aaniket's picture
Upload tokenizer
52de8da
raw
history blame
750 Bytes
{
"[PAD]": 62,
"[UNK]": 61,
"aa": 53,
"ae": 22,
"ah": 44,
"ao": 34,
"aw": 15,
"ax": 45,
"ax-h": 5,
"axr": 50,
"ay": 37,
"b": 14,
"bcl": 49,
"ch": 56,
"d": 42,
"dcl": 7,
"dh": 41,
"dx": 11,
"eh": 19,
"el": 29,
"em": 60,
"en": 55,
"eng": 9,
"epi": 48,
"er": 57,
"ey": 36,
"f": 16,
"g": 52,
"gcl": 21,
"h#": 18,
"hh": 59,
"hv": 35,
"ih": 31,
"ix": 54,
"iy": 24,
"jh": 13,
"k": 1,
"kcl": 27,
"l": 43,
"m": 58,
"n": 32,
"ng": 4,
"nx": 25,
"ow": 28,
"oy": 2,
"p": 20,
"pau": 38,
"pcl": 0,
"q": 51,
"r": 23,
"s": 12,
"sh": 47,
"t": 46,
"tcl": 40,
"th": 26,
"uh": 6,
"uw": 33,
"ux": 10,
"v": 17,
"w": 39,
"y": 3,
"z": 30,
"zh": 8
}