add tokenizer

vocab.json

@@ -1 +1 @@
-{"A": 0, "E": 1, "p": 2, "J": 3, "o": 4, "'": 5, "z": 6, "u": 7, "g": 8, "W": 9, "C": 10, "n": 11, "-": 12, "i": 13, "B": 14, "a": 15, ".": 16, "K": 17, ",": 18, "O": 19, "l": 20, "H": 21, "m": 22, "T": 23, "b": 24, "y": 25, "j": 26, "c": 27, "G": 28, "\"": 29, "V": 30, "r": 31, "Q": 32, "I": 33, "!": 34, "Y": 35, ":": 36, "x": 37, "U": 38, "N": 39, "h": 40, "f": 41, "P": 42, "M": 43, "D": 44, "t": 45, "w": 46, "e": 47, "F": 48, ";": 49, "k": 50, "s": 52, "X": 53, "S": 54, "L": 55, "v": 56, "q": 57, "R": 58, "d": 59, "?": 60, "|": 51, "[UNK]": 61, "[PAD]": 62}
+{"l": 0, "H": 1, ".": 2, "t": 3, "G": 4, "L": 5, ";": 6, "a": 7, "C": 8, "n": 9, "R": 10, "N": 11, "-": 12, "Q": 13, "\"": 14, "w": 15, "q": 16, "X": 17, "P": 18, "'": 19, ":": 20, "M": 21, "F": 22, "r": 23, "j": 24, "z": 25, "B": 26, "v": 27, "W": 28, "D": 29, "s": 30, "c": 32, ",": 33, "f": 34, "O": 35, "u": 36, "?": 37, "E": 38, "b": 39, "A": 40, "T": 41, "k": 42, "K": 43, "d": 44, "Y": 45, "y": 46, "J": 47, "V": 48, "U": 49, "o": 50, "m": 51, "e": 52, "i": 53, "x": 54, "g": 55, "S": 56, "!": 57, "h": 58, "p": 59, "I": 60, "|": 31, "[UNK]": 61, "[PAD]": 62}