www.youtube.com/watch?v=S2po...
www.youtube.com/watch?v=S2po...
Specifically I'd like to run it on an early-mid-20thC printed periodical, and would really like hOCR or ALTO output
So far I've had moderate luck with Kraken and not much with Tesseract
Specifically I'd like to run it on an early-mid-20thC printed periodical, and would really like hOCR or ALTO output
So far I've had moderate luck with Kraken and not much with Tesseract
Claude: "I think this rabbit hole has reached its natural end. The data you already have is excellent for the article, and reliable headline extraction from 1927 HOCR would need a proper ML approach. Shall we call it here?"
Claude: "I think this rabbit hole has reached its natural end. The data you already have is excellent for the article, and reliable headline extraction from 1927 HOCR would need a proper ML approach. Shall we call it here?"
the DTIYS mentioned is also now here
the DTIYS mentioned is also now here
www.youtube.com/watch?v=HOCr...
www.youtube.com/watch?v=HOCr...
www.youtube.com/watch?v=HocR...
www.youtube.com/watch?v=HocR...
We’ll all get through this a lot faster if you do.
We’ll all get through this a lot faster if you do.
Published on Sunday, October 19, 2025
Published on Sunday, October 19, 2025
The PDF output strikes a balance between visual fidelity and searchability - but it can't reflow properly.
Might be as far as I can take it. Will sleep on the problem.
The PDF output strikes a balance between visual fidelity and searchability - but it can't reflow properly.
Might be as far as I can take it. Will sleep on the problem.
He was the first racer to cross the line in the first race of the weekend. I'm not actually sure if he even won that race, but he was the first finisher of the event.
He was the first racer to cross the line in the first race of the weekend. I'm not actually sure if he even won that race, but he was the first finisher of the event.
Think of the poor cancer patients!
Think of the poor cancer patients!
They've got a full pavilion on the waterfront, including a giant widget out front made of oars. Hoping to get inside later, as I saw a 744 model and biscoff on display.
They've got a full pavilion on the waterfront, including a giant widget out front made of oars. Hoping to get inside later, as I saw a 744 model and biscoff on display.