It's hilarious to see the model do go off the rails and just make random but coherent audio up – it's still quite impressive for a 350M Text to Speech model 👀 https://t.co/bqsULmSPlK pic.twitter.com/TMJWaHY2KS

— Vaibhav (VB) Srivastav (@reach_vb) 4 novembre 2024

It's hilarious to see the model do go off the rails and just make random but coherent audio up – it's still quite impressive for a 350M Text to Speech model

→ View original post on X — @reach_vb,