metadata
base_model: vikp/texify2
library_name: transformers.js
pipeline_tag: image-to-text
https://huggingface.co/vikp/texify2 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 @xenova/transformers
Example: Image-to-text w/ Xenova/texify2.
import { pipeline } from '@xenova/transformers';
// Create an image-to-text pipeline
const texify = await pipeline('image-to-text', 'Xenova/texify2');
// Generate LaTeX from image
const image = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/latex.png';
const latex = await texify(image, { max_new_tokens: 384 });
console.log(latex);
// [{ generated_text: "The potential $V_i$ of cell $\\mathcal{C}_i$ centred at position $\\mathbf{r}_i$ is related to the surface charge densities $\\sigma_j$ of cells $\\mathcal{C}_j$ $j\\in[1,N]$ through the superposition principle as: $$V_i\\,=\\,\\sum_{j=0}^{N}\\,\\frac{\\sigma_j}{4\\pi\\varepsilon_0}\\,\\int_{\\mathcal{C}_j}\\frac{1}{\\|\\mathbf{r}_i-\\mathbf{r}'\\|}\\mathrm{d}^2\\mathbf{r}'\\,=\\,\\sum_{j=0}^{N}\\,Q_{ij}\\,\\sigma_j,$$ where the integral over the surface of cell $\\mathcal{C}_j$ only depends on $\\mathcal{C}_j$ shape and on the relative position of the target point $\\mathbf{r}_i$ with respect to $\\mathcal{C}_j$ location, as $\\sigma_j$ is assumed constant over the whole surface of cell $\\mathcal{C}_j$." }]
| Input image | Visualized output |
|---|---|
 |
 |
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).