跳到正文
Semafor· Mohammed Sergie·· 2026-10-08AI 評分45

Emirati dialect-trained AI models are released by Abu Dhabi's Technology Innovation Institute

Emirati dialect-trained AI models are released by Abu Dhabi's Technology Innovation Institute

AI 導讀

阿布扎比技術創新研究院推出以阿聯酋阿拉伯語方言訓練的 AI 模型,改善翻譯、轉錄及語音服務。其語音識別模型有 1.6 billion parameters,據該研究院稱,準確度高於一個 30-billion-parameter model。研究院希望透過本地方言、慣用語和文化參照訓練模型,減少翻譯錯誤,令 AI 更切合區內需要。

正文

Abu Dhabi’s Technology Innovation Institute, a state-run research body, released AI models trained on the Emirati Arabic dialect, improving translation, transcription, and voice-enabled services. The Falcon-Emirati model and related tools for speech recognition and extracting Arabic text from images and documents are relatively compact. The speech recognition model has 1.6 billion parameters, but is more accurate than a 30-billion-parameter model, according to TII.

AI training in Arabic has lagged behind other languages, partly because dialects vary widely and can be incomprehensible to people who know only the formal Arabic used in news reports and textbooks. This has made some machine translations comically inaccurate, sometimes turning innocuous words into vulgar references in English. TII aims to eliminate those errors by training models on local dialects, idioms, and cultural references, ultimately making AI more useful in the region.

— Mohammed Sergie

來源:Semafor · semafor.com