Speech-to-Text Accuracy in 2026: Open-Weight vs. Cloud | Hacker News - But Better

Speech-to-Text Accuracy in 2026: Open-Weight vs. Cloud verli.app

See major speech-to-text engines tested on identical LibriSpeech and Earnings-22 audio with one scorer and paired-bootstrap confidence intervals.

4 points•arttaboi•4 days ago•1 comment•

#speech #text #accuracy #cloud #weight #text accuracy #open weight #major

1 comment

arttaboi4 days ago

Not affiliated in any way, just found this benchmark interesting and worth sharing.

Read the full thread on Hacker News →

Related stories

Show HN: Universal 3.6 Pro – streaming speech-to-text tuned for voice agentsassemblyai.com
Hacker News · 1 points · 1 day ago
Show HN: I emulated Roborock's cloud so my vacuum works without internetgithub.com
Hacker News · 1 points · 2 days ago
Open-weight models take 56% of token volumevercel.com
Hacker News · 1 points · 8 days ago
The Economics of Open-Weight Inferencedata.ornn.com
Hacker News · 36 points · 8 days ago
Does an open-weight decision model beat a hosted one? Jev vs. Layaastgl.com
Hacker News · 2 points · 8 days ago
Shipping local speech-to-text inside a Tauri appwritewithset.com
Hacker News · 1 points · 7 days ago