arunasrivastava
tokenizer
3818acc
|
{ |
|
"A": 267, |
|
"E": 45, |
|
"H": 72, |
|
"I": 20, |
|
"O": 305, |
|
"U": 292, |
|
"[PAD]": 310, |
|
"[UNK]": 309, |
|
"_": 182, |
|
"a": 53, |
|
"ã": 125, |
|
"b": 113, |
|
"b̪": 177, |
|
"b̪͡v": 289, |
|
"b͡ꞵ": 287, |
|
"c": 25, |
|
"cʼ": 229, |
|
"c͡ç": 66, |
|
"d": 176, |
|
"d̼": 118, |
|
"d͡z": 263, |
|
"d͡ð": 244, |
|
"d͡ɮ": 18, |
|
"d͡ʑ": 94, |
|
"d͡ʒ": 280, |
|
"e": 175, |
|
"ẽ": 211, |
|
"e̞": 114, |
|
"ẽ̞": 265, |
|
"f": 139, |
|
"fʼ": 249, |
|
"h": 179, |
|
"i": 245, |
|
"j": 215, |
|
"k": 282, |
|
"kxʼ": 281, |
|
"kǀ": 41, |
|
"kǁ": 61, |
|
"kǂ": 21, |
|
"kǃ": 70, |
|
"kʘ": 79, |
|
"kʼ": 39, |
|
"k̚": 89, |
|
"k͡p": 48, |
|
"k͡x": 198, |
|
"l": 303, |
|
"m": 75, |
|
"m̥": 172, |
|
"n": 102, |
|
"n̥": 28, |
|
"n̼": 169, |
|
"o": 117, |
|
"õ": 119, |
|
"o̞": 62, |
|
"õ̞": 234, |
|
"p": 259, |
|
"pʼ": 286, |
|
"p̚": 149, |
|
"p̪": 273, |
|
"p̪͡f": 105, |
|
"p͡f": 225, |
|
"p͡ɸ": 103, |
|
"q": 130, |
|
"qǀ": 302, |
|
"qǁ": 126, |
|
"qǂ": 299, |
|
"qǃ": 37, |
|
"qʘ": 261, |
|
"qʼ": 58, |
|
"q͡ʡ": 127, |
|
"q͡χʼ": 291, |
|
"q͡ꭓ": 4, |
|
"r": 82, |
|
"r̥": 34, |
|
"s": 247, |
|
"sʼ": 200, |
|
"t": 307, |
|
"tʼ": 183, |
|
"t̚": 241, |
|
"t̪͡θʼ": 216, |
|
"t̼": 87, |
|
"t͡s": 156, |
|
"t͡sʼ": 43, |
|
"t͡ɕ": 264, |
|
"t͡ɬ": 170, |
|
"t͡ɬʼ": 164, |
|
"t͡ʃ": 91, |
|
"t͡ʃʼ": 108, |
|
"t͡θ": 140, |
|
"u": 154, |
|
"ũ": 81, |
|
"v": 243, |
|
"w": 143, |
|
"x": 133, |
|
"xʼ": 129, |
|
"y": 214, |
|
"ỹ": 277, |
|
"z": 271, |
|
"{": 251, |
|
"}": 74, |
|
"ã": 99, |
|
"ä": 165, |
|
"ä̃": 115, |
|
"æ": 191, |
|
"æ̃": 217, |
|
"ç": 71, |
|
"ð": 69, |
|
"ð̠": 192, |
|
"ð̼": 9, |
|
"õ": 157, |
|
"ø": 47, |
|
"ø̃": 46, |
|
"ø̞": 112, |
|
"ø̞̃": 12, |
|
"ħ": 224, |
|
"ĩ": 180, |
|
"ŋ": 213, |
|
"ŋǀ": 231, |
|
"ŋǁ": 304, |
|
"ŋǂ": 301, |
|
"ŋǃ": 284, |
|
"ŋʘ": 168, |
|
"ŋ̊": 27, |
|
"ŋ͡m": 296, |
|
"œ": 29, |
|
"œ̃": 153, |
|
"ũ": 31, |
|
"ɐ": 142, |
|
"ɐ̃": 7, |
|
"ɑ": 49, |
|
"ɑ̃": 50, |
|
"ɒ": 116, |
|
"ɒ̃": 85, |
|
"ɓ": 178, |
|
"ɓ̥": 13, |
|
"ɔ": 228, |
|
"ɔ̃": 186, |
|
"ɕ": 220, |
|
"ɕʼ": 36, |
|
"ɖ": 256, |
|
"ɖ͡ʐ": 77, |
|
"ɗ": 93, |
|
"ɗ̥": 270, |
|
"ɘ": 104, |
|
"ɘ̃": 189, |
|
"ə": 6, |
|
"ə̃": 294, |
|
"ɚ": 184, |
|
"ɛ": 293, |
|
"ɛ̃": 98, |
|
"ɜ": 92, |
|
"ɜ̃": 73, |
|
"ɝ": 196, |
|
"ɞ": 210, |
|
"ɞ̃": 54, |
|
"ɟ": 68, |
|
"ɟ͡ʝ": 86, |
|
"ɠ": 160, |
|
"ɠ̊": 1, |
|
"ɡ": 252, |
|
"ɡǀ": 19, |
|
"ɡǁ": 226, |
|
"ɡǂ": 131, |
|
"ɡǃ": 152, |
|
"ɡʘ": 162, |
|
"ɡ̆": 201, |
|
"ɡ͡b": 185, |
|
"ɡ͡ɣ": 78, |
|
"ɢ": 195, |
|
"ɢǀ": 88, |
|
"ɢǁ": 258, |
|
"ɢǂ": 64, |
|
"ɢǃ": 308, |
|
"ɢʘ": 107, |
|
"ɢ̆": 123, |
|
"ɢ͡ʁ": 111, |
|
"ɣ": 219, |
|
"ɤ": 194, |
|
"ɤ̃": 17, |
|
"ɤ̞": 187, |
|
"ɤ̞̃": 60, |
|
"ɥ": 24, |
|
"ɥ̊": 135, |
|
"ɧ": 246, |
|
"ɨ": 40, |
|
"ɨ̃": 109, |
|
"ɪ": 8, |
|
"ɪ̃": 97, |
|
"ɬ": 121, |
|
"ɬʼ": 3, |
|
"ɭ": 290, |
|
"ɭ˔": 279, |
|
"ɭ̆": 236, |
|
"ɭ̥̆": 240, |
|
"ɮ": 266, |
|
"ɯ": 275, |
|
"ɯ̃": 300, |
|
"ɰ": 208, |
|
"ɱ": 295, |
|
"ɲ": 128, |
|
"ɲ̊": 197, |
|
"ɳ": 63, |
|
"ɳ̊": 144, |
|
"ɴ": 136, |
|
"ɴǀ": 101, |
|
"ɴǁ": 14, |
|
"ɴǂ": 238, |
|
"ɴǃ": 147, |
|
"ɴʘ": 221, |
|
"ɵ": 95, |
|
"ɵ̃": 51, |
|
"ɶ": 145, |
|
"ɶ̃": 146, |
|
"ɸ": 166, |
|
"ɸʼ": 306, |
|
"ɹ": 223, |
|
"ɹ̠˔": 202, |
|
"ɹ̠̊˔": 173, |
|
"ɺ": 76, |
|
"ɺ̥": 181, |
|
"ɻ": 163, |
|
"ɻ˔": 30, |
|
"ɻ̊˔": 42, |
|
"ɽ": 254, |
|
"ɽ̊": 218, |
|
"ɾ": 232, |
|
"ɾ̥": 120, |
|
"ɾ̼": 32, |
|
"ʀ": 52, |
|
"ʀ̥": 148, |
|
"ʁ": 239, |
|
"ʂ": 242, |
|
"ʂʼ": 110, |
|
"ʃ": 253, |
|
"ʃʼ": 230, |
|
"ʄ": 132, |
|
"ʄ̊": 155, |
|
"ʈ": 199, |
|
"ʈʼ": 44, |
|
"ʈ͡ʂ": 190, |
|
"ʈ͡ʂʼ": 67, |
|
"ʉ": 80, |
|
"ʉ̃": 250, |
|
"ʊ": 83, |
|
"ʊ̃": 205, |
|
"ʋ": 106, |
|
"ʌ": 272, |
|
"ʌ̃": 158, |
|
"ʍ": 141, |
|
"ʎ": 276, |
|
"ʎ̆": 84, |
|
"ʎ̝": 262, |
|
"ʎ̝̊": 59, |
|
"ʏ": 23, |
|
"ʏ̃": 237, |
|
"ʐ": 209, |
|
"ʑ": 137, |
|
"ʒ": 171, |
|
"ʔ": 10, |
|
"ʔ̞": 257, |
|
"ʔ͡h": 203, |
|
"ʕ": 38, |
|
"ʙ": 274, |
|
"ʙ̥": 167, |
|
"ʛ": 233, |
|
"ʛ̥": 159, |
|
"ʜ": 298, |
|
"ʝ": 35, |
|
"ʟ": 150, |
|
"ʟ̆": 248, |
|
"ʟ̝": 33, |
|
"ʟ̝̊": 161, |
|
"ʟ̠": 285, |
|
"ʡ": 174, |
|
"ʡʼ": 5, |
|
"ʡ̆": 22, |
|
"ʡ͡ʜ": 56, |
|
"ʡ͡ʢ": 255, |
|
"ʢ": 188, |
|
"ʰ": 206, |
|
"ʲ": 0, |
|
"ʷ": 288, |
|
"ː": 235, |
|
"˞": 90, |
|
"ˠ": 122, |
|
"ˡ": 16, |
|
"ˣ": 96, |
|
"ˤ": 15, |
|
"̃": 57, |
|
"̩": 204, |
|
"β": 269, |
|
"θ": 283, |
|
"θʼ": 26, |
|
"θ̠": 100, |
|
"θ̼": 227, |
|
"χ": 65, |
|
"χʼ": 260, |
|
"ᵐ": 124, |
|
"ᵑ": 297, |
|
"ᶑ": 212, |
|
"ᶑ̊": 268, |
|
"ᶬ": 151, |
|
"ᶮ": 55, |
|
"ᶯ": 207, |
|
"ᶰ": 11, |
|
"ᶿ": 138, |
|
"ẽ": 2, |
|
"ⁿ": 222, |
|
"ⱱ": 134, |
|
"ⱱ̟": 193, |
|
"ꞎ": 278 |
|
} |
|
|