SWivid / F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
https://arxiv.org/abs/2410.06885
MIT License
7.46k stars 919 forks source link

long text generate a bad result #470

Closed wwbnjsace closed 1 week ago

wwbnjsace commented 1 week ago

Checks

Question details

i read the paper that the F5 can have a good and robustness result ;but when is use a long text, for example the text is "In this paper, we introduce me,i will be a good boy" ,the generated audio sounds very bad

SWivid commented 1 week ago

Hi @wwbnjsace , need some examples~ Feel free to open with the help wanted template.