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.

AiOla open-sources ultra-fast ‘multi-head’ speech recognition model

71 pointsby cheptsov10 months ago

5 comments

BetterWhisper10 months ago
Does it do speaker recognition/ diarization? Can't see it from the repo readme
评论 #41150256 未加载
gronky_10 months ago
GH repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;aiola-lab&#x2F;whisper-medusa">https:&#x2F;&#x2F;github.com&#x2F;aiola-lab&#x2F;whisper-medusa</a>
Doohickey-d10 months ago
I&#x27;m curious which of the Whisper derivatives is actually the fastest ?<p>Since faster-whisper claims 4x speedup over base Whisper, and I&#x27;ve found WhisperX to be faster still (for longer audio where it can do batch inference), at least on consumer GPUs.<p>So with AiOla saying &quot;50% speedup&quot;, is that actually noteworthy?
评论 #41145815 未加载
评论 #41146170 未加载
phkahler10 months ago
IIRC Whisper works on wave files. Can this do real time low latency continuous ASR?
qwertox10 months ago
Nothing of interest here, it&#x27;s an ad.<p>If you&#x27;re interested, you might as well check out Gladia, at least they have a pricing section and allow you to use it as a developer, unlike just asking you to &quot;Request a Demo&quot;.<p>And while a sibling comment links to the GitHub repository, their entire website does not contain such a link.<p>---<p>Edit: My bad, for some reason I first checked the website instead of the blog post. Looks much more interesting now.
评论 #41145741 未加载
评论 #41145874 未加载