index.js

import { MgpstrForSceneTextRecognition, MgpstrProcessor, RawImage } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@3.1.0';

// Since we will download the model from the Hugging Face Hub, we can skip the local model check
env.allowLocalModels = false;

// Reference the elements that we will need
const status = document.getElementById('status');
const fileUpload = document.getElementById('upload');
const imageContainer = document.getElementById('container');
const example = document.getElementById('example');

// Load Model
status.textContent = 'Loading model...';
const model_id = 'onnx-community/mgp-str-base';
const model = await MgpstrForSceneTextRecognition.from_pretrained(model_id);
const processor = await MgpstrProcessor.from_pretrained(model_id);
status.textContent = 'Ready';

// Load image from the IIIT-5k dataset
const EXAMPLE_URL = "https://i.postimg.cc/ZKwLg2Gw/367-14.png";

example.addEventListener('click', (e) => {
    e.preventDefault();
    detect(EXAMPLE_URL);
});

fileUpload.addEventListener('change', function (e) {
    const file = e.target.files[0];
    if (!file) {
        return;
    }

    const reader = new FileReader();

    // Set up a callback when the file is loaded
    reader.onload = e2 => detect(e2.target.result);

    reader.readAsDataURL(file);
});


// Detect objects in the image
async function detect(img) {
    imageContainer.innerHTML = '';
    imageContainer.style.backgroundImage = `url(${img})`;

    status.textContent = 'Analysing...';
    const image = await RawImage.read(img)-;

    // Preprocess the image
    const result = await processor(image);

    // Perform inference
    const outputs = await model(result);

    // Decode the model outputs
    const generated_text = processor.batch_decode(outputs.logits).generated_text;
    status.textContent = generated_text;
}