# Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

arXiv: https://arxiv.org/abs/2411.17835 · HTML: https://mlsanity.com/paper/2411.17835/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Builds on (most cited first, 10 of 10)

- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model](https://mlsanity.com/paper/2310.05126/) (2023)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding](https://mlsanity.com/paper/1909.04948/) (2019)
- [Focus Anywhere for Fine-grained Multi-page Document Understanding](https://mlsanity.com/paper/2405.14295/) (2024)

## Built on by (most cited first, 4 of 4)

- [Tokens with Meaning: A Hybrid Tokenization Approach for Turkish](https://mlsanity.com/paper/2508.14292/) (2025)
- [SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition](https://mlsanity.com/paper/2505.24600/) (2025)
- [Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding](https://mlsanity.com/paper/2511.04699/) (2025)
- [A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation](https://mlsanity.com/paper/2509.02864/) (2025)

## Abstract (arXiv)

We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat, and arabic-large-nougat. These models are fine-tuned on a synthetic dataset, arabic-img2md, comprising 13.7k pairs of Arabic book pages and their Markdown representations. Key contributions include the Aranizer-PBE-86k tokenizer, designed for efficient tokenization, and the use of torch.bfloat16 precision with Flash Attention 2 for optimized training and inference. Our models achieve state-of-the-art performance, with arabic-large-nougat delivering the highest Markdown Structure Accuracy and the lowest Character Error Rate. Additionally, we release a large-scale dataset containing 1.1 billion Arabic tokens extracted from over 8,500 books using our best-performing model, providing a valuable resource for Arabic OCR research. All models, datasets, and code are open-sourced and available at https://github.com/MohamedAliRashad/arabic-nougat.