add tokenizer

vocab.json

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