add tokenizer

vocab.json

@@ -1 +1 @@
-{"iy ": 1, "n ": 2, "r ": 3, "en ": 4, "dh ": 5, "sh ": 6, "er ": 7, "el ": 8, "aa ": 9, "eng ": 10, "h# ": 11, "axr ": 12, "ae ": 13, "ay ": 14, "dx ": 15, "l ": 16, "zh ": 17, "aw ": 18, "ax ": 19, "s ": 20, "eh ": 21, "v ": 22, "em ": 23, "f ": 24, "ih ": 25, "k ": 26, "ey ": 27, "gcl ": 28, "p ": 29, "ah ": 30, "ix ": 31, "g ": 32, "uh ": 33, "pau ": 34, "w ": 35, "uw ": 36, "ao ": 37, "ux ": 38, "hh ": 39, "d ": 40, "th ": 41, "q ": 42, "ch ": 43, "ow ": 44, "ng ": 45, "tcl ": 46, "t ": 47, "y ": 48, "bcl ": 49, "dcl ": 50, "m ": 51, "jh ": 52, "kcl ": 53, "b ": 54, "z ": 55, "nx ": 56, "hv ": 57, "epi ": 58, "pcl ": 59, "oy ": 60, "ax-h ": 61, "[UNK]": 63, "[PAD]": 63}
+{"aa": 0, "zh": 1, "g": 2, "m": 3, "ao": 4, "kcl": 5, "bcl": 6, "eh": 7, "sh": 8, "y": 9, "th": 10, "ch": 11, "r": 12, "h#": 13, "jh": 14, "z": 15, "ax-h": 16, "l": 17, "nx": 18, "ae": 19, "hh": 20, "ix": 21, "dcl": 22, "n": 23, "dx": 24, "ux": 25, "k": 26, "axr": 27, "eng": 28, "dh": 29, "ih": 30, "iy": 31, "ng": 32, "f": 33, "en": 34, "q": 35, "t": 36, "el": 37, "pau": 38, "ay": 39, "tcl": 40, "oy": 41, "hv": 42, "aw": 43, "ow": 44, "er": 45, "uh": 46, "gcl": 47, "ah": 48, "ey": 49, "b": 50, "ax": 51, "p": 52, "uw": 53, "v": 54, "epi": 55, "w": 56, "em": 57, "pcl": 58, "d": 59, "s": 60, "[UNK]": 61, "[PAD]": 62}