A community-supported supercharged document management system: scan, index and archive all your documents
Repository Index
99,825 visible repositories in the index
1–17 of 17 · Most stars
OCR, layout analysis, reading order, table recognition in 90+ languages
- deep-learning
- document-ai
- layout-analysis
- multilingual-ocr
OCR model that handles complex tables, forms, handwriting with full layout.
Multilingual Document Layout Parsing in a Single Vision-Language Model
📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
- ocr
- onnxruntime
- crnn
- dbnet
All-in-One Development Tool based on PaddlePaddle
- classification
- segmentation
- deployment
- ocr
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
- fcos
- blendmask
- abcnet
- object-detection
OCR powered screen-capture tool to capture information instead of images
- screenshot
- tool
- multiplatform
- ocr
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
- chart-understanding
- document-understanding
- mllm
- multimodal
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.
Get clean data from tricky documents, powered by vision-language models ⚡
- multimodal
- large-language-models
- scrapers
基于Pytorch的OCR工具库,支持常用的文字检测和识别算法
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
Meta Self-learning for Multi-Source Domain Adaptation: A Benchmark
- text-recognition
- ocr-recognition
- domain-adaptation
- multi-source-domain-adaptation
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.