fossil vessel
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 + dialogue isolate (for the singing bit of the dataset), resampled to 40k)
CV: Rina Honnizumi
pitch extraction: rmvpe
steps: 10.8k
batch size: 2
pretrain: klm 4 hfg / 40k
huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/shizuku_act2.zip
mint cedar