Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Voicebox: A speech generation model from Meta (facebook.com)
3 points by sebzim4500 on June 17, 2023 | hide | past | favorite | 1 comment


I'm curious what "word error rate" means in this context. Are they claiming that 2% of the time the model literally says the wrong word? That does not sound impressive even compared to the TTS software of the early 2000s.




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: