tokenizer.json

{
  "vocab": [
    "<pad>",
    "<unk>",
    "<bos>",
    "<eos>",
    " ",
    "a",
    "b",
    "c",
    "d",
    "e",
    "f",
    "g",
    "h",
    "i",
    "j",
    "k",
    "l",
    "m",
    "n",
    "o",
    "p",
    "q",
    "r",
    "s",
    "t",
    "u",
    "v",
    "w",
    "x",
    "y",
    "z",
    "es",
    "er",
    "ed",
    "'s",
    "ng",
    "ing",
    "ma",
    "le",
    "al",
    "re",
    "en",
    "co",
    "ne",
    "ch",
    "st",
    "te",
    "the",
    "and",
    "of",
    "in",
    "to",
    "is",
    "was",
    "it",
    "he",
    "for",
    "on",
    "as",
    "by",
    "that",
    "with",
    "at",
    "be",
    "this",
    "have",
    "water",
    "sun",
    "earth",
    "tree",
    "plant",
    "animal",
    "bird",
    "fish",
    "dog",
    "cat",
    "fire",
    "air",
    "head",
    "hand",
    "eye",
    "face",
    "body",
    "heart",
    "eat",
    "walk",
    "play",
    "work",
    "see",
    "make",
    "take",
    "sleep",
    "talk",
    "help",
    "know",
    "house",
    "home",
    "room",
    "door",
    "car",
    "book",
    "bed",
    "school",
    "big",
    "small",
    "good",
    "bad",
    "new",
    "old",
    "hot",
    "cold",
    "time",
    "day",
    "night",
    "year",
    "world",
    "up",
    "man",
    "woman",
    "child",
    "boy",
    "girl",
    "people",
    "one",
    "two",
    "three",
    "four"
  ],
  "tok_to_id": {
    "<pad>": 0,
    "<unk>": 1,
    "<bos>": 2,
    "<eos>": 3,
    " ": 4,
    "a": 5,
    "b": 6,
    "c": 7,
    "d": 8,
    "e": 9,
    "f": 10,
    "g": 11,
    "h": 12,
    "i": 13,
    "j": 14,
    "k": 15,
    "l": 16,
    "m": 17,
    "n": 18,
    "o": 19,
    "p": 20,
    "q": 21,
    "r": 22,
    "s": 23,
    "t": 24,
    "u": 25,
    "v": 26,
    "w": 27,
    "x": 28,
    "y": 29,
    "z": 30,
    "es": 31,
    "er": 32,
    "ed": 33,
    "'s": 34,
    "ng": 35,
    "ing": 36,
    "ma": 37,
    "le": 38,
    "al": 39,
    "re": 40,
    "en": 41,
    "co": 42,
    "ne": 43,
    "ch": 44,
    "st": 45,
    "te": 46,
    "the": 47,
    "and": 48,
    "of": 49,
    "in": 50,
    "to": 51,
    "is": 52,
    "was": 53,
    "it": 54,
    "he": 55,
    "for": 56,
    "on": 57,
    "as": 58,
    "by": 59,
    "that": 60,
    "with": 61,
    "at": 62,
    "be": 63,
    "this": 64,
    "have": 65,
    "water": 66,
    "sun": 67,
    "earth": 68,
    "tree": 69,
    "plant": 70,
    "animal": 71,
    "bird": 72,
    "fish": 73,
    "dog": 74,
    "cat": 75,
    "fire": 76,
    "air": 77,
    "head": 78,
    "hand": 79,
    "eye": 80,
    "face": 81,
    "body": 82,
    "heart": 83,
    "eat": 84,
    "walk": 85,
    "play": 86,
    "work": 87,
    "see": 88,
    "make": 89,
    "take": 90,
    "sleep": 91,
    "talk": 92,
    "help": 93,
    "know": 94,
    "house": 95,
    "home": 96,
    "room": 97,
    "door": 98,
    "car": 99,
    "book": 100,
    "bed": 101,
    "school": 102,
    "big": 103,
    "small": 104,
    "good": 105,
    "bad": 106,
    "new": 107,
    "old": 108,
    "hot": 109,
    "cold": 110,
    "time": 111,
    "day": 112,
    "night": 113,
    "year": 114,
    "world": 115,
    "up": 116,
    "man": 117,
    "woman": 118,
    "child": 119,
    "boy": 120,
    "girl": 121,
    "people": 122,
    "one": 123,
    "two": 124,
    "three": 125,
    "four": 126
  }
}