add tokenizer

vocab.json

@@ -1 +1 @@
-{"z": 0, "ƴ": 1, "n": 2, "ɗ": 3, "p": 4, "s": 5, "u": 6, "f": 7, "w": 8, "m": 9, "'": 10, "q": 11, "í": 12, "h": 13, "d": 14, "ɓ": 15, "ƙ": 16, "y": 17, "ʻ": 18, "j": 19, "o": 20, "c": 21, "k": 22, "i": 23, "v": 25, "b": 26, "e": 27, "l": 28, "t": 29, "g": 30, "r": 31, "a": 32, "x": 33, "|": 24, "[UNK]": 34, "[PAD]": 35}
+{"p": 0, "ƙ": 1, "b": 2, "y": 3, "k": 4, "x": 5, "c": 6, "n": 7, "j": 8, "d": 9, "w": 10, "'": 11, "i": 12, "u": 13, "r": 14, "v": 15, "m": 16, "ƴ": 17, "l": 18, "ɗ": 19, "s": 20, "o": 21, "ʻ": 22, "a": 23, "í": 24, "f": 25, "ɓ": 26, "h": 27, "z": 28, "q": 29, "t": 30, "g": 31, "e": 33, "|": 32, "[UNK]": 34, "[PAD]": 35}