OCRing Music from YouTube with Common Lisp

#1

Post by superdisk » Sun, Jan 05, 2025, 12:29 PM UTC

OCRing Music from YouTube with Common Lisp
nickfa.ro

Re: OCRing Music from YouTube with Common Lisp

#2

Post by kanwisher » Mon, Jan 06, 2025, 8:03 AM UTC

honestly this would be better with an AI model

Re: OCRing Music from YouTube with Common Lisp

#3

Post by teruakohatu » Mon, Jan 06, 2025, 8:17 AM UTC

kanwisher wrote: post #2

honestly this would be better with an AI model

> honestly this would be better with an AI model

In the article the author tried Tesseract which uses ML and has some neural network models, and also tried ChatGPT.

I have come to the same conclusion as the author when doing OCR that needed 100% accuracy.

When you know the font, spacing and the layout is fixed, old school statistical analysis of the pixels works a treat.

Re: OCRing Music from YouTube with Common Lisp

#4

Post by register » Mon, Jan 06, 2025, 8:36 AM UTC

teruakohatu wrote: post #3

kanwisher wrote: post #2

honestly this would be better with an AI model

> honestly this would be better with an AI model In the article the author tried Tesseract which uses ML and has some neural network models, and also tried ChatGPT. I have come to the same conclusion as the author when doing OCR that needed 100% accuracy. When you know the font, spacing and the layout is fixed, old school statistical analysis of the pixels works a treat.

Completely second that. This is my experience as well.

Re: OCRing Music from YouTube with Common Lisp

#5

Post by rcarmo » Mon, Jan 06, 2025, 8:58 AM UTC

Holy cow.

Re: OCRing Music from YouTube with Common Lisp

#6

Post by secondplacetho » Mon, Jan 06, 2025, 9:20 AM UTC

kanwisher wrote: post #2

honestly this would be better with an AI model

ML is the second best answer to everything, and very rarely the first best answer.

Of course it'd be better than something that is intentionally limiting itself. But that says nothing.

Re: OCRing Music from YouTube with Common Lisp

#7

Post by varjag » Mon, Jan 06, 2025, 9:59 AM UTC

If you're also getting a 500:

https://web.archive.org/web/20250106075631/https://nickfa.ro...

Re: OCRing Music from YouTube with Common Lisp

#8

Post by superdisk » Mon, Jan 06, 2025, 10:13 AM UTC

varjag wrote: post #7

If you're also getting a 500: https://web.archive.org/web/20250106075631/https://nickfa.ro...

I just restarted the webserver. It's running on OpenBSD HTTPd + MediaWiki + SQLite, and keeping it up has been a perpetual thorn in my side. Oh well. I need to figure out some alternative setup probably.

Re: OCRing Music from YouTube with Common Lisp

#9

Post by j45 » Mon, Jan 06, 2025, 10:28 AM UTC

superdisk wrote: post #8

varjag wrote: post #7

If you're also getting a 500: https://web.archive.org/web/20250106075631/https://nickfa.ro...

I just restarted the webserver. It's running on OpenBSD HTTPd + MediaWiki + SQLite, and keeping it up has been a perpetual thorn in my side. Oh well. I need to figure out some alternative setup probably.

Modify your DNS to put cloudflare or bunny in front of it and you'll be good. Don't stop self-hosting :)

Re: OCRing Music from YouTube with Common Lisp

#10

Post by curt15 » Mon, Jan 06, 2025, 10:50 AM UTC

kanwisher wrote: post #2

honestly this would be better with an AI model

By "AI model" do you mean neural nets? "AI" or "ML" are just buzzwords that conveys no real meaning about the underlying mathematics. The underlying models could be something as basic as linear or logistic regression, which depending on the application could actually be more appropriate that full-blown neural nets.