Re:StyleTTS2 – open-source Eleven Labs quality Text To Speech
by slow_numbnut on Monday November 20, 2023 @02:49AM
(#38344120)
Instead of sacrificing flexibility by building one monolith model that does Audio to audio in one go, wouldn't it be better to train a model that handles conversing with the user (knows when the user is done talking, when it's hearing itself, etc) and leave the thinking to other, more generic models?
[ Parent
| on HN ]