Model was trained from 18 minutes of ___clean___ 768Kbps WAV files, meaning the datasets are not from an episode or a song with post-processing.
This ensures that the model could replicate as close to the actual raw recording as possible.
`"A model trained from good datasets beats a model trained from subpar datasets, no matter how much you trained it"`

note: due to her voice being mostly whispers with low pitch range, this model may not perform that well on tracks with high pitch range
all were made on mangio-crepe with 120 hop
https://huggingface.co/Zerokano/Yukinoshita_Yukino-RVCv2/resolve/main/Yukinoshita_Yukino.zip

Additional Details:

Tags: Anime Character, RVC v2, Japanese

Related URL: https://huggingface.co/Zerokano/Yukinoshita_Yukino-RVCv2/resolve/main/Yukinoshita_Yukino.zip

Download Link: https://huggingface.co/Zerokano/Yukinoshita_Yukino-RVCv2/resolve/main/Yukinoshita_Yukino.zip