Text-to-Speech
dual_ar

Finetuning?

#2
by Vezora - opened

I saw we can zero shot and few shot voice clone, but can we finetune it?

I couldn’t find a script on the github page

I saw we can zero shot and few shot voice clone, but can we finetune it?

I couldn’t find a script on the github page

here the documentation: https://speech.fish.audio/finetune/

Excuse my ignorance I did not see that documentation 😅.

Thank you! 🙏

@Paulgramma in the future will there be fine tuning with out lora? (Not that big of a deal at all tbh just curious)

Vezora changed discussion status to closed

has there anyone gotten the fine-tunning of v 1.5 to work?

Fish Audio org

Done in the latest update.

on a mac book M series?

did anyone here make fine-tune on the latest version and got a good result?
@PoTaTo721

Fish Audio org

did anyone here make fine-tune on the latest version and got a good result?
@PoTaTo721

You can go to our github repo for more information, and according to my own experiments, the finetune make sense.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment