update model card
Browse files
README.md
CHANGED
|
@@ -21,3 +21,18 @@ Base model: **dh-unibe/trocr-kurrent**
|
|
| 21 |
Epochs: 19.85 / 20
|
| 22 |
Eval CER: 0.05673
|
| 23 |
Test CER: 0.05416
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
Epochs: 19.85 / 20
|
| 22 |
Eval CER: 0.05673
|
| 23 |
Test CER: 0.05416
|
| 24 |
+
|
| 25 |
+
This model is based on an extensive training set (of roughly 1579200 words) and evaluated against the same hands in an evaluation and test set (automatic split).
|
| 26 |
+
Consisting of German Kurrent scripts written in the 16th-18th century.
|
| 27 |
+
|
| 28 |
+
The ground truth stems from different projects and partners and is biased toward Swiss documents.
|
| 29 |
+
It is based on documents from a variety of archives and projects.
|
| 30 |
+
Among others, the State Archives of Zürich (Stillstandsprotokolle, Ratsmanuale, Findmittel), and the scholarly edition project Königsfelden (Universitäten Zürich und Bern: www.koenigsfelden.uzh.ch).
|
| 31 |
+
As well as transcriptions from Einsiedeln.
|
| 32 |
+
Further contributions by the university archives of Greifswald: https://rechtsprechung-im-ostseeraum.archiv.uni-greifswald.de/.
|
| 33 |
+
|
| 34 |
+
The public Transkribus model (based on PyLaia) can be found here: https://readcoop.eu/model/german-kurrent-16th-18th/
|
| 35 |
+
|
| 36 |
+
Extensive testing of the model has still to be carried out.
|
| 37 |
+
This is only a first attempt but might help for fine-tuning tasks.
|
| 38 |
+
|