RapidAI/RapidOcrOnnx

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

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

Rust multi‑backend OCR/VLM engine (DeepSeek‑OCR-1/2, PaddleOCR‑VL, DotsOCR) with DSQ quantization and an OpenAI‑compatible server & CLI – run locally without Python.

Pure-Rust, CPU-only OCR engine for Baidu Unlimited-OCR (a DeepSeek-OCR-derived 3B MoE VLM). Five-model zoo, custom int8 kernels, no ML framework, no Python, no GPU.

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr

OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR

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.

OpenMMLab Text Detection, Recognition and Understanding Toolbox

a lightweight C++ cross-platform vision inference library,support YOLOv10/v11/v26、PaddleOCR,using ONNXRuntime/RKNPU with multiple exectuion providers