add tokenizer

vocab.json

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