The First Ancient Greek Macronizer

Enter Ancient Greek text to have the alphas, iotas and ypsilons marked as long or short.

There are two models: a pretrained ModernBERT 0.1B with the highest Norma Syllabarum Graecarum benchmark score (Ericu950/SyllaMoBert-grc-macronizer-v1) and the default, a tiny and extremely fast fine-tuned RoBERTa 11M (Ericu950/macronizer_mini), with only slightly lower benchmark score.

Made by Albin Thörn Cleland (Lund university) and Eric Cullhed (Uppsala university). Training the models was made possible by resources provided by the National Academic Infrastructure for Supercomputing in Sweden (NAISS), partially funded by the Swedish Research Council (grant agreement no. 2022-06725).

Model

Pretrained ModernBERT Fine-tuned RoBERTa

Greek Lines

Try examples

Plain Output

Python API

from gradio_client import Client

client = Client("Urdatorn/macronizer")
result = client.predict(
    text="μῆνιν ἄειδε θεὰ Πηληϊάδεω Ἀχιλῆος",
    model="roberta",
    api_name="/macronize",
)
print(result)

Model options are model="modernbert" for the slightly higher benchmark score but larger and slower pretrained 0.1B model, or model="roberta" for the smaller and faster fine-tuned RoBERTa 11M model.