If you're training your own models, try including the --convert_to_int flag when converting from a checkpoint to a traineddata.
Otherwise if you're using the base language models, try out the "fast" version in the repository. On Thu, Aug 1, 2019 at 3:08 PM Thomas Mann <[email protected]> wrote: > Hi all, > > I was wondering if there is a way to set Tesseract to a lower accuracy and > get more speed in return. > I'm not happy with the performance, and for my purposes I actually don't > need perfect results as long as the return value is deterministic. > So as long as I get the same erroneous result for the same input image, > I'm fine. > > Does anyone know whether there is a way to tweak that? > > Many thanks in advance! > > -- > You received this message because you are subscribed to the Google Groups > "tesseract-ocr" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/bf6716bf-a5bd-4af6-901e-ad0c099155bc%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/bf6716bf-a5bd-4af6-901e-ad0c099155bc%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CABtjQ9JmJoFynOan6fYsR8gb7225h-7M6H8PpMqG1AZTZz1C2A%40mail.gmail.com.
