add tokenizer

vocab.json

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