Fine-tune with multiple speakers' data.

[soominjung]

I have a pre-trained model and want to fine-tune it with multiple speakers' data.

I copied one pre-trained model and fine-tuned each of them with two speakers' data.
However, It is not efficient to make two models since VITS supports multi-speaker settings.
Is it possible to fine-tune several voices based on one pre-trained model?

Also, I'm wondering if it's possible to separate one speaker model from a multi-speaker model.