an attempt of making an rvc model of her had to be made.
isn't really accurate but whatever
this character's featured in umamusume (both the anime and game)
trained on 17 minutes of audio data extracted from the game.
CV: Hiyori Nitta
pitch extraction: rmvpe
steps: 20.4k
batch size: 6
pretrain: legacy core v1.5 / 40k
hf: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/matikanefukukitaru.zip