| { | |
| "train_rows": 30692, | |
| "train_unique": 30527, | |
| "eval_clips": 48, | |
| "counts": { | |
| "exact": 0, | |
| "near_dup": 0, | |
| "ngram_ge_5": 2, | |
| "clean": 46 | |
| }, | |
| "findings": [ | |
| { | |
| "id": "gen_001", | |
| "category": "general", | |
| "tier": "ngram_ge_5", | |
| "detail": "shares a 5-gram with training", | |
| "text": "Habari za asubuhi, karibu katika matangazo yetu ya leo." | |
| }, | |
| { | |
| "id": "ne_010", | |
| "category": "named_entities", | |
| "tier": "ngram_ge_5", | |
| "detail": "shares a 5-gram with training", | |
| "text": "Jiji la Dar es Salaam lina wakazi zaidi ya milioni sita." | |
| } | |
| ] | |
| } |