Cohere has released Cohere Transcribe Arabic, an open-source model built for Arabic speech recognition. The 2-billion-parameter ASR model is, according to Cohere, the most accurate open-source Arabic speech-to-text system available. It targets the specific challenges of Arabic speech, including dialect variety, bilingual Arabic-English conversations, code-switching, and specialized vocabulary. Cohere says it outscores Whisper Large V3, the standard Cohere Transcribe model, and other systems in benchmarks.

The model ships under the Apache 2.0 license and is available on Hugging Face and through the Cohere API. More benchmarks and examples are on the Cohere blog.