#supervised fine-tuning

1 story

#canto #dictation #noisy audio #real-world audio #reinforcement learning #speech model #speech recognition #speech transcription #wispr advanced interfaces lab #wispr flow #word error rate

Canto: speech model built for real dictation
Wispr Flow's new speech model outperforms competitors on messy, real-world audio where people actually dictate.
Wisprflow · 3m