honestly surprised this model turned out well despire a very short dataset

this character is featured in project sekai.

trained on 1 minute of audio data from the "a miku who can't sing" movie
(5.1 + revive 3e + anvuew mono de-reverb (for the singing bit of the dataset), resampled to 40k)

CV: Furihata Ai

pitch extraction: rmvpe
steps: 11k
batch size: 2
pretrain: klm 4 hfg / 40k

huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/airi_act2.zip

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/airi_act2.zip Hosted on Hugging Face