RVC v2
·65 Epochs
可不 / KAFU
Vocaloid CeVIO
RVC v2
65 Epochs
Peak Quality 3.29 MOS
Added Feb 23, 2024
★ 10 saved
Open Model Weights Vault · Hosted on Hugging Face
· 97.1 MB
✓ Verified Direct URL
https://huggingface.co/RYUMIXTAPE/RVC-v2/resolve/main/KAFU.zip
Convert Audio with This Voice in EasyAIVoice
Carries this exact model URL and your selected pitch (0 st) into the cloud studio.
Audio Decision Loop · Sample Deck
Audition Across 18 Pitch References
Click any semitone cell below to hear how this voice performs on female and male reference vocals and lock your preferred pitch.
Female Ref
Male Ref
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: 可不 / KAFU (Vocaloid CeVIO) [65 Epochs] [RVC v2]
CLAP Semantic Analysis · Voice Accords
Sonic Profile at Selected Pitch
Acoustic traits measured directly from the generated output sample. Switch pitches in the Sample Deck to see how timbre shifts.
Age Profile
teenage
63%
young adult
17%
middle aged adult
10%
Music & Vocal Fit
music
57%
singing
14%
rap
9%
Timbre & Texture
cute
46%
anime
28%
energetic
8%
Best Use Case
character
35%
gaming
24%
podcasts
16%
Auditory Discovery · Close Alternatives
Voices That Sound Like 可不 / KAFU
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
Model Documentation & Notes
About 可不 / KAFU (Vocaloid CeVIO) [65 Epochs] [RVC v2]
https://huggingface.co/RYUMIXTAPE/RVC-v2/resolve/main/KAFU.zip Despite the low epochs I'd say its a good freaking model. Trained with 7 minutes dataset of her official singing stems. Pretrain is original, 48k sample rate, rmvpe train, 16 batch size.
Provenance & Open Access