eFontes Project

eFontes develops open models and tools for the linguistic analysis of Medieval Latin texts.

Models

Our Hugging Face collection contains models for:

• part-of-speech tagging
• morphological-feature tagging
• lemmatization
• named-entity recognition

Browse the eFontes model collection

eFontes Latin Tagger v2

The corrected eFontes Latin Tagger v2 provides POS tagging, morphological features, and clean lemmatization through a single public runtime.

• POS tagging model
• Morphological-features model
• Lemmatization model
• All eFontes models

Links

• eFontes project
• Public runtime source code
• eFontes models

Citation

Earlier eFontes release

The earlier eFontes models and their evaluation are described in:

Nowak, Krzysztof; Jędrzej Ziębura; Krzysztof Wróbel; and Aleksander Smywiński-Pohl. 2024. eFontes. Part of Speech Tagging and Lemmatization of Medieval Latin Texts: A Cross-Genre Survey. https://doi.org/10.48550/arXiv.2407.00418

eFontes Latin Tagger v2

The corrected v2 release is maintained and released by Krzysztof Nowak (2026). It is based on the earlier eFontes models and research described in the 2024 paper above.