alt Hacker NewsParakeet does streaming I think, so if you throw enough compute at it, it should be. The closest competitor is whisper v3 which is relatively slow, maybe Voxtral but it's still very new.
Parakeet does streaming I think, so if you throw enough compute at it, it should be. The closest competitor is whisper v3 which is relatively slow, maybe Voxtral but it's still very new.
There's a minimum possible latency just given the structure of language and how humans process phonemes. Spoken language isn't quite unambiguously causal so there's a limit to how far you can go for a given accuracy. I don't know where the efficiency curve is though. It wouldn't surprise me if 100ms was pushing it.