4965898/UmiOCR-PP-OCRv6-ONNX-Plugin

为Umi-OCR提供多厂商AI云端识别能力的插件。集成OpenAI/Gemini/Grok等，作为离线OCR的强力补充，提供更高精度和更广泛的语言支持。

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.

C++ inference implementation of PaddleOCR

纯 C# PP-OCRv6 推理库：多平台手写 Kernel / GEMM 等算子、超高性能、低内存需求、超高准确率。 自带托管 ONNX 解释器，不依赖 Paddle Inference、ONNX Runtime 或 OpenCV 原生库。

轻量级、无运行时依赖的纯 C PP-OCR 推理运行时，支持 PP-OCRv6 Tiny/Small/Medium、DET/CLS/REC、完整 OCR、SIMD 与 WebAssembly。 Lightweight dependency-free pure-C PP-OCR runtime with PP-OCRv6 Tiny/Small/Medium, full OCR, SIMD and WebAssembly.

📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

rapidocr onnx cpp

High accurate text detection (OCR) Javascript/Typescript library that runs on Node.js, Browser, React Native and C++. Based on PaddleOCR and ONNX runtime

Lightweight, probably the fastest PaddleOCR SDK in TypeScript. Multilingual Support. Runs anywhere JavaScript runs: Node.js, Bun, Deno, mobile react-native, web browsers, web worker, and browser extensions. Docker & CLI supported. The official SDK is browser-only.