TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Speaker diarization (labels) for OpenAI Whisper generated transcripts

44 pointsby ufarooqiover 2 years ago

2 comments

algon33over 2 years ago
I tried using this for a technical talk[1], and it got the amount of speakers wrong. Which is somewhat suprising to me, as I would have thought diarization tech would just worked by now.<p>[1]<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=5lFxURxbyEc&amp;list=PLiayR7yJx8-aCfBlccBjF1t-UO86fZJVu&amp;index=2">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=5lFxURxbyEc&amp;list=PLiayR7yJx8...</a>
评论 #34191387 未加载
sandkoanover 2 years ago
Woah! I&#x27;ve been facing the same problems with pyannote+whisper for diarization+transcription, and, coincidentally, was just experimenting with combining NeMO and whisper. Do you happen to have a repo for this? Would be invaluable.<p>Edit: Nevermind, found the link: <a href="https:&#x2F;&#x2F;colab.research.google.com&#x2F;drive&#x2F;1X5XTiob6irFq8NJM831S0ADwz5_wIS-r" rel="nofollow">https:&#x2F;&#x2F;colab.research.google.com&#x2F;drive&#x2F;1X5XTiob6irFq8NJM831...</a>
评论 #34190210 未加载