add tokenizer

vocab.json

@@ -1 +1 @@
-{"sh": 1, "th": 2, "er": 3, "n": 4, "v": 5, "p": 6, "jh": 7, "d": 8, "b": 9, "z": 10, "ow": 11, "g": 12, "uw": 13, "hh": 14, "ah": 15, "iy": 16, "ih": 17, "f": 18, "l": 19, "zh": 20, "y": 21, "eh": 22, "s": 23, "k": 24, "uh": 25, "m": 26, "aa": 27, "ch": 28, "oy": 29, "w": 30, "ae": 31, "ey": 32, "r": 33, "aw": 34, "ay": 35, "ng": 36, "t": 37, "dh": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}
+{"ah": 1, "n": 2, "hh": 3, "k": 4, "iy": 5, "w": 6, "ow": 7, "th": 8, "ng": 9, "ey": 10, "g": 11, "uw": 12, "jh": 13, "dh": 14, "f": 15, "s": 16, "r": 17, "oy": 18, "y": 19, "l": 20, "ch": 21, "v": 22, "aw": 23, "ih": 24, "z": 25, "t": 26, "zh": 27, "uh": 28, "aa": 29, "b": 30, "ay": 31, "ae": 32, "sh": 33, "m": 34, "d": 35, "eh": 36, "p": 37, "er": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}