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": 55,
      "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,
      "m": 6,
      "ɛ": 7,
      "ɲ": 8,
      "y": 9,
      "n": 10,
      "k": 11,
      "ɑ": 12,
      "r": 13,
      "aː": 14,
      "d": 15,
      "i": 16,
      "o": 17,
      "h": 18,
      "z": 19,
      "v": 20,
      "l": 21,
      "eː": 22,
      "j": 23,
      "ʃ": 24,
      "ɟ": 25,
      "s": 26,
      "oː": 27,
      "p": 28,
      "t": 29,
      "tsː": 30,
      "b": 31,
      "u": 32,
      "ɡ": 33,
      "tː": 34,
      "f": 35,
      "ø": 36,
      "t̠ʃ": 37,
      "uː": 38,
      "iː": 39,
      "ts": 40,
      "ɟː": 41,
      "yː": 42,
      "øː": 43,
      "ʎ": 44,
      "t̠ʃː": 45,
      "c": 46,
      "ɡː": 47,
      "kː": 48,
      "ɑː": 49,
      "dː": 50,
      "pː": 51,
      "ʒ": 52,
      "cː": 53,
      "bː": 54
    },
    "unk_token": "UNK"
  }
}