search

p0p4k / vits2_pytorch

unofficial vits2-TTS implementation in pytorch
https://arxiv.org/abs/2307.16430
MIT License
477 stars 85 forks source link

Fine tuning #40

Closed CCludts closed 1 year ago

CCludts commented 1 year ago

Hi.

First of all, thanks for your contributions on VITS2!

I was wondering if you'd have any tips how to train a different (English) voice than the ljspeech one. I don't have access to very powerful GPUs, so it'd great if it were possible to do fine-tuning on top of the 64k steps checkpoint that you've already posted (again, thanks!). Possibly something similar to https://github.com/nivibilla/efficient-vits-finetuning?

Subarasheese commented 1 year ago

You could simply apply RVC over the generated audio. But if you want a different accent, that's another story. I wish we had a Lora or Lora-like solution for this, though.