https://huggingface.co/alibaba-damo/mgp-str-base with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

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

npm i @huggingface/transformers

Example: Optical Character Recognition (OCR) w/ onnx-community/mgp-str-base

import { MgpstrForSceneTextRecognition, MgpstrProcessor, load_image } from '@huggingface/transformers';

const model_id = 'onnx-community/mgp-str-base';
const model = await MgpstrForSceneTextRecognition.from_pretrained(model_id);
const processor = await MgpstrProcessor.from_pretrained(model_id);

// Load image from a URL
const url = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/ocr-demo.png";
const image = await load_image(url);

// 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;
console.log(generated_text); // [ 'ticket' ]

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 ๐Ÿค— Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Downloads last month
49
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support image-to-text models for transformers.js library.

Model tree for onnx-community/mgp-str-base

Quantized
(1)
this model

Space using onnx-community/mgp-str-base 1