search

tesseract-ocr / tesstrain

Train Tesseract LSTM with make
Apache License 2.0
599 stars 178 forks source link

Training for fonts? #305

Closed orsondmc closed 1 year ago

orsondmc commented 2 years ago

I've seen some outdated docs for training tesseract with specific fonts.

What's the current way of doing this? Pointers would be appreciated :)

Shreeshrii commented 2 years ago

You can try the scripts in https://github.com/Shreeshrii/tess5train-fonts

These work for me. Please be prepared to modify the bash scripts as needed.

stefan6419846 commented 2 years ago

If you want to fine tune a model for a specific font using artificial data, the scripts in https://github.com/tesseract-ocr/tesstrain/tree/main/src/training mostly are a drop-in replacement for the old tesstrains.h script.

stale[bot] commented 1 year 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.