Search

Across 58925 posts, found1posts across1collections

All Collections 1 Posts 1

SortTitle matches first, then newest

Matching collections

Related editions in the archive

No.004AI Product Updates: New Features and ReleasesUpdated 12 hours ago · Today +701 matches

Matching posts

Matching terms are highlighted

Wispr Flow releases Canto speech model with 3.4% WER on real-time dictation

Wispr Flow's new proprietary speech model Canto reached a 3.4% word error rate on 9.8 hours of English Flow dictations from more than 2,300 speakers, the lowest among the models tested.

wispr-flow@WisprFlow　Filed in No.004

2026.09.18

Showing1of1posts