search

yl4579 / StyleTTS2

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
MIT License
4.95k stars 417 forks source link

Weird sound in the beginning and in the end of audio #138

Closed flipkast closed 11 months ago

flipkast commented 11 months ago

Hi, I am getting a weird sound in every generated clip most of times.

https://drive.google.com/file/d/1hjuxDqn4d5eKbMYoYynleWV3NwCXmQWD/view?usp=sharing

yl4579 commented 11 months ago

See https://github.com/yl4579/StyleTTS2/discussions/81#discussioncomment-7732185 and the proposed solutions. I'm working on this and trying to add this feature on the finetuning code.