{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFKD"
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "\\s+"
        },
        "content": " "
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "[–—]"
        },
        "content": "-"
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "[^a-zA-Z0-9\\s\\-!\"$%()*+,.\\/:;?@_ÀÁÂÉÈÊËÌÍÎÏÒÓÔÙÚÛŸŃŊŋƆɔƐɛʉǎǐǒǔḿẅ’ʼ£̀́̂̌]"
        },
        "content": ""
      }
    ]
  },
  "pre_tokenizer": {
    "type": "FixedLength",
    "length": 1
  },
  "post_processor": null,
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      " ": 0,
      "!": 1,
      "\"": 2,
      "$": 3,
      "%": 4,
      "&": 5,
      "'": 6,
      "(": 7,
      ")": 8,
      "*": 9,
      "+": 10,
      ",": 11,
      "-": 12,
      ".": 13,
      "/": 14,
      "0": 15,
      "1": 16,
      "2": 17,
      "3": 18,
      "4": 19,
      "5": 20,
      "6": 21,
      "7": 22,
      "8": 23,
      "9": 24,
      ":": 25,
      ";": 26,
      "?": 27,
      "@": 28,
      "A": 29,
      "B": 30,
      "C": 31,
      "D": 32,
      "E": 33,
      "F": 34,
      "G": 35,
      "H": 36,
      "I": 37,
      "J": 38,
      "K": 39,
      "L": 40,
      "M": 41,
      "N": 42,
      "O": 43,
      "P": 44,
      "Q": 45,
      "R": 46,
      "S": 47,
      "T": 48,
      "U": 49,
      "V": 50,
      "W": 51,
      "X": 52,
      "Y": 53,
      "Z": 54,
      "a": 55,
      "b": 56,
      "c": 57,
      "d": 58,
      "e": 59,
      "f": 60,
      "g": 61,
      "h": 62,
      "i": 63,
      "j": 64,
      "k": 65,
      "l": 66,
      "m": 67,
      "n": 68,
      "o": 69,
      "p": 70,
      "q": 71,
      "r": 72,
      "s": 73,
      "t": 74,
      "u": 75,
      "v": 76,
      "w": 77,
      "x": 78,
      "y": 79,
      "z": 80,
      "À": 81,
      "Á": 82,
      "Â": 83,
      "É": 84,
      "È": 85,
      "Ê": 86,
      "Ë": 87,
      "Ì": 88,
      "Í": 89,
      "Î": 90,
      "Ï": 91,
      "Ò": 92,
      "Ó": 93,
      "Ô": 94,
      "Ù": 95,
      "Ú": 96,
      "Û": 97,
      "Ÿ": 98,
      "Ń": 99,
      "Ŋ": 100,
      "ŋ": 101,
      "Ɔ": 102,
      "ɔ": 103,
      "Ɛ": 104,
      "ɛ": 105,
      "ʉ": 106,
      "ǎ": 107,
      "ǐ": 108,
      "ǒ": 109,
      "ǔ": 110,
      "ḿ": 111,
      "ẅ": 112,
      "’": 113,
      "ʼ": 114,
      "£": 115,
      "_": 116,
      "̀": 117,
      "́": 118,
      "̂": 119,
      "̌": 120,
      "�": 121
    },
    "unk_token": "�"
  }
}