tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "_",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 111,
      "content": "UNK",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "Regex": "(?:\\[SEP\\]|^|$)"
        },
        "content": "_"
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "(?:_)+"
        },
        "content": "_"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "_"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "vocab": {
      "!": 103,
      "'": 108,
      ",": 106,
      "-": 109,
      ".": 107,
      "?": 104,
      "AA": 1,
      "E": 2,
      "EE": 3,
      "En": 4,
      "N": 5,
      "OO": 6,
      "SP": 110,
      "UNK": 111,
      "V": 7,
      "_": 0,
      "a": 8,
      "a:": 9,
      "aa": 10,
      "ae": 11,
      "ah": 12,
      "ai": 13,
      "an": 14,
      "ang": 15,
      "ao": 16,
      "aw": 17,
      "ay": 18,
      "b": 19,
      "by": 20,
      "c": 21,
      "ch": 22,
      "d": 23,
      "dh": 24,
      "dy": 25,
      "e": 26,
      "e:": 27,
      "eh": 28,
      "ei": 29,
      "en": 30,
      "eng": 31,
      "er": 32,
      "ey": 33,
      "f": 34,
      "g": 35,
      "gy": 36,
      "h": 37,
      "hh": 38,
      "hy": 39,
      "i": 40,
      "i0": 41,
      "i:": 42,
      "ia": 43,
      "ian": 44,
      "iang": 45,
      "iao": 46,
      "ie": 47,
      "ih": 48,
      "in": 49,
      "ing": 50,
      "iong": 51,
      "ir": 52,
      "iu": 53,
      "iy": 54,
      "j": 55,
      "jh": 56,
      "k": 57,
      "ky": 58,
      "l": 59,
      "m": 60,
      "my": 61,
      "n": 62,
      "ng": 63,
      "ny": 64,
      "o": 65,
      "o:": 66,
      "ong": 67,
      "ou": 68,
      "ow": 69,
      "oy": 70,
      "p": 71,
      "py": 72,
      "q": 73,
      "r": 74,
      "ry": 75,
      "s": 76,
      "sh": 77,
      "t": 78,
      "th": 79,
      "ts": 80,
      "ty": 81,
      "u": 82,
      "u:": 83,
      "ua": 84,
      "uai": 85,
      "uan": 86,
      "uang": 87,
      "uh": 88,
      "ui": 89,
      "un": 90,
      "uo": 91,
      "uw": 92,
      "v": 93,
      "van": 94,
      "ve": 95,
      "vn": 96,
      "w": 97,
      "x": 98,
      "y": 99,
      "z": 100,
      "zh": 101,
      "zy": 102,
      "…": 105
    }    
  }
}