tokenizer.json

{
  "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": "[\u2013\u2014]"
        },
        "content": "-"
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "[^ -\"$-.0-;?A-Za-z£́]"
        },
        "content": ""
      }
    ]
  },
  "pre_tokenizer": {
    "type": "FixedLength",
    "length": 1
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      " ": 0,
      "!": 1,
      "\"": 2,
      "$": 3,
      "%": 4,
      "&": 5,
      "'": 6,
      "(": 7,
      ")": 8,
      "*": 9,
      "+": 10,
      ",": 11,
      "-": 12,
      ".": 13,
      "0": 14,
      "1": 15,
      "2": 16,
      "3": 17,
      "4": 18,
      "5": 19,
      "6": 20,
      "7": 21,
      "8": 22,
      "9": 23,
      ":": 24,
      ";": 25,
      "?": 26,
      "A": 27,
      "B": 28,
      "C": 29,
      "D": 30,
      "E": 31,
      "F": 32,
      "G": 33,
      "H": 34,
      "I": 35,
      "J": 36,
      "K": 37,
      "L": 38,
      "M": 39,
      "N": 40,
      "O": 41,
      "P": 42,
      "Q": 43,
      "R": 44,
      "S": 45,
      "T": 46,
      "U": 47,
      "V": 48,
      "W": 49,
      "X": 50,
      "Y": 51,
      "Z": 52,
      "a": 53,
      "b": 54,
      "c": 55,
      "d": 56,
      "e": 57,
      "f": 58,
      "g": 59,
      "h": 60,
      "i": 61,
      "j": 62,
      "k": 63,
      "l": 64,
      "m": 65,
      "n": 66,
      "o": 67,
      "p": 68,
      "q": 69,
      "r": 70,
      "s": 71,
      "t": 72,
      "u": 73,
      "v": 74,
      "w": 75,
      "x": 76,
      "y": 77,
      "z": 78,
      "£": 79,
      "\u0301": 80
    },
    "unk_token": "\u0301"
  }
}