tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 128,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<s>",
      "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": "</s>",
      "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
    },
    {
      "id": 4,
      "content": "<mask>",
      "single_word": false,
      "lstrip": true,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Lowercase"
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Removed",
    "invert": false
  },
  "post_processor": {
    "type": "RobertaProcessing",
    "sep": [
      "</s>",
      2
    ],
    "cls": [
      "<s>",
      0
    ],
    "trim_offsets": true,
    "add_prefix_space": false
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<s>": 0,
      "<pad>": 1,
      "</s>": 2,
      "<unk>": 3,
      "<mask>": 4,
      "e": 5,
      "a": 6,
      "s": 7,
      "i": 8,
      "r": 9,
      "n": 10,
      "AH0": 11,
      "o": 12,
      "N": 13,
      "t": 14,
      "l": 15,
      "S": 16,
      "L": 17,
      "T": 18,
      "R": 19,
      "K": 20,
      "c": 21,
      "d": 22,
      "D": 23,
      "u": 24,
      "IH0": 25,
      "m": 26,
      "M": 27,
      "Z": 28,
      "h": 29,
      "g": 30,
      "p": 31,
      "ER0": 32,
      "IY0": 33,
      "b": 34,
      "B": 35,
      "P": 36,
      "EH1": 37,
      "AE1": 38,
      "AA1": 39,
      "y": 40,
      "k": 41,
      "IH1": 42,
      "F": 43,
      "f": 44,
      "G": 45,
      "w": 46,
      "V": 47,
      "v": 48,
      "NG": 49,
      "'": 50,
      "IY1": 51,
      "EY1": 52,
      "HH": 53,
      "W": 54,
      "SH": 55,
      "OW1": 56,
      "AO1": 57,
      "OW0": 58,
      "AH1": 59,
      "UW1": 60,
      "AY1": 61,
      "JH": 62,
      "z": 63,
      "CH": 64,
      "Y": 65,
      "AA0": 66,
      "ER1": 67,
      "EH2": 68,
      "IH2": 69,
      "TH": 70,
      "AY2": 71,
      "AE2": 72,
      "EY2": 73,
      "AA2": 74,
      "EH0": 75,
      "j": 76,
      "AW1": 77,
      "OW2": 78,
      "x": 79,
      "IY2": 80,
      "UW0": 81,
      "AO2": 82,
      "UH1": 83,
      "AE0": 84,
      "q": 85,
      "AO0": 86,
      "AH2": 87,
      "UW2": 88,
      "AY0": 89,
      "OY1": 90,
      "-": 91,
      "EY0": 92,
      "DH": 93,
      "AW2": 94,
      "ER2": 95,
      "ZH": 96,
      "UH2": 97,
      "AW0": 98,
      "UH0": 99,
      "OY2": 100,
      "OY0": 101,
      ".": 102
    },
    "unk_token": "<unk>"
  }
}