Add support for Table Transformer model

[xenova]

Needed by #475

Example usage

Quantized

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

const detector = await pipeline('object-detection', 'Xenova/table-transformer-detection');

const img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/invoice-with-table.png';
const output = await detector(img);
console.log(output);
// [{ score: 0.9969743490219116, label: 'table', box: { xmin: 53, ymin: 324, xmax: 547, ymax: 524 } }]

Show example output

Unquantized

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

const detector = await pipeline('object-detection', 'Xenova/table-transformer-detection', { quantized: false });

const img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/invoice-with-table.png';
const output = await detector(img);
console.log(output);
// [{ score: 0.9967531561851501, label: 'table', box: { xmin: 52, ymin: 322, xmax: 546, ymax: 525 } }]

Show example output

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.