add tokenizer

vocab.json

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