After months of struggling to make a model due to the incident, I can do the VOICEVOX models since they outright allow people to use this in a voice changer which is interesting.

Model: https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/VoiceVoxRVC/SakuraUtaMiko.zip?download=true

Trained using the program and multiple copypastas in japanese.

Credit to me **and** VOICEVOX is required as per the TOS (attached in zip).

Use pitch 12 or 13 for male vocals, and 0 for female vocals.

Realtime only.

Sample added below.

I now have a HFSpace where you can make your own datasets, its always getting updated and its pretty fast without a GPU:

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/VoiceVoxRVC/SakuraUtaMiko.zip?download=true