add tokenizer

vocab.json

@@ -1 +1 @@
-{"ay": 1, "p": 2, "aw": 3, "t": 4, "dx": 5, "ae": 6, "uh": 7, "hh": 8, "f": 9, "m": 10, "s": 11, "eh": 12, "k": 13, "g": 14, "zh": 15, "ey": 16, "ah": 17, "y": 18, "v": 19, "n": 20, "iy": 21, "z": 22, "ih": 23, "ch": 24, "er": 25, "aa": 26, "b": 27, "th": 28, "r": 29, "l": 30, "sh": 31, "jh": 32, "dh": 33, "uw": 34, "ng": 35, "ow": 36, "oy": 37, "d": 38, "w": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}
+{"ay": 1, "p": 2, "aw": 3, "t": 4, "ae": 5, "uh": 6, "hh": 7, "f": 8, "m": 9, "s": 10, "eh": 11, "k": 12, "g": 13, "zh": 14, "ey": 15, "ah": 16, "y": 17, "v": 18, "n": 19, "iy": 20, "z": 21, "ih": 22, "ch": 23, "er": 24, "aa": 25, "b": 26, "th": 27, "r": 28, "l": 29, "sh": 30, "jh": 31, "dh": 32, "uw": 33, "ng": 34, "ow": 35, "oy": 36, "d": 37, "w": 38, "|": 0, "[UNK]": 39, "[PAD]": 40}