{
  "made": "2026-11-02",
  "corpus": "Tamil Wikipedia development corpus (CC BY-SA 4.0); evaluation sentences left out",
  "sentences": 1598428,
  "tokensInCountsFile": 17457202,
  "distinctWordsInCountsFile": 1213516,
  "tamilScriptWords": 1213516,
  "tamilScriptOccurrences": 17457202,
  "wordsWithALetter": 1099888,
  "occurrencesWithALetter": 14850390,
  "shareOfAllOccurrencesWithALetter": 85.1,
  "sourceSha256": "93ee5b838fb2e45d87d66da8039315bc098b966101a729a1f0a3925fec5ca4cc",
  "dominance": 20,
  "thresholds": [
    {
      "threshold": 3,
      "pairs": 4510,
      "byLetterPair": {
        "ண/ந": 19,
        "ண/ன": 1242,
        "ந/ன": 360,
        "ர/ற": 833,
        "ல/ள": 1320,
        "ல/ழ": 444,
        "ள/ழ": 292
      },
      "twinWords": 8684,
      "twinOccurrences": 2403921,
      "lopsidedPairs": 961,
      "dominantOccurrences": 2040647,
      "sharePercent": 16.2,
      "shareOfAllPercent": 13.8,
      "dominantSharePercent": 84.9
    },
    {
      "threshold": 10,
      "pairs": 1330,
      "byLetterPair": {
        "ண/ந": 5,
        "ண/ன": 295,
        "ந/ன": 121,
        "ர/ற": 223,
        "ல/ள": 415,
        "ல/ழ": 174,
        "ள/ழ": 97
      },
      "twinWords": 2570,
      "twinOccurrences": 1150070,
      "lopsidedPairs": 193,
      "dominantOccurrences": 848673,
      "sharePercent": 7.7,
      "shareOfAllPercent": 6.6,
      "dominantSharePercent": 73.8
    },
    {
      "threshold": 30,
      "pairs": 457,
      "byLetterPair": {
        "ண/ந": 2,
        "ண/ன": 86,
        "ந/ன": 36,
        "ர/ற": 66,
        "ல/ள": 165,
        "ல/ழ": 66,
        "ள/ழ": 36
      },
      "twinWords": 887,
      "twinOccurrences": 650810,
      "lopsidedPairs": 50,
      "dominantOccurrences": 412251,
      "sharePercent": 4.4,
      "shareOfAllPercent": 3.7,
      "dominantSharePercent": 63.3
    },
    {
      "threshold": 100,
      "pairs": 127,
      "byLetterPair": {
        "ண/ன": 20,
        "ந/ன": 7,
        "ர/ற": 18,
        "ல/ள": 56,
        "ல/ழ": 16,
        "ள/ழ": 10
      },
      "twinWords": 245,
      "twinOccurrences": 273215,
      "lopsidedPairs": 9,
      "dominantOccurrences": 115628,
      "sharePercent": 1.8,
      "shareOfAllPercent": 1.6,
      "dominantSharePercent": 42.3
    }
  ]
}