๐ Just dropped our first research blog! ๐
We trained a discrete-diffusion model (think Gemini Diffusion โจ) that handles TTS ๐๏ธ, adds words โ, and even removes words โ from speech! Open-sourced ๐.
Check out our blog ๐, GitHub ๐, and Hugging Face ๐ค links in the comments!
Weโve written more about how the model works, its architecture, and training setup in our blog.
If you're building in this space or want to contribute, weโd love to connect.
More here: blog.play.ai/blog/play-diffuโฆ