A from-scratch 52.3M Transformer that maps raw Japanese to the
full Kanjiland
reading-comprehension format — segmentation, furigana, glosses, word groupings,
translation, and grammar labels (⟨T⟩/⟨W⟩/⟨S⟩/⟨G⟩), with
no MeCab at inference
(it learned segmentation itself). Part of
Kanjiland.
1git clone https://github.com/jakequist/kanjiland && cd kanjiland
2uv run python scripts/annotate.py --config config.yaml --checkpoint model.pt \
3 --text "彼は古い寺を訪れた。" --device cpu
Weights:
MIT. This is an
early de-risk baseline trained on only 6.8k
examples — valid
structure, rough
content (glosses/translations loop). Improve
via more silver data + constrained decoding, not architecture. Grammar inventory:
docs/GRAMMAR_RULES.md.
