search

tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
630 stars 184 forks source link

Regarding the training data #280

Closed SreyaKambhatla closed 2 years ago

SreyaKambhatla commented 3 years ago

Hi, I'm new to this field, and I'm learning a lot of new stuff. But I'm quite stuck at the training data part. I've seen how the ocrd test samples with ground truth. I've extracted that data, followed all the steps, and created the trained data. But when I'm trying to create my own data set to train the tesseract with English as my preferred language, I get a lot of errors when trying to train it. I'm not quite sure where I've gone wrong. Can you please tell me how the foo data set was made? It will be really helpful.

aquino-a commented 3 years ago

did you read the instructions?

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.