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.

Whisper Turbo: transcribe 20x faster than realtime using Rust and WebGPU

11 pointsby jasondaviesover 1 year ago

4 comments

lhlover 1 year ago
Neat to see a new implementation, although I&#x27;ll note that for those looking for a drop-in replacement for the whisper <i>library</i>, I believe that both <a href="https:&#x2F;&#x2F;github.com&#x2F;guillaumekln&#x2F;faster-whisper">https:&#x2F;&#x2F;github.com&#x2F;guillaumekln&#x2F;faster-whisper</a> and <a href="https:&#x2F;&#x2F;github.com&#x2F;m-bain&#x2F;whisperX">https:&#x2F;&#x2F;github.com&#x2F;m-bain&#x2F;whisperX</a> are easier (PyTorch-based, doesn&#x27;t require a web browser), and a lot faster (WhisperX is up to 70X realtime).
评论 #37497013 未加载
评论 #37492584 未加载
iandanforthover 1 year ago
Vercel demo doesn&#x27;t work in Firefox:<p>&quot;TypeError: i[e] is undefined&quot;<p>and &quot;No Model Loaded&quot; error after loading and picking a file and pressing transcribe.
评论 #37497007 未加载
mmastracover 1 year ago
Where is the Rust portion of the project? It appears to be named Rumble.
评论 #37497039 未加载
评论 #37496998 未加载
theususover 1 year ago
Looks like just the website wrapper. Where is the code?