TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER
The Technology Innovation Institute (TII) in Abu Dhabi has released Falcon-ASR, a 1.6B parameter Arabic speech recognition model.
Proof1 independent outlet
Key points
- In TII’s evaluation, Falcon-ASR posts a 20.92% average word error rate (WER) across 6 Arabic test sets.
- Performance: Lowest Arabic and Emirati WER in TII’s own comparisons, with solid English results.
- Falcon-ASR is a speech-to-text model from TII that converts spoken Arabic and 4 other languages into text.
- How does Falcon-ASR handle Arabic dialects?
Sources (1)
- [1]TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WERMarkTechPost · Oct 12, 03:16 AM
The Technology Innovation Institute (TII) in Abu Dhabi has released Falcon-ASR, a 1.6B parameter Arabic speech recognition model.
In TII’s evaluation, Falcon-ASR posts a 20.92% average word error rate (WER) across 6 Arabic test sets.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 10, 2026vllm-sr/d3
- Oct 9, 2026autotrust/GLM5.3-Flash-E192-DGX-Spark
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 9, 2026AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis
- Oct 8, 2026Understanding Jev, the new model everyone is talking about