News for hackers. Stuff that matters.
Re:StyleTTS2 – open-source Eleven Labs quality Text To Speech by generalizations on Monday November 20, 2023 @09:33AM (#38348822)
> It could possibly be done zero-shot using prompting of a LLM

That's how I've been thinking of doing it - seemed like you could use a much smaller GPT-J-ish model for that, and measure the relative probability of 'yes' vs 'no' tokens in response to a question like 'is the user done talking'. Seemed like even that would be orders of magnitude better than just waiting for silence.

There are no comments on this comment yet.