add tokenizer

vocab.json

@@ -1 +1 @@
-{"ầ": 0, "t": 1, "é": 2, "ẩ": 3, "s": 4, "x": 5, "â": 6, "b": 7, "ê": 8, "ậ": 9, "ổ": 10, "m": 11, "ă": 12, "ỗ": 13, "v": 14, "á": 15, "ợ": 16, "ò": 17, "ì": 18, "ữ": 19, "y": 20, "d": 21, "ự": 22, "í": 23, "ừ": 24, "ả": 25, "o": 26, "u": 27, "ấ": 28, "ụ": 29, "ể": 30, "ộ": 31, "ọ": 32, "ờ": 33, "ề": 34, "ỏ": 35, "ặ": 36, "à": 37, "ỹ": 38, "ó": 39, "ạ": 40, "e": 41, "ù": 42, "p": 43, "ứ": 44, "ồ": 45, "ế": 46, "a": 47, "ỉ": 48, "l": 49, "ắ": 50, "ỵ": 51, "q": 52, "ẻ": 53, "c": 54, "ỳ": 55, "ẫ": 56, "ố": 57, "ô": 58, "ẹ": 59, "ư": 60, "n": 61, "ở": 62, "ễ": 63, "đ": 64, "ũ": 65, "ẽ": 66, "ý": 67, "k": 68, "r": 69, "ỡ": 70, "g": 71, "ú": 73, "h": 74, "ớ": 75, "4": 76, "ử": 77, "ẵ": 78, "ẳ": 79, "õ": 80, "ủ": 81, "ị": 82, "ĩ": 83, "ơ": 84, "ỷ": 85, "ã": 86, "ằ": 87, "i": 88, "ệ": 89, "è": 90, "|": 72, "[UNK]": 91, "[PAD]": 92}
+{"P": 0, "Í": 1, "Ị": 2, "Ê": 3, "Ớ": 4, "Ự": 5, "Ỏ": 6, "Ể": 7, "Ì": 8, "Ạ": 9, "Ộ": 10, "Ý": 11, "È": 12, "Ờ": 13, "Ừ": 14, "L": 15, "Ỹ": 16, "K": 17, "O": 18, "Ư": 19, "Ệ": 20, "Ỡ": 21, "H": 22, "M": 23, "Ẽ": 24, "Ậ": 25, "Ỵ": 26, "Â": 27, "Ã": 28, ":": 29, "Ữ": 30, "B": 31, "Ù": 32, "Ầ": 33, "Ề": 34, "Ỗ": 35, "D": 36, "A": 37, "Ẹ": 38, "C": 39, "Ỷ": 40, "Ỳ": 41, "Q": 42, "Ĩ": 43, "Ă": 44, "Ỉ": 45, "É": 46, "Ố": 47, "Ứ": 48, "Ử": 49, "I": 50, "Ó": 51, "Ẳ": 52, "E": 53, "V": 54, "Ò": 55, "N": 56, "Ắ": 57, "R": 58, "Y": 59, "Ồ": 60, "Ẫ": 61, "U": 62, "T": 63, "Ễ": 64, "Ủ": 65, "Ú": 66, "Ẻ": 67, "À": 68, "X": 69, "Ụ": 70, "Ả": 71, "Ẵ": 72, "Ằ": 73, "Ơ": 75, "Ặ": 76, "G": 77, "4": 78, "Á": 79, "Ế": 80, "Ấ": 81, "Ọ": 82, "S": 83, "Ổ": 84, "Õ": 85, "Ô": 86, "Ũ": 87, "Đ": 88, "Ở": 89, "Ẩ": 90, "Ợ": 91, "|": 74, "[UNK]": 92, "[PAD]": 93}