2026-04-11 11:23 UTC
yeah but that doesn't mean anything, does it? I don't think they just tokenize the raw audio, that wouldn't make sense, right?
Replies (1)
-
@sobchak@programming.dev 2026-04-11 11:50
I mean, you could. Just encode 100ms chunks or whatever into tokens then push them through the same model. I'm pretty sure that's what the claim to do (though with MoE/routing now, maybe).