tokenizers/char/eng/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<eos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "NFC"
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<bos>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<eos>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<bos>": {
        "id": "<bos>",
        "ids": [
          1
        ],
        "tokens": [
          "<bos>"
        ]
      },
      "<eos>": {
        "id": "<eos>",
        "ids": [
          2
        ],
        "tokens": [
          "<eos>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<bos>": 1,
      "<eos>": 2,
      "<unk>": 3,
      "!": 4,
      "'": 5,
      "(": 6,
      ")": 7,
      ",": 8,
      "-": 9,
      ".": 10,
      "0": 11,
      "1": 12,
      "2": 13,
      "3": 14,
      "4": 15,
      "5": 16,
      "6": 17,
      "7": 18,
      "8": 19,
      "9": 20,
      "?": 21,
      "A": 22,
      "B": 23,
      "C": 24,
      "D": 25,
      "E": 26,
      "F": 27,
      "G": 28,
      "H": 29,
      "I": 30,
      "J": 31,
      "K": 32,
      "L": 33,
      "M": 34,
      "N": 35,
      "O": 36,
      "P": 37,
      "Q": 38,
      "R": 39,
      "S": 40,
      "T": 41,
      "U": 42,
      "V": 43,
      "W": 44,
      "X": 45,
      "Y": 46,
      "Z": 47,
      "_": 48,
      "a": 49,
      "b": 50,
      "c": 51,
      "d": 52,
      "e": 53,
      "f": 54,
      "g": 55,
      "h": 56,
      "i": 57,
      "j": 58,
      "k": 59,
      "l": 60,
      "m": 61,
      "n": 62,
      "o": 63,
      "p": 64,
      "q": 65,
      "r": 66,
      "s": 67,
      "t": 68,
      "u": 69,
      "v": 70,
      "w": 71,
      "x": 72,
      "y": 73,
      "z": 74,
      "Ç": 75,
      "Ö": 76,
      "ç": 77,
      "é": 78,
      "ö": 79,
      "ü": 80,
      "ğ": 81,
      "İ": 82,
      "ı": 83,
      "Ş": 84,
      "ş": 85
    },
    "unk_token": "<unk>"
  }
}