studio-dots-ai/dots.ocr

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9090 stars · 804 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

dots.ocr is a 1.7B-parameter vision-language model for multilingual document layout parsing, converting documents into structured output with state-of-the-art OCR performance. It also handles chart-to-SVG conversion, web screen parsing, and scene text spotting.

Use cases

• parse documents from pdfs into structured text
• extract text from scanned documents in multiple languages
• convert charts and diagrams to svg code
• detect and read scene text in images
• parse document layout with tables and formulas
• ocr for multilingual scripts

When to choose

• you need a single compact model for multilingual document parsing
• you want layout-aware extraction including tables, formulas, and reading order
• you need chart-to-SVG conversion or scene text spotting alongside OCR

When to avoid

• you need a lightweight CPU-only OCR solution
• you only need simple text extraction without layout understanding
• you cannot run GPU inference for vision-language models

Facets

library · maturity active

ocr machine-learning pdf image-processing llm-inference computer-vision pdf deep-learning large-language-models python cross-platform vision-language-model document-parsing document-layout-analysis multilingual-ocr svg-generation scene-text-detection natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="studio-dots-ai/dots.ocr")