Show HN: Local-first fast CPU image to text for screenshots, PDFs, webpages
19 points
2 days ago
| 8 comments
| github.com
| HN
KetoManx64
2 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.
reply
mrkn1
2 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

reply
KetoManx64
2 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!!
reply
abstract257
2 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...
reply
krunck
2 days ago
[-]
I had to extract the image from a PDF for it to work. Then run it on each page image extracted.
reply
abstract257
2 days ago
[-]
Thanks
reply
lavaman131
2 days ago
[-]
This is awesome! Been needing something like this for some research paper diagrams I've been indexing.
reply
vivzkestrel
2 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
reply
mrkn1
2 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));
      }
    }); 
  });
reply
monosma
2 days ago
[-]
What was the reason for adopting PaddleOCR? Can other OCR models be used as well?
reply
mrkn1
2 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
reply
kouru225
2 days ago
[-]
Roman alphabet only or does this work with other alphabets?
reply
mrkn1
2 days ago
[-]
109 languages, including other alphabets.
reply
garrett2558
2 days ago
[-]
Very cool, I'm building my own local-first product as well
reply
mrkn1
2 days ago
[-]
thank you! what is it about?
reply
BIGFOOT_EXISTS
2 days ago
[-]
Now this is legit cool, keep up the great work.
reply
mrkn1
2 days ago
[-]
thank you!
reply