A Handwritten Text Recognition (HTR) model for 14th–15th century Croatian Glagolitic manuscripts,
based on the CNN + BiLSTM + CTC architecture introduced in
Puigcerver (2017) and used as
the backbone of PyLaia and Transkribus.
Important: This model reads Glagolitic handwriting and outputs Latin script transliteration,
not Glagolitic Unicode characters. It handles ligatures and resolves the most common abbreviations.
This is a clean-room PyTorch reimplementation of that published architecture (PyLaia-inspired).
It does not use the PyLaia Python package and is not loadable by it —
training and inference run via plain PyTorch (see Usage below).
Input: Grayscale line images, normalized to 128 px height with aspect ratio preserved
Output: Latin script transliteration of Croatian Glagolitic text
Vocabulary: 76 symbols (symbols.txt)
Framework: Pure PyTorch — clean-room reimplementation of the Puigcerver (2017) architecture (PyLaia-inspired); the PyLaia package is not required
Performance
Metric
Value
Validation CER
5.33%
Training epochs
42
Training lines
23,203
Validation lines
1,361
Training Data
Trained on Glagolitic handwriting images transcribed and exported from
Transkribus (see the corresponding
Transkribus model page).
The dataset covers 14th–15th century Croatian Glagolitic handwriting.
Source manuscripts:
Cod. Vind. Slav. 3 (Breviary of Vid of Omišalj)
II. beramski brevijar
Ground truth data was kindly provided by Sanja Zubčić (Rijeka) and Jagoda and Guido Kappel (Vienna).
Model trained and curated by Achim Rabus (Slavic Department, University of Freiburg).
The Transkribus collection comprises 531 training pages and 31 validation pages (~31,035 lines in total).
Our CRNN-CTC model was trained on 23,203 lines (training) and 1,361 lines (validation) from this export.
Usage
Requirements
pip install torch torchvision pillow
Inference
Download best_model.pt, symbols.txt, and model_config.json from this repository,
then use the inference script from polyscriptor:
python
1from inference_pylaia_native import PyLaiaInference
2from PIL import Image
34# Load model5model = PyLaiaInference(6 checkpoint_path="best_model.pt",7 syms_path="symbols.txt"8)910# Transcribe a line image11image = Image.open("line_image.jpg")12text = model.transcribe(image)13print(text)# Output: Latin script transliteration
Note: Input should be a single text line image, not a full page.
Preprocessing (grayscale conversion, height normalization, aspect ratio preservation) is handled
automatically by inference_pylaia_native.py.
For full-page inference with automatic line segmentation, use batch_processing.py:
polyscriptor also ships graphical interfaces that handle
full-page processing without requiring pre-segmented line images:
Interactive single-page GUI — loads raw page images, performs automatic line segmentation,
and can export results as PAGE XML:
python transcription_gui_plugin.py
Batch processing GUI — processes entire folders; auto-detects existing PAGE XML files
(e.g. from Transkribus) and uses them for segmentation when available:
python polyscriptor_batch_gui.py
Intended Use
Transcription of 14th–15th century Croatian Glagolitic manuscripts
Digital humanities research on medieval Croatian texts
Limitations
Trained on two manuscript sources (Cod. Vind. Slav. 3 and II. beramski brevijar); may underperform on other hands or periods
Output is Latin script transliteration, not Glagolitic Unicode
Full-page segmentation quality depends on the segmentation method used upstream
Citation
If you use this model in your research, please cite the architecture paper, the publication describing
the training data and recognition system, and this model:
bibtex
1@article{rabus2022glagolitic,
2 title = {Handwritten Text Recognition for Croatian Glagolitic},
3 author = {Rabus, Achim},
4 journal = {Slovo: časopis Staroslavenskoga instituta u Zagrebu},
5 volume = {72},
6 pages = {181--192},
7 year = {2022},
8 doi = {10.31745/s.72.5},
9 url = {https://doi.org/10.31745/s.72.5}
10}
1112@article{puigcerver2017multidimensional,
13 title = {Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?},
14 author = {Puigcerver, Joan},
15 journal = {Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
16 year = {2017},
17 url = {https://www.jpuigcerver.net/pubs/jpuigcerver_icdar2017.pdf}
18}
1920@misc{rabus2026polyscriptor,
21 title = {Polyscriptor: Multi-Engine HTR Training \& Comparison Tool},
22 author = {Rabus, Achim},
23 year = {2026},
24 url = {https://github.com/achimrabus/polyscriptor}
25}
