✳flâneur — a map of the web's best reading

Introducing hertz-dev, the first open-source base model for conversational audio generation | blog

si.inc · 1,051 words · saved by 1 readers

We're releasing hertz-dev, an 8.5B parameter autoregressive model for interactive, full-duplex speech generation.

Audio modality is imperative to creating interactive agents that feel natural. Currently the two methods of utilizing audio with generative AI are either diffusion based methods or autoregressive methods . Though diffusion based audio models prove to be good at music generation and small samples, truly interactive audio generation needs to be autoregressive. The largest problems in this field are 1) Getting audio generation that sounds human (ie. non-synthetic as well as handling interruptions well) and 2) Handling realtime generation with two live channels that are both producing information,

Explore this link on the map →

related reading