Re:DeepSeek OCR
by jakewins on Monday October 20, 2025 @05:05AM
(#45641608)
But this was very much the case with existing OCR software as well? I guess the LLMs will end up making up plausible looking text instead of text riddled with errors, which makes it much harder to catch the mistakes, in fairness
[ Parent
| on HN ]
Good libraries gave results with embedded confidence levels for each unit recognized.
Re:DeepSeek OCR
by wahnfrieden on Monday October 20, 2025 @09:41AM
(#45643820)
Existing ocr doesn’t skip over entire (legible) paragraphs or hallucinate entire sentences
This must be some older/smaller model.
I usually run the image(s) through more than one converter then compare the results. They all have problems, but the parts they agree on are usually correct.
Re:DeepSeek OCR
by Davidzheng on Monday October 20, 2025 @09:50AM
(#45643920)
rarely happens to me using LLMs to transcribe pdfs