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.
More from Apps
- Dia says its browser is coming to Windows this fall — brianmichel · 2026-07-30
- Dropbox Pilots Leadpoet's AI Sales Intelligence Platform — markjeffrey · 2026-07-30
- Amasad says Replit Design marks the start of a post-prompt era — amasad · 2026-07-30
- ComfyUI users are still hunting for a queue manager that won’t break — CelestVestra · 2026-07-30
- LlamaParse adds one-click batch parsing for up to 10,000 files in the UI — llama_index · 2026-07-30
- Harvey Open-Sources Legal Agent Benchmark Spanning 1,200 Tasks — baseten · 2026-07-30