OCRModule

TypeScript API implementation of the useOCR hook.

API Reference

• For detailed API Reference for OCRModule see: OCRModule API Reference.
• For all alphabets available in ocr out-of-the-box in React Native ExecuTorch see: OCR Supported Alphabets.

High Level Overview

import { OCRModule, OCR_ENGLISH } from 'react-native-executorch';
const imageUri = 'path/to/image.png';

// Creating an instance and loading the model
const ocrModule = await OCRModule.fromModelName(OCR_ENGLISH);

// Running the model
const detections = await ocrModule.forward(imageUri);

Methods

All methods of OCRModule are explained in details here: OCRModule API Reference

Loading the model

Use the static fromModelName factory method. It accepts a namedSources object (e.g. OCR_ENGLISH) containing:

• modelName - Model name identifier.
• detectorSource - Location of the used detector.
• recognizerSource - Location of the used recognizer.
• language - Language used in OCR.

And an optional onDownloadProgress callback. It returns a promise resolving to an OCRModule instance.

For more information on loading resources, take a look at loading models page.

Running the model

To run the model, use the forward method. It accepts one argument — the image to recognize. The image can be a remote URL, a local file URI, a base64-encoded image (whole URI or only raw base64), or a PixelData object (raw RGB pixel buffer). The method returns a promise resolving to an array of OCRDetection objects, each containing the bounding box, recognized text, and confidence score.

For real-time frame processing, use runOnFrame instead.