News for hackers. Stuff that matters.

A comment on Neural audio codecs: how to get audio into LLMs. Parent comment

Re:Neural audio codecs: how to get audio into LLMs by mohsen1 on Tuesday October 21, 2025 @09:52AM (#45655815)
It costs more to train on audio tokens but I'm sure we will get there. Training a model on transcript of a lecture on YouTube vs. training on audio of it will make a difference.
[ Parent | on HN ]

There are no comments on this comment yet.