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

MarkTechPost
Read the full article
The Technology Innovation Institute (TII) launched Falcon-ASR, a 1.6B parameter Arabic speech recognition model focused on the Emirati dialect, achieving a 20.92% average word error rate across six Arabic test sets, outperforming previous models. Falcon-ASR also transcribes English, French, Spanish, and Portuguese, but currently is accessible only via a hosted demo without published weights or API.

More on this story


More in Machine Learning

Machine Learning7 min read

Can AI help solve the COBOL code crisis?

The Verge
Machine Learning3 min read

Most of Anthropic’s Q3 revenue came from models that barely existed six months ago

The New Stack (AI)
Machine Learning4 min read

Exclusive: iMerit launches platform to connect AI developers with specialized domain experts

Covered by 2 sources