TII releases Falcon-ASR, a 1.6B Arabic speech recognition model with Emirati focus

AITechnology Innovation Institute (TII) of Abu Dhabi releases Falcon-ASR, a 1.6B-parameter speech recognition model that transcribes Arabic, including the Emirati dialect, plus English, French, Spanish and Portuguese. In TII's own evaluation, it posts a 20.92% average word error rate across 6 Arabic test sets, 2.25 points better than Audar-ASR-V1-Turbo. The model is available only as a hosted Hugging Face demo, with no weights, license or API published yet.

AIThe Technology Innovation Institute introduces Falcon-ASR, a 1.6 billion parameter speech recognition model for Arabic with a focus on the Emirati dialect. On six Arabic test sets it reports an average word error rate of 20.92%, versus 23.17% for the best published leaderboard result it compared against. The model also transcribes English, French, Spanish and Portuguese with the same weights, and a demo Space is available while API access and native apps are planned.