How much latency does the system have in the best/worst and average case? And is... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		FractalNerve on Dec 18, 2014 \| parent \| context \| favorite \| on: DeepSpeech: Scaling up end-to-end speech recogniti... How much latency does the system have in the best/worst and average case? And is your implementation public?

cbcase on Dec 19, 2014 [–]

For a single utterance, it's fast enough that we can produce results in real time. Of course, building a production system for millions of users might require just a bit more engineering work...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact