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": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "[UNK]",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "[UNK]": 0,
      "[CLS]": 1,
      "[SEP]": 2,
      "[PAD]": 3,
      "[MASK]": 4,
      "!": 5,
      ".": 6,
      "G": 7,
      "M": 8,
      "Q": 9,
      "T": 10,
      "W": 11,
      "a": 12,
      "b": 13,
      "d": 14,
      "e": 15,
      "f": 16,
      "i": 17,
      "j": 18,
      "l": 19,
      "m": 20,
      "n": 21,
      "o": 22,
      "p": 23,
      "q": 24,
      "r": 25,
      "s": 26,
      "t": 27,
      "u": 28,
      "v": 29,
      "w": 30,
      "ç": 31,
      "é": 32,
      "..": 33,
      "ou": 34,
      "aou": 35,
      "aouf": 36,
      "Waouf": 37,
      "rr": 38,
      "is": 39,
      "Grr": 40,
      "le": 41,
      "on": 42,
      "su": 43,
      "...": 44,
      "Grrr": 45,
      "suis": 46,
      "as": 47,
      "ble": 48,
      "dis": 49,
      "ible": 50,
      "je": 51,
      "oi": 52,
      "pon": 53,
      "pas": 54,
      "rd": 55,
      "sou": 56,
      "te": 57,
      "uoi": 58,
      "....": 59,
      "dispon": 60,
      "sourd": 61,
      "disponible": 62,
      "!!": 63,
      "!.": 64,
      "Ma": 65,
      "Quoi": 66,
      "Ta": 67,
      "Tu": 68,
      "aa": 69,
      "ai": 70,
      "dé": 71,
      "eu": 72,
      "fai": 73,
      "ir": 74,
      "iu": 75,
      "me": 76,
      "non": 77,
      "or": 78,
      "quoi": 79,
      "riu": 80,
      "ste": 81,
      "sor": 82,
      "tir": 83,
      "veu": 84,
      "waouf": 85,
      "waa": 86,
      "ça": 87,
      "les": 88,
      "teste": 89,
      "Mariu": 90,
      "déteste": 91,
      "fait": 92,
      "sortir": 93,
      "veut": 94,
      "Marius": 95
    },
    "merges": [
      [
        ".",
        "."
      ],
      [
        "o",
        "u"
      ],
      [
        "a",
        "ou"
      ],
      [
        "aou",
        "f"
      ],
      [
        "W",
        "aouf"
      ],
      [
        "r",
        "r"
      ],
      [
        "i",
        "s"
      ],
      [
        "G",
        "rr"
      ],
      [
        "l",
        "e"
      ],
      [
        "o",
        "n"
      ],
      [
        "s",
        "u"
      ],
      [
        "..",
        "."
      ],
      [
        "Grr",
        "r"
      ],
      [
        "su",
        "is"
      ],
      [
        "a",
        "s"
      ],
      [
        "b",
        "le"
      ],
      [
        "d",
        "is"
      ],
      [
        "i",
        "ble"
      ],
      [
        "j",
        "e"
      ],
      [
        "o",
        "i"
      ],
      [
        "p",
        "on"
      ],
      [
        "p",
        "as"
      ],
      [
        "r",
        "d"
      ],
      [
        "s",
        "ou"
      ],
      [
        "t",
        "e"
      ],
      [
        "u",
        "oi"
      ],
      [
        "..",
        ".."
      ],
      [
        "dis",
        "pon"
      ],
      [
        "sou",
        "rd"
      ],
      [
        "dispon",
        "ible"
      ],
      [
        "!",
        "!"
      ],
      [
        "!",
        "."
      ],
      [
        "M",
        "a"
      ],
      [
        "Q",
        "uoi"
      ],
      [
        "T",
        "a"
      ],
      [
        "T",
        "u"
      ],
      [
        "a",
        "a"
      ],
      [
        "a",
        "i"
      ],
      [
        "d",
        "é"
      ],
      [
        "e",
        "u"
      ],
      [
        "f",
        "ai"
      ],
      [
        "i",
        "r"
      ],
      [
        "i",
        "u"
      ],
      [
        "m",
        "e"
      ],
      [
        "n",
        "on"
      ],
      [
        "o",
        "r"
      ],
      [
        "q",
        "uoi"
      ],
      [
        "r",
        "iu"
      ],
      [
        "s",
        "te"
      ],
      [
        "s",
        "or"
      ],
      [
        "t",
        "ir"
      ],
      [
        "v",
        "eu"
      ],
      [
        "w",
        "aouf"
      ],
      [
        "w",
        "aa"
      ],
      [
        "ç",
        "a"
      ],
      [
        "le",
        "s"
      ],
      [
        "te",
        "ste"
      ],
      [
        "Ma",
        "riu"
      ],
      [
        "dé",
        "teste"
      ],
      [
        "fai",
        "t"
      ],
      [
        "sor",
        "tir"
      ],
      [
        "veu",
        "t"
      ],
      [
        "Mariu",
        "s"
      ]
    ]
  }
}