Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic
This addresses the problem of limited Arabic ASR resources for researchers and developers, offering open-source models that improve performance for both modern and classical variants, though it is incremental as it builds on existing architectures.
The paper tackles the lack of public Arabic ASR models by introducing a universal methodology for Arabic speech and text processing, training two FastConformer-based models: one for Modern Standard Arabic (MSA) that sets a new SOTA benchmark, and the first unified public model for both MSA and Classical Arabic (CA) that achieves SOTA accuracy with diacritics for CA while maintaining strong MSA performance.
Despite Arabic being one of the most widely spoken languages, the development of Arabic Automatic Speech Recognition (ASR) systems faces significant challenges due to the language's complexity, and only a limited number of public Arabic ASR models exist. While much of the focus has been on Modern Standard Arabic (MSA), there is considerably less attention given to the variations within the language. This paper introduces a universal methodology for Arabic speech and text processing designed to address unique challenges of the language. Using this methodology, we train two novel models based on the FastConformer architecture: one designed specifically for MSA and the other, the first unified public model for both MSA and Classical Arabic (CA). The MSA model sets a new benchmark with state-of-the-art (SOTA) performance on related datasets, while the unified model achieves SOTA accuracy with diacritics for CA while maintaining strong performance for MSA. To promote reproducibility, we open-source the models and their training recipes.