add tokenizer

vocab.json

@@ -1 +1 @@
-{"ể": 0, "ị": 1, "n": 2, "ủ": 3, "ẽ": 4, "õ": 5, "ắ": 6, "o": 7, "ã": 8, "q": 9, "ờ": 10, "ề": 11, "l": 12, "m": 13, "f": 14, "ơ": 15, "ê": 16, "ó": 17, "ẳ": 18, "x": 19, "ỳ": 20, "ò": 22, "ẹ": 23, "k": 24, "ĩ": 25, "ố": 26, "y": 27, "â": 28, "é": 29, "ẫ": 30, "ổ": 31, "è": 32, "à": 33, "ư": 34, "ý": 35, "j": 36, "á": 37, "e": 38, "u": 39, "i": 40, "b": 41, "d": 42, "ỹ": 43, "ễ": 44, "ặ": 45, "ậ": 46, "a": 47, "ô": 48, "ạ": 49, "ộ": 50, "ở": 51, "ợ": 52, "ệ": 53, "ả": 54, "ũ": 55, "ế": 56, "t": 57, "c": 58, "ẵ": 59, "ỏ": 60, "ì": 61, "ọ": 62, "ử": 63, "g": 64, "ù": 65, "ú": 66, "r": 67, "w": 68, "v": 69, "ứ": 70, "ầ": 71, "h": 72, "í": 73, "ẩ": 74, "ừ": 75, "s": 76, "đ": 77, "ụ": 78, "ự": 79, "p": 80, "ỵ": 81, "ỷ": 82, "ấ": 83, "ồ": 84, "ớ": 85, "ỗ": 86, "ẻ": 87, "ữ": 88, "ă": 89, "z": 90, "ằ": 91, "ỉ": 92, "ỡ": 93, "|": 21, "[UNK]": 94, "[PAD]": 95}
+{"o": 0, "ơ": 1, "ế": 2, "ỵ": 3, "ũ": 4, "ọ": 6, "k": 7, "ẩ": 8, "f": 9, "t": 10, "ó": 11, "ợ": 12, "q": 13, "ữ": 14, "c": 15, "ỳ": 16, "w": 17, "r": 18, "ỏ": 19, "ú": 20, "é": 21, "õ": 22, "ẽ": 23, "ỉ": 24, "ù": 25, "ộ": 26, "ừ": 27, "u": 28, "ã": 29, "ở": 30, "m": 31, "ă": 32, "á": 33, "ỷ": 34, "ệ": 35, "ồ": 36, "d": 37, "ẻ": 38, "s": 39, "ả": 40, "ề": 41, "ờ": 42, "ố": 43, "ẵ": 44, "ị": 45, "ì": 46, "ư": 47, "ằ": 48, "ẳ": 49, "l": 50, "j": 51, "ứ": 52, "p": 53, "ẹ": 54, "ê": 55, "e": 56, "z": 57, "ổ": 58, "đ": 59, "ặ": 60, "y": 61, "è": 62, "ĩ": 63, "i": 64, "ỡ": 65, "â": 66, "ý": 67, "ò": 68, "ầ": 69, "g": 70, "à": 71, "h": 72, "x": 73, "ễ": 74, "í": 75, "ỹ": 76, "ẫ": 77, "ô": 78, "ự": 79, "ắ": 80, "ậ": 81, "ụ": 82, "b": 83, "ử": 84, "ủ": 85, "ấ": 86, "ể": 87, "ớ": 88, "ỗ": 89, "ạ": 90, "v": 91, "n": 92, "a": 93, "|": 5, "[UNK]": 94, "[PAD]": 95}