tesseract.js/docs/faq.md

FAQ

How does tesseract.js download and keep *.traineddata?

When you execute recognize() function (ex: recognize(image, 'eng')), the language model to download is determined by the 2nd argument of recognize(). (eng in the example)

Tesseract.js will first check if *.traineddata already exists. (browser: IndexedDB, Node.js: fs, in the folder you execute the command) If the *.traineddata doesn't exist, it will fetch *.traineddata.gz from tessdata, ungzip and store in IndexedDB or fs, you can delete it manually and it will download again for you.

How can I train my own *.traineddata?

For tesseract.js v2, check TrainingTesseract 4.00

For tesseract.js v1, check Training Tesseract 3.03–3.05

How can I get HOCR, TSV, Box, UNLV, OSD?

Starting from 2.0.0-alpha.10, you can get all these information in the final result.

import Tesseract from 'tesseract.js';

const { TesseractWorker } = Tesseract;
const worker = new TesseractWorker();

worker
  .recognize('https://tesseract.projectnaptha.com/img/eng_bw.png')
  .then((result) => {
    console.log(result.text);
    console.log(result.hocr);
    console.log(result.tsv);
    console.log(result.box);
    console.log(result.unlv);
    console.log(result.osd);
  });