Cohere Releases Open-Source Arabic Speech Recognition Model
JayAlammar · x · 2026-07-07
Cohere has released an Arabic Transcribe model, claiming it to be the best open-source Arabic speech-to-text model available. It accommodates various Arabic dialects and has topped the Open Universal Arabic ASR Leaderboard. The model supports speech conversion between Arabic and English, as well as the recognition of English spoken with an Arabic accent, aiming to help developers and enterprises build robust voice experiences.
Related event: Cohere Releases Open-Source Arabic ASR Model, Topping Leaderboards(8 posts)→
More from Multimodal
- CapCut plugin launches in early access on ChatGPT desktop, mobile and web due mid-November — HeyZoyaKhan · 2026-10-27
- Magnific teases October 28 release: 'We're making it move' — cuenca · 2026-10-27
- Midjourney --sref demo: retro Americana Batman art series — gizakdag · 2026-10-27
- AI video is a new medium, not cinema or animation — and it's perfect for depicting dreams — Kyrannio · 2026-10-27
- Dad turns his toddler's 31-year-old quote into a song via SUNO kids' choir — NathanpmYoung · 2026-10-27
- Band's local-AI music video hits 200k views: 900 generations kept 64, 3-second clips beat face drift — Hwang0500 · 2026-10-27