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 Learning3 min read

Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs

InfoQ (AI, ML & Data)
Machine Learning5 min read

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost
Machine Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources