Skip to content
NewA calmer, faster ZeroHour

TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER

MarkTechPostby Asif Razzaq ()1
AI summary · grok-4.7Summaries by Vani AI

TII released Falcon-ASR, a 1.6B Arabic speech model reporting 20.92% average WER; weights are not public.

The Technology Innovation Institute released Falcon-ASR, a 1.6 billion-parameter automatic speech recognition model for Arabic with an Emirati focus. It reports a 20.92% average word error rate across six Arabic test sets. Model weights and an API are not yet available.

Key facts
  • Falcon-ASR is a 1.6 billion-parameter Arabic speech recognition model.
  • It reports 20.92% average word error rate on six Arabic test sets.
  • The model has an Emirati Arabic focus.
  • Weights and an API are not yet available.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

TII has released Falcon-ASR, a 1. 6B speech recognition model for Arabic with an Emirati focus. It reports 20.

MarkTechPost

By Asif Razzaq · marktechpost.com

Read the full article at MarkTechPost

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.