pp-ocr

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

🍭 Image text recognition service based on Paddle OCR onnx models, compatible with OpenAI's chat/completions API.

An offline OCR utility, powered by PP-OCRv5 and PP-OCRv6 models via ONNX Runtime.

Chinese handwriting input engine for IBus with trackpad/touchpad support. Simplified & Traditional Chinese. Inspired by macOS Trackpad Handwriting.

Unofficial PP-OCR models for Core ML on Apple platforms, with reproducible conversion and measured optimization.

极简 Windows 框选 OCR：悬浮球 → 框选 → 百度 PP-OCR tiny → 文本进剪贴板。

Local-first AI image translation workbench with PP-OCR, llama.cpp and automatic text replacement

本地离线 OCR 工具：三种截屏识别（无障碍 / root / 录屏，自动挑选）、本地 HTTP 接口、MacroDroid / Tasker 插件、边缘滑动手势触发器，全程无需联网

Provide structured, machine-readable JSON of the official 2026 Thai election results extracted via OCR from Election Commission PDFs.