Ocr

A specialized UI tool for automated manga translation that builds on manga-image-translator, combining OCR, AI translation engines (OpenAI, Gemini,...

iOS OCR Server turns an iPhone into a local OCR endpoint using Apple's Vision Framework, eliminating cloud dependencies and privacy concerns. It...

OpenDataLoader PDF is a specialized PDF parser designed for AI-ready data extraction and PDF accessibility automation. It extracts structured...

React Native ExecuTorch enables on-device AI model inference in React Native applications using Meta's ExecuTorch framework, supporting computer...

MinerU is a document parsing tool that converts PDFs, Word files, PowerPoints, and spreadsheets into LLM-ready Markdown or JSON, with capabilities...

LiteParse is a fast, lightweight Rust-based PDF and document parser that performs local spatial text extraction with bounding boxes, offering...

RapidOCR is a production-grade, open-source OCR toolkit supporting multiple inference backends (ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT,...

STranslate is a desktop translation and OCR tool built with WPF, designed for Windows users who need quick text translation and optical character...

PDF Craft converts PDF files—especially scanned books—into Markdown or EPUB formats using DeepSeek OCR for document recognition. It excels at...

A curated collection of practical AI projects demonstrating OCR systems, retrieval-augmented generation (RAG), multi-agent workflows, and specialized...

YomiToku is a specialized Python package for AI-powered optical character recognition and document layout analysis designed specifically for Japanese...

LunaTranslator is a specialized visual novel translator for Windows that extracts and translates in-game text using HOOK injection, OCR, and emulator...

TRex is a macOS menu bar application that uses OCR to extract text from any visible screen content—PDFs, images, videos, screen shares—directly to...

PaddleOCR2Pytorch converts PaddleOCR models to PyTorch format, enabling OCR inference across detection, recognition, and document structure parsing....

ShareX is a free, open-source Windows desktop application for screen capture, recording, and file sharing with built-in editing, annotation, and...

RetainPDF is a specialized PDF translation tool designed to preserve layout, formulas, and structure while translating documents—particularly...

Kraken is a specialized OCR engine optimized for historical documents and non-Latin scripts, offering trainable layout analysis, multi-script support...

paperless-gpt integrates AI-powered OCR and document processing with paperless-ngx, using LLMs (OpenAI, Ollama) and specialized services (Google...

RuVector is a self-learning vector database and memory system written in Rust, designed for AI workloads with local model inference, graph neural...

Translumo is a real-time screen translator for games and video subtitles that combines multiple OCR engines with machine learning to select the...

MouseTooltipTranslator is a browser extension for Chrome, Edge, and Firefox that enables instant translation of text via mouseover hover or...

X-AnyLabeling is a desktop application for image and video annotation with integrated AI models (SAM, YOLO, GroundingDINO, OCR, etc.) that automates...

A structured educational repository providing hands-on Jupyter notebooks and code for learning AI fundamentals, from math and PyTorch through...

PaddleOCR is an OCR toolkit and document AI engine built on PaddlePaddle that extracts structured data from images and PDFs, supporting 100+...

DocStrange is a Python library for converting documents (PDF, DOCX, PPTX, XLSX, images, URLs) into clean Markdown, JSON, CSV, and HTML with...

PaddleX is a low-code AI development tool built on PaddlePaddle that integrates 270+ pre-trained models across document analysis, OCR, object...

PyMuPDF is a high-performance Python library for PDF and document processing, built on the MuPDF C engine, offering data extraction, conversion,...

BallonsTranslator is a deep-learning-powered tool designed specifically for translating comics and manga, automating text detection, inpainting, OCR,...

Skill Seekers is a Python tool that extracts documentation from websites, GitHub repositories, PDFs, and 10+ other sources, transforming them into...

LLPlayer is a desktop video player built specifically for language learners, offering dual subtitles, AI-generated subtitles via Whisper, real-time...