OmniOCR: Generalist OCR for Ethnic Minority Languages

TL;DR

OmniOCR is a universal OCR framework designed for ethnic minority languages, utilizing dynamic adaptation and sparsity regularization to achieve high accuracy and efficiency in recognizing diverse scripts with limited data.

Contribution

The paper introduces Dynamic LoRA and a sparsity regularization technique, enabling effective low-resource script recognition with minimal additional inference cost.

Findings

Outperforms zero-shot foundation models on minority scripts

Achieves 39%-66% accuracy improvement over baselines

Maintains model efficiency with compact adaptation

Abstract

Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR.