Trocr Small Handwritten

🚀 Trocr-small-handwritten with Transformers.js

This project provides the ONNX weights of the microsoft/trocr-small-handwritten model, making it compatible with Transformers.js for image-to-text tasks.

🚀 Quick Start

This repository contains the ONNX weights of microsoft/trocr-small-handwritten to ensure compatibility with Transformers.js.

✨ Features

• Model Compatibility: Offers ONNX weights for seamless integration with Transformers.js.
• Image-to-Text: Enables optical character recognition for handwritten text.

📦 Installation

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @xenova/transformers

💻 Usage Examples

Basic Usage

Example: Optical character recognition w/ Xenova/trocr-small-handwritten.

import { pipeline } from '@xenova/transformers';

// Create image-to-text pipeline
const captioner = await pipeline('image-to-text', 'Xenova/trocr-small-handwritten');

// Perform optical character recognition
const image = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/handwriting.jpg';
const output = await captioner(image);
// [{ generated_text: 'Mr. Brown commented icily.' }]

⚠️ Important Note

Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).