Hi there, I have trouble extracting data from long pdfs (>30 pages).
The engine works beautifully and does exactly what it should. However, only a small portion of the pdf is extracted. Even when I re-run the extraction specifying to apply it to all pages (and giving detailed input how many results I expect), I only get a fraction of the pdf’s data extracted.
Any idea what to change - or is it simply that Julius can only handle small pdfs?