TII introduces Falcon-ASR for Arabic and Emirati speech
Technology Innovation Institute (TII) has introduced Falcon-ASR, a 1.6B-parameter speech recognition model focused on Arabic, including the Emirati dialect. TII says it supports English, French, Spanish and Portuguese, offers word-level timestamps, and achieved a 20.92% average WER across six Arabic test sets in its evaluation.
It adds a multilingual speech model with a specific focus on dialectal Arabic and Emirati transcription.
Arabic WER: 20.92% · Parameters: 1.6B · Emirati WER (TII evaluation): 22.73%
We’re introducing Falcon-ASR, our 1.6 billion parameter speech recognition model for Arabic, with a particular focus on the Emirati dialect. Developed at the Technology Innovation Institute (TII) in Abu Dhabi, it also supports English, French, Spanish and Portuguese.
In our evaluation, Falcon-ASR achieved an average word error rate of 20.92% across six Arabic test sets, compared with the best published result of 23.17% in the leaderboard snapshot we used. On our internal Emirati evaluation, it recorded the lowest word and character error rates among the systems we compared.
We also support word-level timestamps for transcriptions, linking each transcribed word to its position in the audio.