Machine Learning

This component is an experimental machine learning local inference engine based on Transformers.js and the ONNX runtime.

In the example below, an image is converted to text using the image-to-text task.

const {PipelineOptions, EngineProcess } = ChromeUtils.importESModule("chrome://global/content/ml/EngineProcess.sys.mjs");

// First we create a pipeline options object, which contains the task name
// and any other options needed for the task
const options = new PipelineOptions({taskName: "image-to-text" });

// Next, we create an engine parent object via EngineProcess
const engineParent = await EngineProcess.getMLEngineParent();

// We then create the engine object, using the options
const engine = engineParent.getEngine(options);

// Preparing a request
const request = {url: "https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg"};

// At this point we are ready to do some inference.
const res = await engine.run(request);

// The result is a string containing the text extracted from the image
console.log(res);

Supported Inference Tasks

The following tasks are supported by the machine learning engine:

imageToText(request, model, tokenizer, processor)

Converts an image to text using a machine learning model.

Arguments:

  • request (object) – The request object containing image data.

  • request.url (string) – The URL of the image to process. If url is not provided, other fields are used.

  • request.data (ArrayBuffer) – The raw image data to process. Ignored if url is provided.

  • request.width (number) – The image width. Ignored if url is provided.

  • request.height (number) – The image height. Ignored if url is provided.

  • request.channels (number) – The image channels. Can be 1, 2, 3 or 4. Defaults to 4. Ignored if url is provided.

  • model (object) – The model used for inference.

  • tokenizer (object) – The tokenizer used for decoding.

  • processor (object) – The processor used for preparing image data.

Returns:

Promise.<object> – The result object containing the processed text.