Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition

TL;DR

Qalam is a new multimodal foundation model for Arabic OCR and HWR that achieves state-of-the-art accuracy, effectively handles diacritics, and processes high-resolution inputs, advancing Arabic script recognition technology.

Contribution

Introduces Qalam, a novel multimodal model based on SwinV2 and RoBERTa, specifically designed for Arabic OCR and HWR, with superior performance and capabilities.

Findings

Achieves 0.80% WER in HWR and 1.18% in OCR tasks.

Trained on over 4.5 million images and 60k synthetic image-text pairs.

Demonstrates exceptional handling of Arabic diacritics and high-resolution inputs.

Abstract

Arabic Optical Character Recognition (OCR) and Handwriting Recognition (HWR) pose unique challenges due to the cursive and context-sensitive nature of the Arabic script. This study introduces Qalam, a novel foundation model designed for Arabic OCR and HWR, built on a SwinV2 encoder and RoBERTa decoder architecture. Our model significantly outperforms existing methods, achieving a Word Error Rate (WER) of just 0.80% in HWR tasks and 1.18% in OCR tasks. We train Qalam on a diverse dataset, including over 4.5 million images from Arabic manuscripts and a synthetic dataset comprising 60k image-text pairs. Notably, Qalam demonstrates exceptional handling of Arabic diacritics, a critical feature in Arabic scripts. Furthermore, it shows a remarkable ability to process high-resolution inputs, addressing a common limitation in current OCR systems. These advancements underscore Qalam's potential as a leading solution for Arabic script recognition, offering a significant leap in accuracy and efficiency.