News for hackers. Stuff that matters.

A comment on How to train large deep learning models as a startup. Parent comment

Re:How to train large deep learning models as a startup by subpar on Thursday October 07, 2021 @12:58PM (#28789061)
How good is their speaker labeling? We've been using the Google API but their diarization has been basically unusable for our application (transcripts of group conversations).
[ Parent | on HN ]
Re:How to train large deep learning models as a startup by dylanbfox on Thursday October 07, 2021 @01:09PM (#28789238)
Dylan from Assembly here. If you want to send me one of your audio files (my email is in my profile) I'd be happy to send you back the diarized results from our API.

You can also signup for a free account and test from the dashboard without having to write any code if that's easier.

Other than lots of crosstalk in your group conversations - is there anything else challenging about your audio (eg, distance from microphones, background noise, etc?)

[ Parent | on HN ]