News for hackers. Stuff that matters.
Re:Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LL... by a2128 on Friday August 04, 2023 @05:06PM (#37005892)
I've always wondered if there's a better way of making voice assistants. With this stack, the AI will not be able to answer "what is this sound?", or give you UK-based information because it picked up on your British accent. It's bottlenecked by text. A model that can understand audio as input, and output audio directly, could be so much more powerful
Re:Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LL... by og_kalu on Friday August 04, 2023 @05:14PM (#37005969)
Sure there's a better way. https://google-research.github.io/seanet/audiopalm/examples/

There's no reason autoregressive LMs can't be used to model audio data.

Re:Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LL... by ddnb on Saturday August 05, 2023 @03:54AM (#37009954)
Unfortunately this hasn't been released yet and since that paper it is very quiet around that topic so chances are high it (or something similar) will just not be released.