So you should get the same/similar speed of recognition as with 3.x version based on our test. Maybe try to use OMP_THREAD_LIMIT=1 as most of openmp negative experience comes from linux.
Zdenko po 18. 4. 2022 o 19:12 Evon O Smith <strivingforholin...@gmail.com> napísal(a): > Here's the output of 'tesseract -v' > > ` tesseract 5.1.0 > leptonica-1.78.0 > libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.5.3) : libpng 1.6.34 : libtiff > 4.0.9 : zlib 1.2.11 : libwebp 1.0.3 > Found AVX > Found SSE4.1 > Found OpenMP 201511` > > On Monday, April 18, 2022 at 12:29:16 PM UTC-4 zdenop wrote: > >> Well according to that information it should support AVX and SSE4.2, so >> performance should be similar to 3.x... >> Can you provide the output of "tesseract -v" from that server? >> >> Zdenko >> >> >> po 18. 4. 2022 o 15:24 Evon O Smith <strivingf...@gmail.com> napísal(a): >> >>> This is the processor I have. Intel(R) Xeon(R) CPU E3-1220 V2 @ >>> 3.10GHz. According to this site >>> https://www.techpowerup.com/cpu-specs/xeon-e3-1220-v2.c1033, it >>> supports AVE. >>> >>> On Saturday, April 16, 2022 at 1:23:06 PM UTC-4 zdenop wrote: >>> >>>> What processor is there? Does it have support for Advanced Vector >>>> Extensions [1] , SSE etc? >>>> >>>> [1] https://en.wikipedia.org/wiki/Advanced_Vector_Extensions >>>> >>>> Zdenko >>>> >>>> >>>> so 16. 4. 2022 o 15:06 Evon O Smith <strivingf...@gmail.com> >>>> napísal(a): >>>> >>>>> Thanks I did read those posts before posting. I will go through them >>>>> again. I don't know how to run a benchmark but I am running Tess on >>>>> Opensuse Leap 15.3 on a DL320e Gen 8 server. >>>>> >>>>> On Saturday, April 16, 2022 at 2:59:57 AM UTC-4 zdenop wrote: >>>>> >>>>>> Hello, >>>>>> >>>>>> you are not very specific (OS, HW, tesseract version, language data >>>>>> type, how did measure performance, etc), so it is difficult to help you. >>>>>> Seems like you skipped reading docs and searching the issue tracker, so I >>>>>> would suggest solving your problem with reading at least this information >>>>>> >>>>>> 1. >>>>>> https://github.com/tesseract-ocr/tessdoc/blob/main/Benchmarks.md >>>>>> 2. https://github.com/tesseract-ocr/tesseract/issues/263 >>>>>> >>>>>> >>>>>> Zdenko >>>>>> >>>>>> >>>>>> so 16. 4. 2022 o 1:31 Evon O Smith <strivingf...@gmail.com> >>>>>> napísal(a): >>>>>> >>>>>>> I'm experiencing very slow performance since I upgraded from Tess 3 >>>>>>> to Tess 5. Should i downgrade to get better performance? I won't be >>>>>>> converting my handwriting anyway (since Tess is terrible at it) so it >>>>>>> shouldn't be an issue right? >>>>>>> >>>>>>> -- >>>>>>> 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 tesseract-oc...@googlegroups.com. >>>>>>> To view this discussion on the web visit >>>>>>> https://groups.google.com/d/msgid/tesseract-ocr/5151bdcd-fab8-42f3-a99c-ac7e34a1a1ean%40googlegroups.com >>>>>>> <https://groups.google.com/d/msgid/tesseract-ocr/5151bdcd-fab8-42f3-a99c-ac7e34a1a1ean%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 tesseract-oc...@googlegroups.com. >>>>> >>>> To view this discussion on the web visit >>>>> https://groups.google.com/d/msgid/tesseract-ocr/5b7687d0-7f59-4b83-9fb7-27c96d751716n%40googlegroups.com >>>>> <https://groups.google.com/d/msgid/tesseract-ocr/5b7687d0-7f59-4b83-9fb7-27c96d751716n%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 tesseract-oc...@googlegroups.com. >>> >> To view this discussion on the web visit >>> https://groups.google.com/d/msgid/tesseract-ocr/834724e3-5800-4dd6-b7dd-b9224c59e163n%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/834724e3-5800-4dd6-b7dd-b9224c59e163n%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 tesseract-ocr+unsubscr...@googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/22384dbd-81dc-4ab8-8554-74db12e4cc82n%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/22384dbd-81dc-4ab8-8554-74db12e4cc82n%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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8zeaqnieS0gq27rufH8fqeycyv0-aK%3DZC%2Bvqct6-eU8LQ%40mail.gmail.com.
