Superwhisper adds Cohere Transcribe for local dictation with 5.35% WER
aidangomez · x · 2026-07-29
Superwhisper has partnered with Cohere to add Transcribe to its model library for local dictation.
The post says the 2B-parameter model is one of the top-ranked ASR models on Hugging Face’s Open ASR leaderboard, with a 5.35% average WER that drops to 1.25% on clean audio. It is described as beating Whisper Large v3 on accuracy and throughput, supporting 14 languages, and running on-device under Apache 2.0.
Related event: Cohere Transcribe Integrates with Superwhisper for Offline Dictation(3 posts)→
More from Apps
- Gamma 5 Recap Slides Quote Verbatim and Cite Sources on Every Bullet — aakashgupta · 2026-10-16
- Hands-on With Gamma 5: Feed It a Keynote, Get a Six-Slide Recap With Zero Questions — aakashgupta · 2026-10-16
- Why All AI-Generated Decks Look Alike: Six-Word Prompts Leave Too Many Blanks — aakashgupta · 2026-10-16
- Duke Study of 4,439 People Finds Coworkers Quietly Rate AI Users as Lazier — aakashgupta · 2026-10-16
- Academic shares workshop slides and code for practical AI workflows in research — JeremyNguyenPhD · 2026-10-16
- Dev Building AI Nutrition Coach for Travelers Open-Sources Mealsight Vision+Voice Workflow — HowDevelop · 2026-10-16