generated female reference sample

Autorun

Run

male

female

female-base generated sample male-base generated sample Enrichment pending: no scores or voice accords yet Ctrl/Cmd-click = select multiple pitches