Hey everyone , I am train my own lstm model based using some specific images that I want tesseract to work efficiently on. I have used the command *$ lstmtraining --model_output=my_output.lstm --traineddata="C:\Program Files\Tesseract-OCR\tessdata\eng.traineddata" --old_traineddata="C:\Program Files\Tesseract-OCR\tessdata\eng.traineddata" --train_listfile=traindata.txt*
but it is giving I high error rate *At iteration 40/40/40, Mean rms=5.874000%, delta=47.785000%, BCER train=99.487000%, BWER train=100.000000%, skip ratio=0.000000%, New worst BCER = 99.487000 wrote checkpoint.* Finished! Selected model with minimal training error rate (BCER) = 99.367 So my questions is What is the reason for this high error rate as my file contains normal english sentences. I think maybe my custom model is not leveraging the preptrained "eng.lstm" model Thanks -- 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/37482650-601d-4a14-b3ed-2add4fc53ca4n%40googlegroups.com.
