Hi Team, We are trying to create custom trained data for our own Tiff image. These are the steps followed
1) created the box file using the below command tesseract customimage.tif -1 eng lstmbox 2) created the lstm file for the box file created tesseract customimage boxfile -psm 6 lstm.train 3 ) lstmtraining --continue_from eng.lstm --traineddata tessdata/eng.traineddata --train_listfile trainingfile.txt --model_output custom_model --debug_level -1 4) lstmtraining --stop_training --continue_from Custom_Model_checkpoint --traineddata tessdata/eng.traineddata --<model_output CustomModel.TrainedData I'm able to generate the custom_traineddata , but it is coping the unicharset of the eng.traineddata and the related files Not taking the unicharset for the custom box file created for our custom image. Our requirement is to create custom trained data with the base as eng.traineddata and use the custom unicharset and the related files created for our own custom image Correct me , if there is any issue with my understanding. Any help would be greatly appreciated -- 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 visit https://groups.google.com/d/msgid/tesseract-ocr/a92b40d3-e783-4cb5-a9f1-fbbb689a635an%40googlegroups.com.
