News for hackers. Stuff that matters.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by jmvalin on Monday March 04, 2024 @03:50PM (#39595885)
Well, there's different ways to make things up. We decided against using a pure generative model to avoid making up phoneme or words. Instead, we predict the expected acoustic features (using a regression loss), which means that model is able to continue a vowel. If unsure it'll just pick the "middle point", which won't be something recognizable as a new word. That's in line with how traditional PLCs work. It just sounds better. The only generative part is the vocoder that reconstructs the waveform, but it's constrained to match the predicted spectrum so it can't hallucinate either.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by CharlesW on Monday March 04, 2024 @03:52PM (#39595911)
That's really cool. Congratulations on the release!
Re:Opus 1.5 released: Opus gets a machine learning upgrade by stevage on Monday March 04, 2024 @04:59PM (#39596703)
Any demos of this to listen to? It sounds potentially really good.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by GaggiX on Monday March 04, 2024 @05:15PM (#39596879)
There is a demo in the link shared by OP.