Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

2026-01-21

AI Summary

Current vision-language models exhibit limited performance in Thai document understanding, primarily due to non-Latin script characteristics, the absence of explicit word boundaries, and highly unstructured layouts. To address these challenges, this work proposes Typhoon OCR—the first lightweight, open-source vision-language model (VLM) specifically optimized for Thai. By integrating conventional OCR, VLM-driven data reconstruction, and synthetic data generation, Typhoon OCR establishes an end-to-end framework that jointly models text transcription, layout reconstruction, and document-level structural consistency. This approach substantially reduces reliance on metadata while enabling efficient deployment. Evaluated across diverse real-world scenarios—including financial reports, government forms, books, infographics, and handwritten documents—Typhoon OCR v1.5 achieves extraction and layout reconstruction accuracy on par with or surpassing that of leading closed-source large models, at a significantly lower computational cost.

Technology Category

• Computer Vision: Language and Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional challenges due to script complexity from non-latin letters, the absence of explicit word boundaries, and the prevalence of highly unstructured real-world documents, limiting the effectiveness of current open-source models. This paper presents Typhoon OCR, an open VLM for document extraction tailored for Thai and English. The model is fine-tuned from vision-language backbones using a Thai-focused training dataset. The dataset is developed using a multi-stage data construction pipeline that combines traditional OCR, VLM-based restructuring, and curated synthetic data. Typhoon OCR is a unified framework capable of text transcription, layout reconstruction, and document-level structural consistency. The latest iteration of our model, Typhoon OCR V1.5, is a compact and inference-efficient model designed to reduce reliance on metadata and simplify deployment. Comprehensive evaluations across diverse Thai document categories, including financial reports, government forms, books, infographics, and handwritten documents, show that Typhoon OCR achieves performance comparable to or exceeding larger frontier proprietary models, despite substantially lower computational cost. The results demonstrate that open vision-language OCR models can achieve accurate text extraction and layout reconstruction for Thai documents, reaching performance comparable to proprietary systems while remaining lightweight and deployable.

Problem

• Thai document extraction
• vision-language model
• OCR
• low-resource language
• unstructured documents

Innovation

• vision-language model
• Thai OCR
• document extraction
• layout reconstruction
• open-source OCR