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. It focuses on the Emirati dialect and also transcribes English, French, Spanish and Portuguese. In TII’s evaluation, Falcon-ASR posts a 20.92% average word error rate (WER) across 6 Arabic test sets. That beats the best published entry in TII’s leaderboard snapshot by 2.25 points. For developers building Arabic voice products, the catch is access: today i
Get smart on it
A speech recognition model called Falcon-ASR has been released for converting spoken Arabic and four other languages into text with word-level timestamps. The model achieved a 20.92% word error rate on Arabic benchmarks, outperforming comparable systems, and was specifically trained on Emirati dialect alongside Modern Standard Arabic and other regional varieties. Currently the model is only available as a hosted demonstration with no published weights or license, though an API is planned for future release. The model's compact size of 1.6 billion parameters allows it to match or exceed the performance of larger competing systems on Arabic and Emirati speech recognition tasks.
Related news
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
The vLLM Semantic Router team has released Decision 3.0, a family of multimodal decision models. Decision 3.0 multimodal decision models read text, JSON and images, then answer typed questions about them. There are 5 sizes, from 0.8B to 27B, all under Apache-2.0. For developers, this is a fast way to classify, route and gate requests without parsing generated text. TL;DR Size: 5 models: d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), d3 (26.09B). Context length: not
Meet Cloudflare Clef-omni: A 30B-A3B Multimodal Decision Model for Audio, Video, Image and Text
Cloudflare has released Clef-omni, a new open-weight member of its Clef decision model family. Clef-omni is a Cloudflare decision model that scores text, images, audio and video in 1 call. It arrived on October 9, 2026, 8 days after the original Clef and Clef-flash launch. The same update cut Clef-flash pricing below TypeSafe’s Jev and made hosted Clef roughly 2x faster. For developers, this removes the transcription and captioning steps that multimodal agent pipelines usually need. TL
