{
  "configuration": {
    "holdout_fields": [
      "dataset"
    ],
    "include_invalid": false,
    "ratios": {
      "train": 0.8,
      "validation": 0.2
    },
    "seed": 42,
    "stratify_fields": [
      "endpoint",
      "language",
      "synthetic"
    ]
  },
  "excluded_invalid_records": 0,
  "holdouts": {
    "dataset": {
      "by_split": {
        "train": [
          "chirp3_1",
          "chirp3_2",
          "human_convcollector_1"
        ],
        "validation": [
          "chirp3_3_short",
          "human_5",
          "liva_1",
          "midcentury_1",
          "mundo_1",
          "orpheus_endfiller_1",
          "orpheus_grammar_1",
          "orpheus_midfiller_1",
          "rime_2"
        ]
      },
      "crossing_values": {}
    }
  },
  "input_records": 3265,
  "leakage": {
    "audio_hash_crossings": {},
    "group_crossings": {},
    "is_valid": true,
    "metadata_key_crossings": {},
    "missing_split_rows": 0
  },
  "records": 3265,
  "split_counts": {
    "train": 2617,
    "validation": 648
  },
  "strata": {
    "endpoint": {
      "train": {
        "false": 1342,
        "true": 1275
      },
      "validation": {
        "false": 325,
        "true": 323
      }
    },
    "language": {
      "train": {
        "ara": 78,
        "ben": 94,
        "dan": 92,
        "deu": 132,
        "eng": 153,
        "fin": 112,
        "fra": 161,
        "hin": 158,
        "ind": 110,
        "ita": 74,
        "jpn": 87,
        "kor": 99,
        "mar": 81,
        "nld": 153,
        "nor": 101,
        "pol": 101,
        "por": 142,
        "rus": 137,
        "spa": 163,
        "tur": 89,
        "ukr": 72,
        "vie": 122,
        "zho": 106
      },
      "validation": {
        "eng": 605,
        "spa": 43
      }
    },
    "synthetic": {
      "train": {
        "false": 3,
        "true": 2614
      },
      "validation": {
        "false": 550,
        "true": 98
      }
    }
  }
}