w2v2-vi-en-char-based / vocab.json
tuanio's picture
Upload tokenizer
e11a91f
{
" ": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"[PAD]": 100,
"[UNK]": 99,
"a": 12,
"b": 13,
"c": 14,
"d": 15,
"e": 16,
"f": 17,
"g": 18,
"h": 19,
"i": 20,
"j": 21,
"k": 22,
"l": 23,
"m": 24,
"n": 25,
"o": 26,
"p": 27,
"q": 28,
"r": 29,
"s": 30,
"t": 31,
"u": 32,
"v": 33,
"w": 34,
"x": 35,
"y": 36,
"z": 37,
"|": 0,
"à": 38,
"á": 39,
"â": 40,
"ã": 41,
"è": 42,
"é": 43,
"ê": 44,
"ì": 45,
"í": 46,
"ò": 47,
"ó": 48,
"ô": 49,
"õ": 50,
"ù": 51,
"ú": 52,
"ý": 53,
"ă": 54,
"đ": 55,
"ĩ": 56,
"ũ": 57,
"ơ": 58,
"ạ": 59,
"ả": 60,
"ấ": 61,
"ầ": 62,
"ẩ": 63,
"ẫ": 64,
"ậ": 65,
"ắ": 66,
"ằ": 67,
"ẳ": 68,
"ẵ": 69,
"ặ": 70,
"ẹ": 71,
"ẻ": 72,
"ẽ": 73,
"ế": 74,
"ề": 75,
"ể": 76,
"ễ": 77,
"ệ": 78,
"ỉ": 79,
"ị": 80,
"ọ": 81,
"ỏ": 82,
"ố": 83,
"ồ": 84,
"ổ": 85,
"ỗ": 86,
"ộ": 87,
"ớ": 88,
"ờ": 89,
"ở": 90,
"ỡ": 91,
"ợ": 92,
"ụ": 93,
"ủ": 94,
"ỳ": 95,
"ỵ": 96,
"ỷ": 97,
"ỹ": 98
}