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

TL;DR

Typhoon OCR is an open, lightweight vision-language model specifically designed for Thai and English document extraction, achieving high accuracy across diverse real-world Thai documents with lower computational costs.

Contribution

The paper introduces Typhoon OCR, a novel open VLM tailored for Thai document extraction, utilizing a multi-stage dataset construction pipeline and achieving competitive performance.

Findings

Achieves performance comparable to proprietary models on Thai documents.

Reduces computational cost with a compact, inference-efficient model.

Demonstrates effective text and layout extraction across diverse Thai document types.

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.