# src/evaluators/transliteration/datasets.py
TRANSLITERATION_DATASETS = {
    "madar-tun": {
        "path": "tunis-ai/MADAR-TUN",
        "split": "test",
        "source_col": "arabish",   # Latin
        "target_col": "words",     # Arabic script
        "description": "MADAR-TUN: Arabizi ↔ Arabic script"
    }
}