add tokenizer

vocab.json

@@ -1 +1 @@
-{"h": 0, "â": 1, "d": 2, "e": 3, "q": 4, "k": 5, "x": 6, "z": 7, "l": 8, "p": 9, "f": 10, "b": 11, "g": 12, "n": 13, "j": 14, "s": 15, "'": 16, "i": 17, "m": 18, "o": 19, "w": 20, "c": 21, "v": 22, "u": 23, "a": 24, "t": 25, "r": 26, "y": 28, "|": 27, "[UNK]": 29, "[PAD]": 30}
+{"u": 0, "r": 1, "s": 2, "â": 3, "n": 4, "a": 5, "e": 6, "h": 8, "m": 9, "d": 10, "k": 11, "j": 12, "v": 13, "g": 14, "l": 15, "c": 16, "t": 17, "w": 18, "o": 19, "x": 20, "i": 21, "y": 22, "f": 23, "q": 24, "'": 25, "p": 26, "b": 27, "z": 28, "|": 7, "[UNK]": 29, "[PAD]": 30}