Show HN: Local-first fast CPU image to text for screenshots, PDFs, webpages

Posted by mrkn1 4 days ago

Counter19Comment17OpenOriginal

Comments

Comment by KetoManx64 4 days ago

What's the performance like compared to tesseract? I don't see tesseract mentioned anywhere in the readme, which is surprising considering that's the number one tool most go to for Image > text OCR.

Comment by mrkn1 4 days ago

No rigorous eval, and I love Tesseract. Here's the example that motivated me to build textsnap (which is in the github's README), parsed with Tesseract:

https://imgur.com/a/i2eQra8

Comment by KetoManx64 4 days ago

Very noticable difference and the exact issue I run repeatedly with tesseract! Definitely going to try dropping textsnap into my scripts now. Thanks!!

Comment by abstract257 4 days ago

Curious how it does on multi-page scanned PDFs vs. single screenshots? The ORT vision/decoder split is the part that usually makes or breaks CPU VLM OCR...

Comment by krunck 4 days ago

I had to extract the image from a PDF for it to work. Then run it on each page image extracted.

Comment by abstract257 3 days ago

Thanks

Comment by lavaman131 3 days ago

This is awesome! Been needing something like this for some research paper diagrams I've been indexing.

Comment by vivzkestrel 4 days ago

- how well do you think this ll work with code? i mean take code screenshots and convert it into actual code for vscode

Comment by mrkn1 4 days ago

Just ran

  textsnap "https://i.ytimg.com/vi/LBNDfxjEYlA/maxresdefault.jpg"
and got this

  $('.count').each(function () {
  $('this').prop('Counter', 0).animate({
    Counter: $('this').text()
  }, {
      duration: 4000,
      easing: 'swing',
      step: 'function (now) {
          $('this").text(Math.ceil(now));
      }
    }); 
  });

Comment by monosma 4 days ago

What was the reason for adopting PaddleOCR? Can other OCR models be used as well?

Comment by mrkn1 4 days ago

No reason other than their Q4 model working reasonably well and fast on my CPU laptop. Should work with any ONNX VLM model

Comment by garrett2558 4 days ago

Very cool, I'm building my own local-first product as well

Comment by mrkn1 4 days ago

thank you! what is it about?

Comment by kouru225 4 days ago

Roman alphabet only or does this work with other alphabets?

Comment by mrkn1 4 days ago

109 languages, including other alphabets.

Comment by BIGFOOT_EXISTS 4 days ago

Now this is legit cool, keep up the great work.

Comment by mrkn1 4 days ago

thank you!

Comment by nabertronic 2 days ago

[dead]