Open Alhar6i opened 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.
That models were trained using data from https://doi.org/10.23636/1135. Usually the fast variant should be sufficient. So you could try ArabicHandwritingOCRD_4.837_138060_365920.traineddata for example. Just copy it into the same directory with eng.traineddata
and optionally rename it to get a shorter model name.
Note that I cannot test those models myself, so I have no idea how good or bad they perform.
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.
Hi,
Is there any configuration required to use the arabic handwriting traineddata, please? I found them here, https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/ArabicHandwritingOCRD/tessdata_best/
Should I download all of them or only the latest version?