قياس Whisper على التعرف الكلامي العربي المتنوع

يكشف حدود التعميم اللهجي لأقوى نماذج الكلام: صفر-shot ممتاز على الفصحى ومنهار على اللهجات — دليل عملي لفرق العربية.

بروتوكول تقييم n-shot على معظم بيانات العربية المتاحة مع بيانات تقييم جديدة مطورة لخمس لهجات غير مرئية.

نقيّم Whisper على معظم بيانات الكلام العربية المتاحة بإعدادات صفر/قليل/كامل الضبط، ونكشف تدهوره الحاد على خمس لهجات غير مرئية (الجزائر، الأردن، فلسطين، الإمارات، اليمن).

Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings. However, it is not clear how Whisper would fare under diverse conditions even on languages it was evaluated on such as Arabic. In this work, we address this gap by comprehensively evaluating Whisper on several varieties of Arabic speech for the ASR task. Our evaluation covers most publicly available Arabic speech data and is performed under n-shot (zero-, few-, and full) finetuning. We also investigate the robustness of Whisper under completely novel conditions, such as in dialect-accented standard Arabic and in unseen dialects for which we develop evaluation data. Our experiments show that although Whisper zero-shot outperforms fully finetuned XLS-R models on all datasets, its performance deteriorates significantly in the zero-shot setting for five unseen dialects (i.e., Algeria, Jordan, Palestine, UAE, and Yemen).