Many settings affect the outputs in interesting ways, but that's half the fun. These LoRAs are very lightly trained; more training may or may not help. The competitions are also performed using zero-shot text guessing, and if Facebook said it, you can bet that's actually Meta AI saying it, and they are leaders in the field. Source: over 1 year ago

You should look at the entire niche of MAE-related papers, that's quite exciting, and the neuroscience-inspired stream of stuff like Barlow Twins. As well, the official Facebook AI blog is surprisingly good coverage of much of the interesting un/semi-supervised DL research FAIR does, and worth going through. Source: almost 2 years ago

Balabolka already uses the MS-SAPI on Window, but you would need to wrap that functionality as a VST Http://cross-plus-a.com/balabolka.htm. Source: about 1 year ago

Brilliant. obviously, they'll work with your screen reader. If you want to turn documents into audio with them, Balabolka will provide you m4b's for apple or mp3's for other platforms, all with imbedded text/lyrics. Source: over 1 year ago