suphankirmizialtin · PyLaia · Published December 7, 2023

OttomanTurkish_Print_v2

Text Recognition

Description

OT print model, trained with the origional data from the first model (ID 52502) and additonal data (see https://docs.google.com/document/d/1z30SeCDf4lMkggLk0qpbiUgWV3DPByre5uhfZOsiKDU/edit#heading=h.go2wj0nr5y3x)

Try this model

OttomanTurkish_Print_v2
Use this modelOpen in Transkribus
Low error rate7.6% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 7.6% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.

Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.

Words248,083
Lines37,866
Training Pages642
Model ID57485
Languages
Turkish Ottoman (1500-1928)