Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This finetune seems pretty stable (1b llasa) https://huggingface.co/spaces/HKUST-Audio/Llasa-1B-multi-spe...

1B is actually huge for a TTS model. Here's an 82m model with probably the most stable/coherent output of all the open weights tts models I've tested: https://huggingface.co/spaces/hexgrad/Kokoro-TTS

But if you mean zero-shot cloning, yeah they all seem to have those slurred speech artefacts from time to time.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: