add tokenizer

vocab.json

@@ -1 +1 @@
-{"p": 0, "j": 2, "l": 3, "x": 4, "y": 5, "d": 6, "v": 7, "i": 8, "e": 9, "r": 10, "w": 11, "b": 12, "z": 13, "c": 14, "g": 15, "o": 16, "h": 17, "t": 18, "a": 19, "n": 20, "'": 21, "k": 22, "m": 23, "u": 24, "f": 25, "q": 26, "s": 27, "|": 1, "[UNK]": 28, "[PAD]": 29}
+{"t": 0, "c": 1, "'": 2, "o": 3, "a": 4, "v": 5, "z": 6, "r": 8, "i": 9, "f": 10, "w": 11, "m": 12, "g": 13, "x": 14, "u": 15, "e": 16, "p": 17, "d": 18, "s": 19, "h": 20, "q": 21, "k": 22, "l": 23, "y": 24, "n": 25, "b": 26, "j": 27, "|": 7, "[UNK]": 28, "[PAD]": 29}