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": 2,
      "content": "BOS",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "EOS",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 196,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "String": "\n"
        },
        "content": " UTT_BOUNDARY"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "BOS": 2,
      "EOS": 3,
      "WORD_BOUNDARY": 4,
      "UTT_BOUNDARY": 5,
      "s": 6,
      "iː": 7,
      "ð": 8,
      "ɛ": 9,
      "ɹ": 10,
      "z": 11,
      "ʌ": 12,
      "f": 13,
      "eɪ": 14,
      "w": 15,
      "ɪ": 16,
      "ɡ": 17,
      "l": 18,
      "æ": 19,
      "ɑ": 20,
      "h": 21,
      "ə": 22,
      "ʊ": 23,
      "k": 24,
      "p": 25,
      "uː": 26,
      "b": 27,
      "i": 28,
      "t": 29,
      "aɪ": 30,
      "θ": 31,
      "ŋ": 32,
      "j": 33,
      "ɔ": 34,
      "m": 35,
      "ɔɪ": 36,
      "n": 37,
      "d": 38,
      "oʊ": 39,
      "aʊ": 40,
      "v": 41,
      "ɜː": 42,
      "t̠ʃ": 43,
      "d̠ʒ": 44,
      "ʃ": 45,
      "iə": 46,
      "ʒ": 47,
      "ɑ̃": 48,
      "r": 49,
      "x": 50,
      "nʲ": 51,
      "ɒ": 52,
      "a": 53,
      "ɑː": 54,
      "ɔː": 55,
      "əʊ": 56,
      "ɐ": 57,
      "eə": 58,
      "ʊə": 59,
      "n̩": 60,
      "aː": 61,
      "y": 62,
      "ɛ̃": 63,
      "ʁ": 64,
      "e": 65,
      "ɔ̃": 66,
      "u": 67,
      "o": 68,
      "œ̃": 69,
      "ø": 70,
      "œ": 71,
      "oː": 72,
      "yː": 73,
      "ɲ": 74,
      "ts": 75,
      "eː": 76,
      "ʀ": 77,
      "ç": 78,
      "ɛɪ": 79,
      "ʏ": 80,
      "ɛː": 81,
      "pf": 82,
      "øː": 83,
      "ã": 84,
      "ɾ": 85,
      "β": 86,
      "ʎ": 87,
      "ɣ": 88,
      "ʝ": 89,
      "oɪ": 90,
      "eʊ": 91,
      "pː": 92,
      "ɟ": 93,
      "ʋ": 94,
      "ɪː": 95,
      "ɵ": 96,
      "œy": 97,
      "tʲ": 98,
      "au̯": 99,
      "ʂ": 100,
      "ɤ": 101,
      "kʰ": 102,
      "ʈʂʰ": 103,
      "ɕ": 104,
      "pʰ": 105,
      "tɕ": 106,
      "ʈʂ": 107,
      "ɹ̩": 108,
      "tɕʰ": 109,
      "tʰ": 110,
      "ɻ": 111,
      "ɥ": 112,
      "tsʰ": 113,
      "ei̯": 114,
      "ou̯": 115,
      "ɻ̩": 116,
      "ai̯": 117,
      "ɯː": 118,
      "ɯ": 119,
      "pʲ": 120,
      "ɸ": 121,
      "rʲ": 122,
      "kʲ": 123,
      "bʲ": 124,
      "mʲ": 125,
      "kː": 126,
      "æi": 127,
      "yi": 128,
      "ɵː": 129,
      "tː": 130,
      "æː": 131,
      "dʑ": 132,
      "l̩": 133,
      "œː": 134,
      "ʌː": 135,
      "ɜ": 136,
      "ʔ": 137,
      "s̺": 138,
      "ts̻": 139,
      "s̻": 140,
      "c": 141,
      "ts̺": 142,
      "tsː": 143,
      "ɟː": 144,
      "t̠ʃː": 145,
      "ɡː": 146,
      "dː": 147,
      "cː": 148,
      "bː": 149,
      "dzː": 150,
      "ɫ": 151,
      "ʊː": 152,
      "q": 153,
      "øy": 154,
      "χ": 155,
      "i̯": 156,
      "t̪": 157,
      "d̪": 158,
      "lʲ": 159,
      "ɡʲ": 160,
      "hʲ": 161,
      "dʲ": 162,
      "çʲ": 163,
      "uə": 164,
      "ŭ": 165,
      "fʲ": 166,
      "aɨ": 167,
      "ɨ": 168,
      "uɨ": 169,
      "əɪ": 170,
      "ɨː": 171,
      "ɬ": 172,
      "əɨ": 173,
      "ɪu": 174,
      "ʉ": 175,
      "ʉː": 176,
      "ɑɪ": 177,
      "ʑ": 178,
      "dz": 179,
      "d̠ʒː": 180,
      "ɐ̃": 181,
      "ɛʊ": 182,
      "ũ": 183,
      "iʊ": 184,
      "õ": 185,
      "uɪ": 186,
      "sʲ": 187,
      "t̠ʃʲ": 188,
      "ɔa": 189,
      "ea": 190,
      "iɪ": 191,
      "tsʲ": 192,
      "eo": 193,
      "d̠ʒʲ": 194,
      "ɾʲ": 195
    },
    "unk_token": "UNK"
  }
}