Gogosseract is a reimplementation of the gosseract library, which eliminates the use of CGo and instead utilizes Tesseract compiled to WebAssembly (WASM) using Emscripten via Wazero. Tesseract is a powerful Optical Character Recognition (OCR) library written in C++. The WASM is generated from a personal fork of robertknight’s tesseract-wasm project. It’s important to note that the compiled Tesseract only supports the LSTM neural network OCR engine, not the “classic” Tesseract. To improve accuracy, Tesseract recommends preprocessing input images. The code examples demonstrate how to use Gogosseract to parse text from an image and how to use a pool of Tesseract workers for thread-safe concurrent image parsing.
https://github.com/Danlock/gogosseract