QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation
This work addresses the persistent problem of accurate Arabic text recognition for users in document processing and research, delivering a marked improvement in accuracy and efficiency.
The paper tackled the challenge of Arabic script OCR by developing Qari-OCR, a series of vision-language models fine-tuned on synthetic datasets, achieving a new open-source state-of-the-art with a Word Error Rate of 0.160 and Character Error Rate of 0.061 on diacritically-rich texts.
The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (OCR). We present Qari-OCR, a series of vision-language models derived from Qwen2-VL-2B-Instruct, progressively optimized for Arabic through iterative fine-tuning on specialized synthetic datasets. Our leading model, QARI v0.2, establishes a new open-source state-of-the-art with a Word Error Rate (WER) of 0.160, Character Error Rate (CER) of 0.061, and BLEU score of 0.737 on diacritically-rich texts. Qari-OCR demonstrates superior handling of tashkeel, diverse fonts, and document layouts, alongside impressive performance on low-resolution images. Further explorations (QARI v0.3) showcase strong potential for structural document understanding and handwritten text. This work delivers a marked improvement in Arabic OCR accuracy and efficiency, with all models and datasets released to foster further research.