add tokenizer

vocab.json

@@ -1 +1 @@
-{"x": 0, "p": 1, "v": 2, "z": 3, "j": 4, "w": 5, "ɓ": 6, "l": 7, "f": 8, "t": 9, "k": 10, "n": 11, "g": 12, "s": 13, "c": 14, "d": 15, "í": 16, "b": 17, "ƙ": 18, "ƴ": 20, "h": 21, "’": 22, "ʻ": 24, "m": 25, "y": 26, "ɗ": 27, "i": 28, "'": 29, "r": 30, "o": 31, "e": 32, "a": 33, "q": 34, "u": 35, "|": 19, "/": 23, "[UNK]": 36, "[PAD]": 37}
+{"’": 0, "u": 1, "x": 2, "m": 3, "í": 4, "q": 5, "f": 6, "k": 7, "g": 8, "d": 9, "t": 10, "i": 11, "o": 13, "s": 14, "y": 15, "z": 16, "c": 17, "ƙ": 18, "l": 19, "w": 20, "e": 21, "p": 23, "h": 24, "r": 25, "ƴ": 26, "b": 27, "ʻ": 28, "a": 29, "'": 30, "ɗ": 31, "ɓ": 32, "j": 33, "n": 34, "v": 35, "|": 12, "/": 22, "[UNK]": 36, "[PAD]": 37}