Pitch previews
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.
Base model (Kesha - 100 steps) trained on 20 min of data. Each subsequent model is trained on top of Kesha for an additional 50 steps.
All stems used are dry stems and I only used the cleanest possible data.
> Kesha - All data in corpus
> Ke$ha - Only ratchet data (pre-Kesha-era)
> Kesha_Power - Only the strongest data
> Kesha_Rap - Only fast talk-singing and rap data
> Kesha_Reborn - Only data from her most recent music (post-$-era)
> Kesha_Soft - Only the softest data
> Kesha_Sweet - Only soft and mildly soft data with a sweeter tone
Please do not credit me for these models publically, crediting is fine within the AI HUB server.
If you make something with these feel free to @ me on the server or dm me on Discord <@502020963693756426>. I'd love to see what you make
(Samples below. Keha = Ke$ha because discord file naming issue)
https://huggingface.co/imsupposedto/Kesha_Complete/resolve/main/Kesha_Complete.zip
Tags: Artist, RVC v2, English
Related URL: https://huggingface.co/imsupposedto/Kesha_Complete/resolve/main/Kesha_Complete.zip
Download Link: https://huggingface.co/imsupposedto/Kesha_Complete/resolve/main/Kesha_Complete.zip Hosted on Hugging Face
Convert this model in EasyAIVoice
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.