p323 (40 epochs, rmvpe, vctk)

[lone rock]

dl link: https://huggingface.co/lyery/models-vc/resolve/main/p323.zip?download=true

female speaker found in the vctk dataset, she is the speaker 88 of the original pretrain
this voice and the whole vctk dataset is free to use (Creative Commons Attribution License) but you must credit CSTR VCTK Corpus (Veaux, Christophe; Yamagishi, Junichi; MacDonald, Kirsten, 2017). https://datashare.ed.ac.uk/handle/10283/2950
works best for speech (audiobooks) but also has singing capabilities

trained on 20 minutes of data and a batch size of 8

[tiny crow]

Is that her name

[lone rock]

(yes i don't know why there is no p319, 320, 321, 322)

[tiny crow]

Overshadowed and dragged into hell/j

[last whale]

Model Ready ✅

This model has been synced with Weights and is ready to use for free!

[lone rock]

this voice is in the og pretrain

the model already knows her

[tulip holly]

Ooh

[tulip holly]

I’m ignorant when it comes to ts, do you have any articles I could read so I could understand better? I was recommended some guide, but I forgot

I’m also gonna delete the glaze out of embarrassment

[lone rock]

https://gudgud96.github.io/2024/09/26/annotated-rvc/

this explains how rvc works

just technical details of whats going on