**Egyptian model**

Uses standard Latin transcription (Unicode) as input.

"Egyptian-Standard" produces lemmata with original long indices.
"Egyptian" produces lemmata with shortened indices.

Sahala & Lincke 2024: Neural Lemmatization and POS-tagging models for Coptic, Demotic and Earlier Egyptian. In. Proceedings of the 1st Workshop on Machine Learning for Ancient Languages (ML4AL 2024)