← Back to context Comment by wahnfrieden 3 months ago Existing ocr doesn’t skip over entire (legible) paragraphs or hallucinate entire sentences 3 comments wahnfrieden Reply criddell 3 months ago 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. Davidzheng 3 months ago rarely happens to me using LLMs to transcribe pdfs KoolKat23 3 months ago This must be some older/smaller model.
criddell 3 months ago 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.
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.
rarely happens to me using LLMs to transcribe pdfs
This must be some older/smaller model.