News for hackers. Stuff that matters.

A comment on WhisperSpeech – An open source text-to-speech system built by inverting Whisper. Parent comment

Re:WhisperSpeech – An open source text-to-speech system buil... by modeless on Wednesday January 17, 2024 @11:54PM (#39038024)
Did you try XTTS v2 for Mandarin? I'm curious how it compares with EmotiVoice.
[ Parent | on HN ]
Re:WhisperSpeech – An open source text-to-speech system buil... by thorum on Thursday January 18, 2024 @04:35AM (#39039791)
It has a big problem with hallucination in Chinese, random extra syllables all over the place.
[ Parent | on HN ]
Re:WhisperSpeech – An open source text-to-speech system buil... by modeless on Thursday January 18, 2024 @10:24AM (#39042826)
Makes sense, I get hallucinations in English too.
[ Parent | on HN ]