[FEATURE REQUEST] Support so-vits-svc

[Ph0rk0z]

Is your feature request related to a problem? Please describe.

RVC works great with spoken word but isn't so good at songs. I was finally able to test it after fixing their UI's loading of files. Results are much better for sung content. It can transform female to male voices effectively, unlike RVC.

Describe the solution you'd like

Support training and use of so-vits models along side RVC.

Describe alternatives you've considered

Janky so-vits-svc-fork UI that's geared more towards real-time voice changing.

[gitmylo]

i'll add it to the backlog, i don't know when i'll implement it though, you'll see a status update when i will.

[Ph0rk0z]

Thanks. From my cursory look now, the RVC voices usually sound more realistic and make less mistakes, but the SVC voices sound more like the person. RVC over the SVC output then makes really good results when the two are complimentary and someone didn't like train reverb into the model.

[gitmylo]

sounds good, i love that you can just combine audio to audio models, and chain them until you've got your desired result

[Ph0rk0z]

Indeed. hoping to train one next using their repo.