Hacker News — vinext + Cloudflare Workers

new
past
show
ask
show
jobs
submit

▲Show HN: Local-first fast CPU image to text for screenshots, PDFs, webpages (github.com)

14 points by mrkn1 20 hours ago | 17 comments

lavaman131 2 hours ago [-]

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

KetoManx64 9 hours 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.

mrkn1 9 hours 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

KetoManx64 5 hours ago [-]

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

abstract257 18 hours 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...

krunck 17 hours ago [-]

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

abstract257 32 minutes ago [-]

Thanks

vivzkestrel 16 hours ago [-]

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

mrkn1 16 hours 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));
      }
    }); 
  });

monosma 15 hours ago [-]

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

mrkn1 15 hours ago [-]

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

kouru225 16 hours ago [-]

Roman alphabet only or does this work with other alphabets?

mrkn1 15 hours ago [-]

109 languages, including other alphabets.

garrett2558 19 hours ago [-]

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

mrkn1 19 hours ago [-]

thank you! what is it about?

BIGFOOT_EXISTS 17 hours ago [-]

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

mrkn1 16 hours ago [-]

thank you!

Rendered at 07:03:36 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.