GigaSpeech 3 for Arabic speech recognition
39,000-hour GigaSpeech 3 corpus covers five Arabic dialects and reduces WER by 16.6% relative to prior systems.
Stories per day · 30 days
1 RSS
9 stories, newest first · one card per story
Stories tagged #arabic
DAR-MGSM benchmark tests math reasoning in Arabic dialects
Eleven models generally scored worse on culturally localized problems than on translated-only versions.
TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER
TII released Falcon-ASR, a 1.6B Arabic speech model reporting 20.92% average WER; weights are not public.
Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR
LoRA-adapted Whisper systems for NADI 2026 Arabic ASR reach 57.1%, 46.7%, and 14.49% WER on three subtasks.
Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
TII’s Falcon-Emirati is an LLM built for Emirati dialect, culture, and linguistic nuance.
Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
Muslim is a production Arabic voice AI for sourced Islamic knowledge, releasing a 6B router and TTS model.
QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge
QuranicMMLU offers 980 questions testing generative models on Quranic Arabic across five linguistic pillars.
Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
Nuha-Speech initiative builds general-purpose Arabic speech-LLMs using a 1.5M-sample speech QA corpus and fine-tuned Qwen-Omni variants.
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
Rosetta ranks 4th and 5th in AlexandriaX-2026 dialectal Arabic dialogue translation using a LoRA adapter on NileChat-3B, finding limited pretraining benefit.