Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Repository Index
142,273 visible repositories in the index
1–24 of 31 · 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.
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ https://greasyfork.org/en/scripts/437569-cotrans-manga-image-translator-regular-edition
- manga
- anime
- ocr
- deep-learning
Multilingual Document Layout Parsing in a Single Vision-Language Model
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
- ocr
- deep-learning
- document-recognition
- text-detection
All-in-One Development Tool based on PaddlePaddle
- classification
- segmentation
- deployment
- ocr
A Unified Toolkit for Deep Learning Based Document Image Analysis
- layout-analysis
- deep-learning
- object-detection
- ocr
TranslatedYet another computer-aided comic/manga translation tool powered by deeplearning. Supports one-click machine translation and simple image/text editing.
- comics
- computer-aided-translation
- deep-learning
- manga
基于manga-image-translator 实现的开源漫画AI翻译桌面工具。支持日、韩、英文漫画自动处理,集成OpenAl、Gemini等多翻译引擎;实现OCR文字检测、原文擦除、AI翻译、图像修复、译文排版完整链路,自带可视化编辑器,支持自定义文本样式,一键部署开箱即用。
- automated-translation
- comic-translation
- gemini
- image-translator
A Repo For Document AI
- document-parser
- document-image-analysis
- table-recognition
- ocr
Translated[Captcha Recognition - Training] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
- captcha-recognition
- tensorflow-tutorials
- ocr
- tensorflow
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
Optical character recognition for Japanese text, with the main focus being Japanese manga
- ocr
- japanese
- manga
- transformers
在保留版面、公式与结构的前提下进行 PDF 翻译,适用于科研与技术文档
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.
Convolutional recurrent network in pytorch
- neural-network
- scene-texts
- recognition
Convert images of LaTex math equations into LaTex code.
- pytorch
- deep-learning
- transformer
- encoder-decoder
基于PaddleOCR重构,并且脱离PaddlePaddle深度学习训练框架的轻量级OCR,推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
- document-layout-analysis
- license-plate-recognition
- ocr
- onnx-models
Using neural networks to build an automatic number plate recognition system
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
- deep-learning
- layout-analysis
- ocr
- python
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of different parts of PDF pages, identifying the elements such as texts, titles, pictures, tables and so on.