FUNDING · MODELS · #1667
TII releases Falcon‑ASR 1.6B, an Arabic-focused speech recognition model
The Technology Innovation Institute (TII) announced Falcon‑ASR, a 1.6 billion‑parameter multilingual speech recognition model trained with emphasis on Emirati and other Arabic dialects. TII reports an average Arabic WER of 20.92% across six public test sets (versus a 23.17% best published snapshot), 22.73% WER and 10.19% CER on an internal Emirati evaluation (4.07 p.p. better than Qwen3‑Omni), and a 5.74% mean WER on seven public English test sets; the model also provides word‑level timestamps and a Hugging Face demo.
KEY POINTS
- The Technology Innovation Institute (TII) announced Falcon‑ASR, a 1.6 billion‑parameter multilingual speech recognition model trained with emphasis on Emirati and other Arabic dialects.
- TII reports an average Arabic WER of 20.92% across six public test sets (versus a 23.17% best published snapshot), 22.73% WER and 10.19% CER on an internal Emirati evaluation (4.07 p.p.
- better than Qwen3‑Omni), and a 5.74% mean WER on seven public English test sets; the model also provides word‑level timestamps and a Hugging Face demo.
WHY IT MATTERS
A dialect‑focused ASR that improves published Arabic leaderboard WER and shows stronger Emirati performance could materially expand usable speech recognition for underrepresented Arabic dialects and real‑world noisy conditions.