Download
dots.ocr is a cutting-edge multilingual document parsing system built on a unified vision-language model that combines layout detection, text recognition, and structural understanding into a single architecture. Unlike traditional OCR pipelines that rely on multiple specialized components, dots.ocr integrates these processes end-to-end, reducing error propagation and improving consistency across tasks. The model is designed to recognize virtually any human script, making it highly effective for global and low-resource language scenarios. It achieves state-of-the-art performance on document parsing benchmarks while maintaining a relatively compact model size, demonstrating efficiency without sacrificing accuracy. Beyond standard OCR tasks, it extends its capabilities to parse complex visual elements such as charts, diagrams, and web interfaces, converting them into structured outputs like SVG code.
Features
- Unified vision-language model for OCR and layout parsing
- Multilingual support across diverse scripts and languages
- End-to-end document understanding including structure and reading order
- Conversion of graphics and charts into structured SVG code
- High performance on document parsing benchmarks
- Flexible deployment with GPU inference and vLLM integration
Project Samples
