Hacker News new | ask | show | jobs
Diffsound: Discrete Diffusion Model for Text-to-Sound Generation (dongchaoyang.top)
51 points by selimonder 1410 days ago
3 comments

Twiddling around trying to get this to work. Looks exciting :)
Very cool. Need to dig around and figure out what the training dataset is. Could be a great way to get some sample fodder.
There seems to be a missing python module called "image_synthesis", anyone know more about this?