latex-ocr / tokenizer-wordlevel.json
Young Ho Shin
Add examples and article.md
36bccd1
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 100,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 100
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "[PAD]"
},
"added_tokens": [
{
"id": 0,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 1
}
}
],
"special_tokens": {
"[CLS]": {
"id": "[CLS]",
"ids": [
1
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
2
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[UNK]": 0,
"[CLS]": 1,
"[SEP]": 2,
"[PAD]": 3,
"[MASK]": 4,
"}": 5,
"{": 6,
"\\": 7,
"_": 8,
"^": 9,
"(": 10,
")": 11,
"2": 12,
"1": 13,
"-": 14,
"=": 15,
",": 16,
"+": 17,
"frac": 18,
"i": 19,
"0": 20,
"x": 21,
"n": 22,
".": 23,
"d": 24,
"\\,": 25,
"a": 26,
"mu": 27,
"left": 28,
"right": 29,
"e": 30,
"k": 31,
"c": 32,
"m": 33,
"r": 34,
"p": 35,
"3": 36,
"alpha": 37,
"t": 38,
"partial": 39,
"~": 40,
"l": 41,
"A": 42,
"s": 43,
"&": 44,
"4": 45,
"j": 46,
"\\;": 47,
"g": 48,
"prime": 49,
"]": 50,
"[": 51,
"nu": 52,
"z": 53,
"pi": 54,
"|": 55,
"b": 56,
"phi": 57,
"\\\\": 58,
"mathrm": 59,
"q": 60,
"operatorname": 61,
"cal": 62,
"N": 63,
"delta": 64,
"f": 65,
"lambda": 66,
"beta": 67,
"bar": 68,
"T": 69,
"int": 70,
"array": 71,
"R": 72,
"S": 73,
"D": 74,
"L": 75,
"M": 76,
"B": 77,
"y": 78,
"sigma": 79,
"F": 80,
"theta": 81,
"/": 82,
"gamma": 83,
"h": 84,
"hat": 85,
"psi": 86,
"sqrt": 87,
"sum": 88,
"u": 89,
"H": 90,
"o": 91,
"rho": 92,
"tilde": 93,
"tau": 94,
"C": 95,
"P": 96,
"G": 97,
"V": 98,
"I": 99,
"X": 100,
"omega": 101,
"epsilon": 102,
"E": 103,
"J": 104,
"bf": 105,
"eta": 106,
"v": 107,
"xi": 108,
"Q": 109,
"Phi": 110,
"quad": 111,
"*": 112,
"5": 113,
"\\{": 114,
"vec": 115,
"begin": 116,
"end": 117,
"Gamma": 118,
"K": 119,
"infty": 120,
"\\}": 121,
"6": 122,
"U": 123,
"rangle": 124,
"dot": 125,
"W": 126,
"pm": 127,
"Lambda": 128,
"Z": 129,
"varphi": 130,
"Delta": 131,
"w": 132,
"chi": 133,
";": 134,
"8": 135,
"\\!": 136,
"Omega": 137,
"kappa": 138,
"qquad": 139,
"cdot": 140,
"Psi": 141,
"equiv": 142,
"langle": 143,
"overline": 144,
">": 145,
"<": 146,
"dagger": 147,
"zeta": 148,
"varepsilon": 149,
"cdots": 150,
"rightarrow": 151,
"O": 152,
"nabla": 153,
"Y": 154,
"ldots": 155,
":": 156,
"Sigma": 157,
"ell": 158,
"7": 159,
"mathcal": 160,
"\\:": 161,
"!": 162,
"otimes": 163,
"prod": 164,
"wedge": 165,
"9": 166,
"hspace": 167,
"Pi": 168,
"hbar": 169,
"sim": 170,
"vert": 171,
"in": 172,
"Big": 173,
"widetilde": 174,
"displaystyle": 175,
"times": 176,
"Theta": 177,
"underline": 178,
"mid": 179,
"to": 180,
"dots": 181,
"mathbf": 182,
"ast": 183,
"leq": 184,
"approx": 185,
"star": 186,
"stackrel": 187,
"perp": 188,
"widehat": 189,
"big": 190,
"vartheta": 191,
"'": 192,
"Bigr": 193,
"geq": 194,
"mp": 195,
"Bigl": 196,
"dag": 197,
"neq": 198,
"simeq": 199
},
"unk_token": "[UNK]"
}
}