top | item 44887121

(no title)

martzoukos | 6 months ago

I guess that there is no streaming option for sending generated tokens to, say, an LLM service to process the text in real-time.

discuss

order

nomad_horse|6 months ago

Whisper has the encoder-decoder architecture, so it's hard to run streaming efficiently, though whisper-streaming is a thing.

https://kyutai.org/next/stt is natively streaming STT.