HackerTrans
TopNewTrendsCommentsPastAskShowJobs

mrkn1

255 karmajoined 6 yıl önce
@kouhxp on twitter and bluesky, follow for more

Submissions

Self-proclaimed King of Switzerland uses loophole to build his empire for free

france24.com
4 points·by mrkn1·14 gün önce·0 comments

Self-proclaimed King of Switzerland uses loophole to build his empire for free

france24.com
6 points·by mrkn1·15 gün önce·0 comments

Show HN: Recreate Thinking Machines 276B voice demo with duct tape and 8B model

github.com
3 points·by mrkn1·29 gün önce·0 comments

Show HN: Realtime voice agent that sees, hears, and interrupts – on a CPU laptop

github.com
1 points·by mrkn1·geçen ay·1 comments

Show HN: A CLI that fact-checks text using a 500MB local model and web search

github.com
1 points·by mrkn1·geçen ay·0 comments

Show HN: Free summary, fact check, ELI5 of any text on CPU

github.com
2 points·by mrkn1·geçen ay·0 comments

Show HN: fftext - quick summary, fact check, ELI5 on CPU

github.com
1 points·by mrkn1·geçen ay·0 comments

Show HN: Fact check, summarize, explain any article or webpage on local CPU

github.com
5 points·by mrkn1·geçen ay·0 comments

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

github.com
19 points·by mrkn1·geçen ay·17 comments

Show HN: CPU-only fact-check, summarize, explain, translate any text

github.com
2 points·by mrkn1·geçen ay·0 comments

Show HN: CPU-only fact-check, summarize, explain, translate anything

github.com
3 points·by mrkn1·geçen ay·0 comments

Show HN: CPU-only fact-check, summarize, explain, translate anything

github.com
3 points·by mrkn1·geçen ay·0 comments

Show HN: CPU-only fast OCR for screenshots, images, PDFs, webpages

github.com
9 points·by mrkn1·geçen ay·8 comments

Show HN: CPU model for fact-checking, summarizing, explaining text locally

github.com
1 points·by mrkn1·geçen ay·0 comments

Show HN: Local CPU OCR for images, PDFs, webpages

github.com
3 points·by mrkn1·geçen ay·0 comments

Show HN: Local CPU model for fact-checking, summarizing, explaining text

github.com
6 points·by mrkn1·geçen ay·0 comments

Show HN: CPU transcription for YouTube/TikTok/X, now 3x faster and diarization

github.com
3 points·by mrkn1·2 ay önce·0 comments

Advancing Mathematics Research with AI-Driven Formal Proof Search

arxiv.org
1 points·by mrkn1·2 ay önce·0 comments

Show HN: CPU-only fast OCR for screenshots, images, PDFs, webpages

github.com
4 points·by mrkn1·2 ay önce·9 comments

Show HN: CPU-only transcription for YouTube, TikTok, X, Instagram videos

github.com
97 points·by mrkn1·2 ay önce·49 comments

comments

mrkn1
·3 gün önce·discuss
fwiw kimchi-derived probiotic bacterium (Leuconostoc mesenteroides CBA3656) was shown to bind nanoplastics and help mice excrete more of them. But it’s not yet proven that eating kimchi removes microplastics from humans
mrkn1
·13 gün önce·discuss
Has anyone tried the others listed? Any feedback?
mrkn1
·18 gün önce·discuss
This runs for free on CPU https://github.com/kouhxp/textsnap
mrkn1
·25 gün önce·discuss
[flagged]
mrkn1
·27 gün önce·discuss
The key moments feat is neat. Been working on a free opensource offline transcriber that runs fast on CPU and does diarization too

https://github.com/kouhxp/yapsnap
mrkn1
·geçen ay·discuss
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
mrkn1
·geçen ay·discuss
No reason other than their Q4 model working reasonably well and fast on my CPU laptop. Should work with any ONNX VLM model
mrkn1
·geçen ay·discuss
109 languages, including other alphabets.
mrkn1
·geçen ay·discuss
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));
      }
    }); 
  });
mrkn1
·geçen ay·discuss
thank you!
mrkn1
·geçen ay·discuss
thank you! what is it about?
mrkn1
·geçen ay·discuss
I have not. My experience has been a few seconds for an 1024x1024 with medium density of text, FWIW. Feel free to try it on a few test images, model is pretty small and fast, but yeah no formal evals on CPU.
mrkn1
·geçen ay·discuss
It should support 109 languages. More info here: https://huggingface.co/PaddlePaddle/PaddleOCR-VL
mrkn1
·geçen ay·discuss
No, simply, my laptop only has a CPU.
mrkn1
·geçen ay·discuss
I haven't. But the evals of the underlying model are published here, including on Omnibench. https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5
mrkn1
·geçen ay·discuss
https://github.com/kouhxp/fftext
mrkn1
·geçen ay·discuss
For 100% local CPU fact checking, I made this: https://news.ycombinator.com/item?id=48301003
mrkn1
·geçen ay·discuss
A lot of my queries are summarize/explain/fact check, and these are covered 100% on my CPU locally [0], reducing frontier model reliance

[0] https://news.ycombinator.com/item?id=48301003
mrkn1
·geçen ay·discuss
just released new version that implements your ideas
mrkn1
·2 ay önce·discuss
new version released is up to 3x faster on CPU. Let me know!