News for hackers. Stuff that matters.

A comment on Pocket TTS: A high quality TTS that gives your CPU a voice. Parent comment

Re:Pocket TTS: A high quality TTS that gives your CPU a voice by vvolhejn on Friday January 16, 2026 @04:09AM (#46644564)
Václav from Kyutai here. Thanks for the bug report! A workaround for now is to chunk the text into smaller parts where the model is more reliable. We already do some chunking in the Python package. There is also a more fancy way to do this chunking in a way that ensures that the stitched-together parts continue well (teacher-forcing), but we haven't implemented that yet.
[ Parent | on HN ]
Re:Pocket TTS: A high quality TTS that gives your CPU a voice by mgaudet on Friday January 16, 2026 @01:32PM (#46650062)
Is this just sort of expected for these models? Should users of this expect only truncation or can hallucinated bits happen too?

I also find Javert in particular seems to put in huge gaps and spaces... side effect of the voice?

[ Parent | on HN ]
Re:Pocket TTS: A high quality TTS that gives your CPU a voice by vvolhejn on Thursday January 22, 2026 @04:27AM (#46716973)
> Is this just sort of expected for these models? Should users of this expect only truncation or can hallucinated bits happen too?

Basically, yes, sort of expected: we don't have detailed enough control to precent it fully. We can measure how much it happens and train better models, but no 100% guarantee. The bigger the model, the less this happens, but this one is tiny, so it's not the sharpest tool in the shed. Hallucinated bits can theoretically happen but I haven't observed it with this model yet.

[ Parent | on HN ]