mms-300m-paper / vocab.json
hts98's picture
Training in progress, epoch 1
764c540
{
",": 1,
".": 2,
"0": 3,
"1": 4,
"2": 5,
"3": 6,
"4": 7,
"5": 8,
"6": 9,
"7": 10,
"8": 11,
"9": 12,
"[PAD]": 107,
"[UNK]": 106,
"a": 13,
"b": 14,
"c": 15,
"d": 16,
"e": 17,
"f": 18,
"g": 19,
"h": 20,
"i": 21,
"j": 22,
"k": 23,
"l": 24,
"m": 25,
"n": 26,
"o": 27,
"p": 28,
"q": 29,
"r": 30,
"s": 31,
"t": 32,
"u": 33,
"v": 34,
"w": 35,
"x": 36,
"y": 37,
"z": 38,
"|": 0,
"à": 39,
"á": 40,
"â": 41,
"ã": 42,
"è": 43,
"é": 44,
"ê": 45,
"ì": 46,
"í": 47,
"ò": 48,
"ó": 49,
"ô": 50,
"õ": 51,
"ù": 52,
"ú": 53,
"ý": 54,
"ă": 55,
"đ": 56,
"ĩ": 57,
"ũ": 58,
"ơ": 59,
"ư": 60,
"ạ": 61,
"ả": 62,
"ấ": 63,
"ầ": 64,
"ẩ": 65,
"ẫ": 66,
"ậ": 67,
"ắ": 68,
"ằ": 69,
"ẳ": 70,
"ẵ": 71,
"ặ": 72,
"ẹ": 73,
"ẻ": 74,
"ẽ": 75,
"ế": 76,
"ề": 77,
"ể": 78,
"ễ": 79,
"ệ": 80,
"ỉ": 81,
"ị": 82,
"ọ": 83,
"ỏ": 84,
"ố": 85,
"ồ": 86,
"ổ": 87,
"ỗ": 88,
"ộ": 89,
"ớ": 90,
"ờ": 91,
"ở": 92,
"ỡ": 93,
"ợ": 94,
"ụ": 95,
"ủ": 96,
"ứ": 97,
"ừ": 98,
"ử": 99,
"ữ": 100,
"ự": 101,
"ỳ": 102,
"ỷ": 103,
"ỹ": 104,
"₫": 105
}