Kesha_Complete (7 models with different timbres) - 150 Epochs - RVC V2 Crepe - Batch Size 30

Created: July 1, 2023
Kesha_Complete (7 models with different timbres) - 150 Epochs - RVC V2 Crepe - Batch Size 30

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

Additional Details:

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

Sample deck

Pitch previews

Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.

samples ready
female base 路 pitch 0 Generated female reference sample
Run
male
female
female-base generated sample male-base generated sample Enrichment pending: no scores or voice accords yet Ctrl/Cmd-click = select multiple pitches