AIWispr Flow introduces Canto for real-time dictation
Wispr Flow says its new speech model achieved a 3.4% word error rate—the lowest among the models it tested in its own evaluation.
TLDR
Wispr Flow announced Canto as its latest speech model for real-time dictation. The company says it evaluated Canto on 9.8 hours of English Flow dictations from more than 2,300 speakers, achieving a 3.4% word error rate—the lowest among the models it tested.
Combined views
590
1 Source, first seen 11h ago
Wispr Flow introduces Canto for real-time dictation
Wispr Flow says its new speech model achieved a 3.4% word error rate—the lowest among the models it tested in its own evaluation.
TLDR
Wispr Flow announced Canto as its latest speech model for real-time dictation. The company says it evaluated Canto on 9.8 hours of English Flow dictations from more than 2,300 speakers, achieving a 3.4% word error rate—the lowest among the models it tested.