Convert it to a fast model. combine_tessdata -c
compresses the traineddata file. You can also do it when you stop lstmtraining with --convert-to-int flag Please check syntax - On Sun, May 17, 2020, 11:13 Kunal Singh <singh.kunal2...@gmail.com> wrote: > Hello, > > I am using a fine-tuned traineddata file (from tessdata_best). But its' > speed is lot slower than tessdata (legacy+LSTM) or tessdata_fast. > Now, is there any way to make the fine-tuned traineddata file faster, by > sacrificing slight accuracy? Can we possibly reduce some of the layers of > LSTM model? > Any suggestions would be great. > > Regards, > Kunal > > -- > 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/b51213f9-9a3c-4ede-807c-036136e2e8c6%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/b51213f9-9a3c-4ede-807c-036136e2e8c6%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/CAG2NduUm%3DEXeXcH%2B-gGk%3DTb19oKZ9jOTTW4zhvtNRxcS9cGaew%40mail.gmail.com.