Upload tokenizer
910bea4
verified
|
{ |
|
"(": 258, |
|
")": 312, |
|
".": 223, |
|
"1": 78, |
|
"??": 215, |
|
"N": 68, |
|
"S": 418, |
|
"X": 224, |
|
"[PAD]": 446, |
|
"[UNK]": 447, |
|
"a": 398, |
|
"a.": 130, |
|
"a.ː": 58, |
|
"a1": 410, |
|
"a2": 276, |
|
"a4": 108, |
|
"a5": 290, |
|
"ai": 424, |
|
"ai2": 38, |
|
"ai5": 99, |
|
"aiɜ": 34, |
|
"ai̯": 21, |
|
"au": 160, |
|
"au̯": 107, |
|
"aɜ": 263, |
|
"aɨ": 53, |
|
"aɪ": 193, |
|
"aɪə": 127, |
|
"aɪɚ": 164, |
|
"aʊ": 138, |
|
"aː": 291, |
|
"ã": 109, |
|
"b": 423, |
|
"bʰ": 387, |
|
"bʲ": 139, |
|
"bː": 73, |
|
"c": 144, |
|
"cʰ": 29, |
|
"cʰcʰ": 232, |
|
"cː": 191, |
|
"d": 100, |
|
"dZ": 64, |
|
"d[": 401, |
|
"d^": 419, |
|
"dzː": 279, |
|
"dʑ": 50, |
|
"dʑʲ": 308, |
|
"dʒ": 231, |
|
"dʒʲ": 31, |
|
"dʒː": 351, |
|
"dʰ": 198, |
|
"dʰː": 26, |
|
"dʲ": 397, |
|
"dʲʲ": 318, |
|
"dː": 345, |
|
"dˤ": 118, |
|
"dˤdˤ": 353, |
|
"e": 121, |
|
"e:": 195, |
|
"ee": 416, |
|
"ei2": 45, |
|
"ei5": 157, |
|
"eiɜ": 329, |
|
"ei̯": 145, |
|
"eɑ": 19, |
|
"eə": 87, |
|
"eɪ": 161, |
|
"eʊ": 116, |
|
"eː": 153, |
|
"ẽ": 11, |
|
"ẽː": 255, |
|
"e̞": 310, |
|
"e̞e̞": 430, |
|
"f": 311, |
|
"fʲ": 281, |
|
"g": 377, |
|
"h": 365, |
|
"i": 40, |
|
"i.": 217, |
|
"i.1": 293, |
|
"i.2": 368, |
|
"i.4": 36, |
|
"i.5": 57, |
|
"i.ɜ": 167, |
|
"i.ː": 203, |
|
"i1": 200, |
|
"i2": 388, |
|
"i4": 305, |
|
"i5": 331, |
|
"i:": 342, |
|
"ie": 380, |
|
"iou1": 247, |
|
"iou2": 63, |
|
"iou4": 174, |
|
"iou5": 444, |
|
"iouɜ": 128, |
|
"iɑ1": 74, |
|
"iɑ2": 151, |
|
"iɑ5": 438, |
|
"iɑɜ": 6, |
|
"iə": 229, |
|
"iɛ1": 71, |
|
"iɛ2": 0, |
|
"iɛ4": 124, |
|
"iɛ5": 163, |
|
"iɛɜ": 192, |
|
"iɜ": 352, |
|
"iʊ": 141, |
|
"iː": 372, |
|
"iː1": 102, |
|
"iːː": 233, |
|
"ĩ": 296, |
|
"i̪1": 18, |
|
"i̪2": 55, |
|
"i̪4": 356, |
|
"i̪5": 52, |
|
"i̪ɜ": 27, |
|
"j": 284, |
|
"ja": 283, |
|
"ju": 350, |
|
"k": 105, |
|
"kh": 69, |
|
"kʰ": 431, |
|
"kʰː": 386, |
|
"kʲ": 196, |
|
"kː": 65, |
|
"l": 43, |
|
"lː": 324, |
|
"l̩": 439, |
|
"m": 204, |
|
"mʲ": 7, |
|
"n": 366, |
|
"nʲ": 422, |
|
"nʲʲ": 288, |
|
"n̩": 302, |
|
"o": 333, |
|
"o1": 44, |
|
"o2": 314, |
|
"o4": 37, |
|
"o5": 93, |
|
"o:": 374, |
|
"oe": 3, |
|
"oe:": 269, |
|
"onɡ2": 208, |
|
"onɡ5": 17, |
|
"onɡɜ": 413, |
|
"ou1": 201, |
|
"ou2": 389, |
|
"ou5": 175, |
|
"ouɜ": 391, |
|
"ou̯": 414, |
|
"oɜ": 12, |
|
"oɪ": 62, |
|
"oʊ": 301, |
|
"oː": 274, |
|
"oːɹ": 134, |
|
"õ": 115, |
|
"o̞": 30, |
|
"o̞o̞": 170, |
|
"p": 307, |
|
"pf": 180, |
|
"ph": 47, |
|
"pʰ": 137, |
|
"pʲ": 349, |
|
"pː": 177, |
|
"q": 76, |
|
"qː": 404, |
|
"r": 393, |
|
"r.": 286, |
|
"rʲ": 101, |
|
"r̝": 230, |
|
"r̝̊": 250, |
|
"r̩": 417, |
|
"s": 427, |
|
"s.": 5, |
|
"s^": 158, |
|
"sx": 243, |
|
"sʲ": 32, |
|
"s̪": 42, |
|
"s̪ː": 209, |
|
"t": 54, |
|
"tS": 339, |
|
"t[": 212, |
|
"t^": 261, |
|
"t^ː": 306, |
|
"th": 15, |
|
"ts": 267, |
|
"ts.": 442, |
|
"ts.h": 23, |
|
"tsh": 252, |
|
"tsʰ": 260, |
|
"tsʲ": 110, |
|
"tsː": 411, |
|
"tɕ": 22, |
|
"tɕh": 70, |
|
"tɕʰ": 190, |
|
"tɕʲ": 218, |
|
"tʃ": 48, |
|
"tʃʰ": 104, |
|
"tʃʲ": 228, |
|
"tʃː": 113, |
|
"tʰ": 268, |
|
"tʲ": 89, |
|
"tː": 211, |
|
"t̪": 90, |
|
"t̪ː": 186, |
|
"u": 297, |
|
"u\"": 443, |
|
"u.": 257, |
|
"u.ː": 435, |
|
"u1": 303, |
|
"u2": 135, |
|
"u4": 61, |
|
"u5": 321, |
|
"u:": 188, |
|
"ua1": 20, |
|
"ua2": 162, |
|
"ua4": 168, |
|
"ua5": 379, |
|
"uai5": 384, |
|
"uaiɜ": 396, |
|
"uaɜ": 189, |
|
"uei2": 207, |
|
"uei5": 434, |
|
"ueiɜ": 147, |
|
"ui": 335, |
|
"uo": 94, |
|
"uo1": 344, |
|
"uo2": 373, |
|
"uo5": 95, |
|
"uoɜ": 304, |
|
"uə2": 369, |
|
"uə5": 315, |
|
"uəɜ": 202, |
|
"uɜ": 226, |
|
"uɨ": 341, |
|
"uɪ": 111, |
|
"uː": 330, |
|
"ũ": 287, |
|
"v": 85, |
|
"vʲ": 285, |
|
"w": 363, |
|
"x": 112, |
|
"xʲ": 159, |
|
"y": 441, |
|
"y1": 355, |
|
"y2": 238, |
|
"y5": 408, |
|
"y:": 9, |
|
"yi": 86, |
|
"yiɜ": 400, |
|
"yu2": 385, |
|
"yu5": 420, |
|
"yuɜ": 272, |
|
"yæ2": 96, |
|
"yæ5": 336, |
|
"yæɜ": 357, |
|
"yə2": 155, |
|
"yə5": 406, |
|
"yəɜ": 183, |
|
"yɛ2": 294, |
|
"yɛ5": 84, |
|
"yɛ5ʲ": 187, |
|
"yɛɜ": 328, |
|
"yɜ": 119, |
|
"yː": 24, |
|
"z": 248, |
|
"|": 445, |
|
"ä": 80, |
|
"ää": 371, |
|
"æ": 97, |
|
"æi": 214, |
|
"æiː": 1, |
|
"æː": 264, |
|
"ç": 359, |
|
"ð": 106, |
|
"ø": 313, |
|
"øi": 123, |
|
"øː": 317, |
|
"ħ": 221, |
|
"ĩ": 334, |
|
"ŋ": 205, |
|
"œ": 227, |
|
"œː": 235, |
|
"œ̃": 129, |
|
"ũ": 166, |
|
"ɐ": 91, |
|
"ɐɐ": 240, |
|
"ɐ̃": 171, |
|
"ɐ̃ʊ̃": 354, |
|
"ɑ": 325, |
|
"ɑ1": 251, |
|
"ɑ2": 142, |
|
"ɑ4": 10, |
|
"ɑ5": 432, |
|
"ɑ:": 256, |
|
"ɑu2": 244, |
|
"ɑu5": 126, |
|
"ɑuɜ": 242, |
|
"ɑɜ": 271, |
|
"ɑɨ": 320, |
|
"ɑː": 46, |
|
"ɑːɹ": 254, |
|
"ɑ̃": 289, |
|
"ɒ": 92, |
|
"ɔ": 362, |
|
"ɔø": 265, |
|
"ɔɨ": 327, |
|
"ɔɪ": 13, |
|
"ɔː": 169, |
|
"ɔːɹ": 409, |
|
"ɔ̃": 253, |
|
"ɕ": 56, |
|
"ɕʲ": 35, |
|
"ɖ": 219, |
|
"ɖʰ": 41, |
|
"ɗ": 148, |
|
"ɘ": 154, |
|
"ə": 194, |
|
"ə1": 149, |
|
"ə2": 436, |
|
"ə4": 309, |
|
"ə5": 425, |
|
"əl": 197, |
|
"ər1": 322, |
|
"ər2": 399, |
|
"ər4": 82, |
|
"ər5": 299, |
|
"ərɜ": 262, |
|
"əɜ": 241, |
|
"əɨ": 298, |
|
"əɪ": 4, |
|
"əʊ": 273, |
|
"əː1": 181, |
|
"ɚ": 437, |
|
"ɛ": 326, |
|
"ɛɪ": 383, |
|
"ɛɹ": 67, |
|
"ɛʊ": 220, |
|
"ɛː": 245, |
|
"ɛ̃": 59, |
|
"ɜ": 440, |
|
"ɜː": 405, |
|
"ɞ": 122, |
|
"ɟ": 222, |
|
"ɟʰ": 156, |
|
"ɟː": 184, |
|
"ɡ": 150, |
|
"ɡʰ": 60, |
|
"ɡʲ": 282, |
|
"ɡː": 75, |
|
"ɢ": 39, |
|
"ɣ": 407, |
|
"ɤ": 83, |
|
"ɥ": 25, |
|
"ɦ": 316, |
|
"ɨ": 402, |
|
"ɨu": 343, |
|
"ɨː": 358, |
|
"ɪ": 375, |
|
"ɪ^": 210, |
|
"ɪu": 120, |
|
"ɪuː": 370, |
|
"ɪɹ": 275, |
|
"ɪː": 51, |
|
"ɫ": 340, |
|
"ɬ": 346, |
|
"ɭ": 178, |
|
"ɭʲ": 131, |
|
"ɮ": 117, |
|
"ɯ": 2, |
|
"ɯɯ": 381, |
|
"ɯᵝ": 146, |
|
"ɯᵝɯᵝ": 103, |
|
"ɰ": 185, |
|
"ɱ": 332, |
|
"ɲ": 433, |
|
"ɳ": 125, |
|
"ɴ": 292, |
|
"ɵ": 72, |
|
"ɵː": 179, |
|
"ɶ": 270, |
|
"ɸ": 376, |
|
"ɹ": 133, |
|
"ɹ̩": 79, |
|
"ɻ": 266, |
|
"ɻ̩": 249, |
|
"ɽ": 390, |
|
"ɾ": 225, |
|
"ʀ": 33, |
|
"ʁ": 367, |
|
"ʂ": 395, |
|
"ʂʲ": 277, |
|
"ʃ": 8, |
|
"ʈ": 239, |
|
"ʈʂ": 426, |
|
"ʈʂʰ": 382, |
|
"ʈʰ": 347, |
|
"ʉ": 173, |
|
"ʊ": 364, |
|
"ʊə": 338, |
|
"ʊɹ": 199, |
|
"ʊː": 236, |
|
"ʋ": 246, |
|
"ʌ": 415, |
|
"ʎ": 77, |
|
"ʏ": 14, |
|
"ʐ": 323, |
|
"ʑ": 176, |
|
"ʒ": 172, |
|
"ʒʲ": 66, |
|
"ʔ": 237, |
|
"ʕ": 429, |
|
"ʙ": 259, |
|
"ʝ": 206, |
|
"ʟ": 49, |
|
"ʡ": 394, |
|
"ʰ": 28, |
|
"ʲ": 81, |
|
"ʷ": 421, |
|
"ː": 428, |
|
"ˠ": 98, |
|
"ˤ": 337, |
|
"̃": 348, |
|
"̈": 88, |
|
"̊": 16, |
|
"̘": 392, |
|
"̙": 182, |
|
"̜": 165, |
|
"̝": 403, |
|
"̞": 234, |
|
"̟": 152, |
|
"̠": 412, |
|
"̤": 136, |
|
"̥": 216, |
|
"̩": 213, |
|
"̬": 360, |
|
"̯": 280, |
|
"̰": 295, |
|
"̹": 361, |
|
"̼": 132, |
|
"̽": 114, |
|
"β": 378, |
|
"θ": 319, |
|
"χ": 143, |
|
"ᵝ": 300, |
|
"ᵻ": 140, |
|
"ⱱ": 278 |
|
} |
|
|