Kai Saikota idolEN V-TUBER (RVC V2; RMVPE; 300 Epochs; 28800 Steps)

Created: September 26, 2023
Kai Saikota idolEN V-TUBER (RVC V2; RMVPE; 300 Epochs; 28800 Steps)

Trained from one of her live streams with about 90 minutes of data.
Output is real talking (and I suck at talking to myself so yay, but the model does fairly well at it)
Please credit me when using the voice (I spend way too much time on this <3)
https://huggingface.co/Rubinlord/Kai_Saikota_V2/resolve/main/Kai_Saikota_V2.zip
All the samples are from V2
I will include the V1 link in case someone wants to play around with it anyway
https://huggingface.co/Rubinlord/Kai_Sakota_V1/resolve/main/Kai%20Sakoyata.zip

Additional Details:

Tags: RVC v2, English, E-Celeb

Related URL: https://huggingface.co/Rubinlord/Kai_Saikota_V2/resolve/main/Kai_Saikota_V2.zip

Related URL: https://huggingface.co/Rubinlord/Kai_Sakota_V1/resolve/main/Kai%20Sakoyata.zip

Download Link: https://huggingface.co/Rubinlord/Kai_Saikota_V2/resolve/main/Kai_Saikota_V2.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 路 pitch 0 Generated female reference sample
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