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": 3,
      "content": "UTT_BOUNDARY",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "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,
      "WORD_BOUNDARY": 2,
      "UTT_BOUNDARY": 3,
      "s": 4,
      "iː": 5,
      "ð": 6,
      "ɛ": 7,
      "ɹ": 8,
      "z": 9,
      "ʌ": 10,
      "f": 11,
      "eɪ": 12,
      "w": 13,
      "ɪ": 14,
      "ɡ": 15,
      "l": 16,
      "æ": 17,
      "ɑ": 18,
      "h": 19,
      "ə": 20,
      "ʊ": 21,
      "k": 22,
      "p": 23,
      "uː": 24,
      "b": 25,
      "i": 26,
      "t": 27,
      "aɪ": 28,
      "θ": 29,
      "ŋ": 30,
      "j": 31,
      "ɔ": 32,
      "m": 33,
      "ɔɪ": 34,
      "n": 35,
      "d": 36,
      "oʊ": 37,
      "aʊ": 38,
      "v": 39,
      "ɜː": 40,
      "t̠ʃ": 41,
      "d̠ʒ": 42,
      "ʃ": 43,
      "iə": 44,
      "ʒ": 45,
      "ɑ̃": 46,
      "r": 47,
      "x": 48,
      "nʲ": 49,
      "ɒ": 50,
      "a": 51,
      "ɑː": 52,
      "ɔː": 53,
      "əʊ": 54,
      "ɐ": 55,
      "eə": 56,
      "ʊə": 57,
      "n̩": 58,
      "aː": 59,
      "y": 60,
      "ɛ̃": 61,
      "ʁ": 62,
      "e": 63,
      "ɔ̃": 64,
      "u": 65,
      "o": 66,
      "œ̃": 67,
      "ø": 68,
      "œ": 69,
      "oː": 70,
      "yː": 71,
      "ɲ": 72,
      "ts": 73,
      "eː": 74,
      "ʀ": 75,
      "ç": 76,
      "ɛɪ": 77,
      "ʏ": 78,
      "ɛː": 79,
      "pf": 80,
      "øː": 81,
      "ã": 82,
      "ɾ": 83,
      "β": 84,
      "ʎ": 85,
      "ɣ": 86,
      "ʝ": 87,
      "oɪ": 88,
      "eʊ": 89,
      "pː": 90,
      "ɟ": 91,
      "ʋ": 92,
      "ɪː": 93,
      "ɵ": 94,
      "œy": 95,
      "tʲ": 96,
      "au̯": 97,
      "ʂ": 98,
      "ɤ": 99,
      "kʰ": 100,
      "ʈʂʰ": 101,
      "ɕ": 102,
      "pʰ": 103,
      "tɕ": 104,
      "ʈʂ": 105,
      "ɹ̩": 106,
      "tɕʰ": 107,
      "tʰ": 108,
      "ɻ": 109,
      "ɥ": 110,
      "tsʰ": 111,
      "ei̯": 112,
      "ou̯": 113,
      "ɻ̩": 114,
      "ai̯": 115,
      "ɯː": 116,
      "ɯ": 117,
      "pʲ": 118,
      "ɸ": 119,
      "rʲ": 120,
      "kʲ": 121,
      "bʲ": 122,
      "mʲ": 123,
      "kː": 124,
      "æi": 125,
      "yi": 126,
      "ɵː": 127,
      "tː": 128,
      "æː": 129,
      "dʑ": 130,
      "l̩": 131,
      "œː": 132,
      "ʌː": 133,
      "ɜ": 134,
      "ʔ": 135,
      "s̺": 136,
      "ts̻": 137,
      "s̻": 138,
      "c": 139,
      "ts̺": 140,
      "tsː": 141,
      "ɟː": 142,
      "t̠ʃː": 143,
      "ɡː": 144,
      "dː": 145,
      "cː": 146,
      "bː": 147,
      "dzː": 148,
      "ɫ": 149,
      "ʊː": 150,
      "q": 151,
      "øy": 152,
      "χ": 153,
      "i̯": 154,
      "t̪": 155,
      "d̪": 156,
      "lʲ": 157,
      "ɡʲ": 158,
      "hʲ": 159,
      "dʲ": 160,
      "çʲ": 161,
      "uə": 162,
      "ŭ": 163,
      "fʲ": 164,
      "aɨ": 165,
      "ɨ": 166,
      "uɨ": 167,
      "əɪ": 168,
      "ɨː": 169,
      "ɬ": 170,
      "əɨ": 171,
      "ɪu": 172,
      "ʉ": 173,
      "ʉː": 174,
      "ɑɪ": 175,
      "ʑ": 176,
      "dz": 177,
      "d̠ʒː": 178,
      "ɐ̃": 179,
      "ɛʊ": 180,
      "ũ": 181,
      "iʊ": 182,
      "õ": 183,
      "uɪ": 184,
      "sʲ": 185,
      "t̠ʃʲ": 186,
      "ɔa": 187,
      "ea": 188,
      "iɪ": 189,
      "tsʲ": 190,
      "eo": 191,
      "d̠ʒʲ": 192,
      "ɾʲ": 193
    },
    "unk_token": "UNK"
  }
}