Hacker News new | past | comments | ask | show | jobs | submit login

As someone who thinker with Text to Speech (TTS), I can say this apply to TTS as well. Good model such as Tacotron2 rarely scale beyond clean ( good text and speech alignmen ) large ( > 12 hours ) datasets.



Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: