This is a RVC model for the character of Kenma Kozume from Haikyuu. Trained at around 300 steps, although I might upgrade to a 500+ version soon(ish).

The current model isn't really optimized for singing, but it should work for inferring speaking audio.

Do whatever you want with it as the license says, I don't care and the voice actor behind Kenma was an adult at the time of recording anyway.

Downloads last month
7
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.