tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "UNK",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "PAD",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "W",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "UTT_BOUNDARY",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "Lowercase"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      },
      {
        "type": "StripAccents"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": " "
        },
        "content": "W"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "UTT_BOUNDARY": {
        "id": "UTT_BOUNDARY",
        "ids": [
          3
        ],
        "tokens": [
          "UTT_BOUNDARY"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "W": 2,
      "UTT_BOUNDARY": 3,
      "y": 4,
      "e": 5,
      "a": 6,
      "h": 7,
      ".": 8,
      "c": 9,
      "o": 10,
      "m": 11,
      "p": 12,
      "u": 13,
      "n": 14,
      "d": 15,
      "'": 16,
      "s": 17,
      "t": 18,
      "i": 19,
      "g": 20,
      "l": 21,
      "k": 22,
      "x": 23,
      ",": 24,
      "r": 25,
      "w": 26,
      "v": 27,
      "f": 28,
      "b": 29,
      "j": 30,
      "?": 31,
      "-": 32,
      "q": 33,
      ";": 34,
      "2": 35,
      "‘": 36,
      "’": 37,
      "!": 38,
      "/": 39,
      "1": 40,
      ":": 41,
      "z": 42,
      "3": 43,
      "6": 44,
      "9": 45,
      "&": 46,
      "4": 47,
      "5": 48,
      "0": 49,
      "=": 50,
      "8": 51,
      "7": 52,
      "£": 53,
      "(": 54,
      ")": 55,
      "—": 56,
      "*": 57,
      "]": 58,
      "[": 59,
      "\"": 60,
      "_": 61,
      "%": 62,
      "“": 63,
      "”": 64,
      "+": 65,
      "$": 66,
      "^": 67,
      "#": 68,
      "æ": 69,
      "ʌ": 70,
      "ɩ": 71,
      "ə": 72,
      "↫": 73,
      "|": 74,
      "°": 75,
      "ø": 76,
      "~": 77,
      "⁄": 78,
      "`": 79,
      "�": 80,
      "′": 81,
      "@": 82,
      "}": 83,
      "{": 84,
      "―": 85,
      "–": 86,
      "·": 87,
      "♪": 88,
      "¡": 89,
      "÷": 90,
      "\\": 91,
      "¶": 92,
      "ð": 93,
      "¿": 94,
      "­": 95,
      "♫": 96,
      "​": 97,
      "œ": 98,
      "ł": 99,
      "¦": 100,
      "×": 101,
      "™": 102,
      "ß": 103,
      "ˈ": 104,
      "ı": 105,
      "đ": 106,
      "−": 107,
      "ː": 108,
      "•": 109,
      "⟨": 110,
      "⟩": 111,
      "ŋ": 112,
      "ʼ": 113,
      "\t": 114
    },
    "unk_token": "UNK"
  }
}