Newseye-project · PyLaia · Published August 17, 2021

NLF_Newseye_SV

Text Recognition

Description

This model works well with Swedish script from late 18th century to mid of 20th century. For normal running text in newspapers from that time error rates much below 1% were measured. The model was created in the NewsEye project and is based on training data coming from the National Library Finland (NLF). Note: the model is trained on Swedish language documents and will therefore be less performant on other languages.

Try this model

Use this modelOpen in Transkribus
Very low error rate3.8% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.8% 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.

Words373,108
Lines64,866
Training Pages255
Model ID35917
Languages
Swedish