ocrs

Spec sheet

Purpose

ocrs is a Rust library and CLI tool for extracting text from images using OCR.Read 9 Oct 2026 · github.com

License

The repository lists Apache-2.0 and MIT licenses.Read 9 Oct 2026 · github.com

Automatic model download

On first run, the CLI downloads required models automatically and stores them in `~/.cache/ocrs`.Read 5 Oct 2026 · github.com

C interface

The project provides a C ABI with functions to recognize text and retrieve lines with bounding boxes.Read 9 Oct 2026 · github.com

CLI

The CLI can extract text from image files and write text, JSON layout data, or annotated PNG output.Read 9 Oct 2026 · github.com

Clipboard

The CLI supports reading an image from the system clipboard when installed with its clipboard feature.Read 9 Oct 2026 · github.com

Clipboard input

An optional `clipboard` feature enables OCR on images from the system clipboard.Read 5 Oct 2026 · github.com

Image types

The project aims to handle scanned documents, photos containing text, and screenshots with little or no preprocessing.Read 9 Oct 2026 · github.com

Implementation

Its neural network models are trained in PyTorch, exported to ONNX, and run using the RTen engine.Read 5 Oct 2026 · github.com

Installation

The CLI can be installed with Cargo using `cargo install ocrs-cli --locked`; installing it requires Rust and Cargo.Read 5 Oct 2026 · github.com

JavaScript

An alpha WebAssembly build is available for Node, browsers, and other WebAssembly runtimes.Read 9 Oct 2026 · github.com

Language support

It currently recognizes the Latin alphabet only, with support for more languages planned.Read 9 Oct 2026 · github.com

Library API

The project provides an OCR engine as a Rust library for use in Rust applications.Read 5 Oct 2026 · github.com

Maturity

The project describes itself as an early preview and says it may make more errors than commercial OCR engines.Read 9 Oct 2026 · github.com

Model customization

The C API can load custom models in ONNX format when built with the onnx feature.Read 9 Oct 2026 · github.com

Model data

The project says it uses open and liberally licensed datasets, and links to a separate repository with model, dataset, and custom training details.Read 5 Oct 2026 · github.com

OCR engine

Its neural network models are trained in PyTorch, exported to ONNX, and run using the RTen engine.Read 9 Oct 2026 · github.com

Output options

The CLI can save extracted text, return text and layout information as JSON, or create an annotated image showing detected words and lines.Read 5 Oct 2026 · github.com

Platform support

The project says it is intended to compile and run across platforms, including WebAssembly.Read 5 Oct 2026 · github.com

Project status

The project describes itself as an early preview and cautions that it may make more errors than commercial OCR engines.Read 5 Oct 2026 · github.com

Supported image input

The C API accepts raw 8-bit grayscale, RGB, or RGBA pixels, and callers are responsible for decoding PNG or JPEG images.Read 9 Oct 2026 · github.com

Training data

The project goal includes training on open and liberally licensed datasets.Read 9 Oct 2026 · github.com

Where Specifiction places it

• OCR API Software#23 of 297.5