Hey Guys, I hope you're all doing well. We have been working on training a model using a handwritten font in Tesseract OCR, and we have encountered an issue related to the START_MODEL flag.
Currently, we are using the following command for training: make tesstrain START_MODEL=hin TESSDATA=tessdata_best However, whenever we include the START_MODEL flag, we consistently encounter the "Segmentation Failure" error. Strangely, when we omit the START_MODEL flag and only specify the TESSDATA path, the training process runs without any failures. I have a couple of questions regarding this issue: 1. When we omit the START_MODEL flag and solely provide the TESSDATA path, which base model does Tesseract use for training? 2. Is there any specific reason why we are encountering the "Segmentation Failure" error when using the START_MODEL flag? I would appreciate any insights or guidance you can provide regarding these questions. Thank you all for your support. -- 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/40c683aa-3e34-40b5-bcc1-199227c52ab0n%40googlegroups.com.
