Cohere's 2B Arabic model beats Whisper at code-switching
cohere released an apache 2.0 licensed 2b parameter model that it claims beats whisper large v3 on arabic benchmarks, addressing dialect diversity and code-switching.
cohere released cohere transcribe arabic, a 2-billion-parameter open-source asr model optimized for dialect variety, bilingual code-switching, and specialized vocabulary. licensed under apache 2.0, the model is accessible via hugging face and the cohere api, claiming to outperform whisper large v3 and standard cohere transcribe on accuracy. human ratings indicate significant gains in dialect faithfulness and handling mixed arabic-english inputs. this signals a push towards specialized, high-performance open-source models for low-resource or complex linguistic scenarios.