Nicole Merkel-Hilf (UB Heidelberg) · PyLaia · Published November 5, 2022
Devanagari mixed M1A
Text Recognition
Description
This PyLaia model was trained for various Devanagari print types based on
approx. 26,000 words. The training material is comprised of letterpress printings
from the Naval Kishore Press (Lakhnau, North India) from the late 19th and
early 20th century in the Hindi, Sanskrit, Braj Bhasha and Awadhi languages.
The model was created as part of the project “Naval Kishore Press – digital”,
which was financially supported by the German Research Foundation (DFG)
until 2021.
Try this model
Use this modelOpen in Transkribus
Very low error rate2.2% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 2.2% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material.
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.
Words26,598
Lines4,333
Training Pages209
Model ID45909