mms-1b-all / vocab.json
patrickvonplaten's picture
upload weights
1365444
raw
history blame
1.87 kB
{
"!": 75,
"\"": 62,
"$": 48,
"%": 47,
"&": 57,
"'": 31,
"+": 56,
",": 44,
"-": 32,
".": 37,
"/": 45,
"0": 27,
"1": 30,
"2": 35,
"3": 41,
"4": 39,
"5": 38,
"6": 40,
"7": 43,
"8": 42,
"9": 36,
":": 46,
";": 52,
"</s>": 2,
"<pad>": 0,
"<s>": 1,
"<unk>": 3,
"[": 59,
"]": 60,
"`": 92,
"a": 7,
"b": 24,
"c": 16,
"d": 15,
"e": 5,
"f": 19,
"g": 21,
"h": 13,
"i": 9,
"j": 29,
"k": 26,
"l": 14,
"m": 18,
"n": 10,
"o": 8,
"p": 20,
"q": 34,
"r": 12,
"s": 11,
"t": 6,
"u": 17,
"v": 25,
"w": 23,
"x": 28,
"y": 22,
"z": 33,
"|": 4,
"£": 68,
"¥": 53,
"§": 139,
"°": 58,
"²": 76,
"ß": 82,
"à": 84,
"á": 49,
"â": 81,
"ã": 66,
"ä": 78,
"å": 123,
"æ": 110,
"ç": 64,
"è": 79,
"é": 55,
"ê": 88,
"ë": 87,
"í": 50,
"î": 97,
"ï": 85,
"ð": 98,
"ñ": 83,
"ò": 105,
"ó": 67,
"ô": 86,
"õ": 69,
"ö": 74,
"ø": 91,
"ú": 70,
"û": 99,
"ü": 54,
"ý": 112,
"þ": 132,
"ā": 100,
"ă": 102,
"ć": 94,
"č": 89,
"ē": 143,
"ę": 119,
"ě": 140,
"ğ": 153,
"ī": 107,
"ı": 103,
"ł": 73,
"ń": 118,
"ň": 137,
"ō": 80,
"ő": 120,
"œ": 96,
"ř": 108,
"ş": 116,
"š": 90,
"ū": 101,
"ž": 95,
"ș": 104,
"ə": 138,
"ʻ": 115,
"́": 93,
"̇": 77,
"α": 106,
"κ": 109,
"π": 117,
"χ": 141,
"а": 144,
"в": 124,
"е": 125,
"з": 130,
"и": 113,
"й": 127,
"к": 114,
"л": 126,
"н": 128,
"ь": 131,
"я": 129,
"נ": 147,
"ע": 148,
"ṃ": 121,
"ạ": 111,
"ả": 145,
"ị": 146,
"ụ": 122,
"​": 71,
"–": 61,
"—": 51,
"‘": 72,
"’": 65,
"”": 63,
"≡": 142,
"京": 149,
"先": 135,
"大": 151,
"尚": 134,
"时": 133,
"生": 136,
"都": 150,
"阪": 152
}