LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Any success in finetuning StyleTTS2? (alien.top)

submitted 11 months ago by enterguild@alien.top to c/localllama@poweruser.forum

1 comments fedilink hide all child comments

Hey guys, just wondering if anyone has had success finetuning StyleTTS2 yet?

The only one I can find is the LJSpeech model, which sounds really good! But wondering what some other narrators / speakers would sound like, especially voices more outside the training dataset.

(Seems zero shot prompting at runtime gives low quality, so need real finetunes!)

you are viewing a single comment's thread
view the rest of the comments

[–] a_beautiful_rhind@alien.top 1 points 11 months ago

Well I played with the demo. https://huggingface.co/spaces/styletts2/styletts2

I dunno if training it on a specific voice is worth it or if RVC will do the job. Compared to XTTS the output is much more natural but the pitch of the cloning is wrong.