add tokenizer

vocab.json

@@ -1 +1 @@
-{"Q:": 0, "I:": 1, "O:": 2, "M": 3, "Z": 4, "TS": 5, "G": 6, "SH": 7, "W": 8, "HY": 9, "J": 10, "O": 11, "T": 12, "H": 13, "K": 14, "A": 15, "P": 16, "A:": 17, "RY": 18, "N!": 19, "PY": 20, "U": 21, "B": 22, "F": 23, "TY": 24, "S": 25, "GY": 26, "U:": 27, "CH": 28, "R": 29, "KY": 30, "E": 31, "E:": 32, "D": 33, "I": 34, "Q": 35, "BY": 36, "Y": 37, "N!:": 38, "[UNK]": 39, "[PAD]": 40, " ": 41, "|": 42}
+{"k": 0, "i:": 1, "u:": 2, "t": 3, "gy": 4, "b": 5, "e": 6, "a": 7, "p": 8, "w": 9, "ch": 10, "f": 11, "hy": 12, "sh": 13, "m": 14, "a:": 15, "u": 16, "z": 17, "r": 18, "e:": 19, "g": 20, "ts": 21, "N": 22, "y": 23, "h": 24, "o": 25, "o:": 26, "ty": 27, "ky": 28, "N:": 29, "q:": 30, "ry": 31, "s": 32, "py": 33, "by": 34, "i": 35, "j": 36, "d": 37, "q": 38, "[UNK]": 39, "[PAD]": 40, " ": 41, "|": 42}