Upload tokenizer
Browse files- added_tokens.json +288 -0
- merges.txt +0 -0
- special_tokens_map.json +219 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2493 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|af|>": 50591,
|
| 3 |
+
"<|am|>": 50598,
|
| 4 |
+
"<|ar|>": 50536,
|
| 5 |
+
"<|as|>": 50614,
|
| 6 |
+
"<|az|>": 50568,
|
| 7 |
+
"<|ba|>": 50619,
|
| 8 |
+
"<|be|>": 50594,
|
| 9 |
+
"<|bg|>": 50556,
|
| 10 |
+
"<|bn|>": 50566,
|
| 11 |
+
"<|bo|>": 50611,
|
| 12 |
+
"<|br|>": 50573,
|
| 13 |
+
"<|bs|>": 50579,
|
| 14 |
+
"<|ca|>": 50534,
|
| 15 |
+
"<|cs|>": 50547,
|
| 16 |
+
"<|cy|>": 50561,
|
| 17 |
+
"<|da|>": 50549,
|
| 18 |
+
"<|de|>": 50525,
|
| 19 |
+
"<|el|>": 50545,
|
| 20 |
+
"<|endoftext|>": 50628,
|
| 21 |
+
"<|en|>": 50523,
|
| 22 |
+
"<|es|>": 50526,
|
| 23 |
+
"<|et|>": 50571,
|
| 24 |
+
"<|eu|>": 50574,
|
| 25 |
+
"<|fa|>": 50564,
|
| 26 |
+
"<|fi|>": 50541,
|
| 27 |
+
"<|fo|>": 50602,
|
| 28 |
+
"<|fr|>": 50529,
|
| 29 |
+
"<|gl|>": 50583,
|
| 30 |
+
"<|gu|>": 50597,
|
| 31 |
+
"<|haw|>": 50616,
|
| 32 |
+
"<|ha|>": 50618,
|
| 33 |
+
"<|he|>": 50543,
|
| 34 |
+
"<|hi|>": 50540,
|
| 35 |
+
"<|hr|>": 50555,
|
| 36 |
+
"<|ht|>": 50603,
|
| 37 |
+
"<|hu|>": 50550,
|
| 38 |
+
"<|hy|>": 50576,
|
| 39 |
+
"<|id|>": 50539,
|
| 40 |
+
"<|is|>": 50575,
|
| 41 |
+
"<|it|>": 50538,
|
| 42 |
+
"<|ja|>": 50530,
|
| 43 |
+
"<|jw|>": 50620,
|
| 44 |
+
"<|ka|>": 50593,
|
| 45 |
+
"<|kk|>": 50580,
|
| 46 |
+
"<|km|>": 50587,
|
| 47 |
+
"<|kn|>": 50570,
|
| 48 |
+
"<|ko|>": 50528,
|
| 49 |
+
"<|la|>": 50558,
|
| 50 |
+
"<|lb|>": 50609,
|
| 51 |
+
"<|ln|>": 50617,
|
| 52 |
+
"<|lo|>": 50600,
|
| 53 |
+
"<|lt|>": 50557,
|
| 54 |
+
"<|lv|>": 50565,
|
| 55 |
+
"<|mg|>": 50613,
|
| 56 |
+
"<|mi|>": 50559,
|
| 57 |
+
"<|mk|>": 50572,
|
| 58 |
+
"<|ml|>": 50560,
|
| 59 |
+
"<|mn|>": 50578,
|
| 60 |
+
"<|mr|>": 50584,
|
| 61 |
+
"<|ms|>": 50546,
|
| 62 |
+
"<|mt|>": 50607,
|
| 63 |
+
"<|my|>": 50610,
|
| 64 |
+
"<|ne|>": 50577,
|
| 65 |
+
"<|nl|>": 50535,
|
| 66 |
+
"<|nn|>": 50606,
|
| 67 |
+
"<|nocaptions|>": 50626,
|
| 68 |
+
"<|notimestamps|>": 50627,
|
| 69 |
+
"<|no|>": 50552,
|
| 70 |
+
"<|oc|>": 50592,
|
| 71 |
+
"<|pa|>": 50585,
|
| 72 |
+
"<|pl|>": 50533,
|
| 73 |
+
"<|ps|>": 50604,
|
| 74 |
+
"<|pt|>": 50531,
|
| 75 |
+
"<|ro|>": 50548,
|
| 76 |
+
"<|ru|>": 50527,
|
| 77 |
+
"<|sa|>": 50608,
|
| 78 |
+
"<|sd|>": 50596,
|
| 79 |
+
"<|si|>": 50586,
|
| 80 |
+
"<|sk|>": 50562,
|
| 81 |
+
"<|sl|>": 50569,
|
| 82 |
+
"<|sn|>": 50588,
|
| 83 |
+
"<|so|>": 50590,
|
| 84 |
+
"<|sq|>": 50581,
|
| 85 |
+
"<|sr|>": 50567,
|
| 86 |
+
"<|startoflm|>": 50624,
|
| 87 |
+
"<|startofprev|>": 50625,
|
| 88 |
+
"<|startoftranscript|>": 50522,
|
| 89 |
+
"<|su|>": 50621,
|
| 90 |
+
"<|sv|>": 50537,
|
| 91 |
+
"<|sw|>": 50582,
|
| 92 |
+
"<|ta|>": 50551,
|
| 93 |
+
"<|te|>": 50563,
|
| 94 |
+
"<|tg|>": 50595,
|
| 95 |
+
"<|th|>": 50553,
|
| 96 |
+
"<|tk|>": 50605,
|
| 97 |
+
"<|tl|>": 50612,
|
| 98 |
+
"<|transcribe|>": 50623,
|
| 99 |
+
"<|translate|>": 50622,
|
| 100 |
+
"<|tr|>": 50532,
|
| 101 |
+
"<|tt|>": 50615,
|
| 102 |
+
"<|uk|>": 50544,
|
| 103 |
+
"<|ur|>": 50554,
|
| 104 |
+
"<|uz|>": 50601,
|
| 105 |
+
"<|vi|>": 50542,
|
| 106 |
+
"<|yi|>": 50599,
|
| 107 |
+
"<|yo|>": 50589,
|
| 108 |
+
"<|zh|>": 50524,
|
| 109 |
+
"<|¡|>": 50629,
|
| 110 |
+
"<|¢|>": 50630,
|
| 111 |
+
"<|£|>": 50631,
|
| 112 |
+
"<|¤|>": 50632,
|
| 113 |
+
"<|¥|>": 50633,
|
| 114 |
+
"<|¦|>": 50634,
|
| 115 |
+
"<|§|>": 50635,
|
| 116 |
+
"<|¨|>": 50636,
|
| 117 |
+
"<|©|>": 50637,
|
| 118 |
+
"<|ª|>": 50638,
|
| 119 |
+
"<|«|>": 50639,
|
| 120 |
+
"<|¬|>": 50640,
|
| 121 |
+
"<|®|>": 50641,
|
| 122 |
+
"<|¯|>": 50642,
|
| 123 |
+
"<|°|>": 50643,
|
| 124 |
+
"<|±|>": 50644,
|
| 125 |
+
"<|²|>": 50645,
|
| 126 |
+
"<|³|>": 50646,
|
| 127 |
+
"<|´|>": 50647,
|
| 128 |
+
"<|µ|>": 50648,
|
| 129 |
+
"<|¶|>": 50649,
|
| 130 |
+
"<|·|>": 50650,
|
| 131 |
+
"<|¸|>": 50651,
|
| 132 |
+
"<|¹|>": 50652,
|
| 133 |
+
"<|º|>": 50653,
|
| 134 |
+
"<|»|>": 50654,
|
| 135 |
+
"<|¼|>": 50655,
|
| 136 |
+
"<|½|>": 50656,
|
| 137 |
+
"<|¾|>": 50657,
|
| 138 |
+
"<|¿|>": 50658,
|
| 139 |
+
"<|À|>": 50659,
|
| 140 |
+
"<|Á|>": 50660,
|
| 141 |
+
"<|Â|>": 50661,
|
| 142 |
+
"<|Ã|>": 50662,
|
| 143 |
+
"<|Ä|>": 50663,
|
| 144 |
+
"<|Å|>": 50664,
|
| 145 |
+
"<|Æ|>": 50665,
|
| 146 |
+
"<|Ç|>": 50666,
|
| 147 |
+
"<|È|>": 50667,
|
| 148 |
+
"<|É|>": 50668,
|
| 149 |
+
"<|Ê|>": 50669,
|
| 150 |
+
"<|Ë|>": 50670,
|
| 151 |
+
"<|Ì|>": 50671,
|
| 152 |
+
"<|Í|>": 50672,
|
| 153 |
+
"<|Î|>": 50673,
|
| 154 |
+
"<|Ï|>": 50674,
|
| 155 |
+
"<|Ð|>": 50675,
|
| 156 |
+
"<|Ñ|>": 50676,
|
| 157 |
+
"<|Ò|>": 50677,
|
| 158 |
+
"<|Ó|>": 50678,
|
| 159 |
+
"<|Ô|>": 50679,
|
| 160 |
+
"<|Õ|>": 50680,
|
| 161 |
+
"<|Ö|>": 50681,
|
| 162 |
+
"<|×|>": 50682,
|
| 163 |
+
"<|Ø|>": 50683,
|
| 164 |
+
"<|ا|>": 50793,
|
| 165 |
+
"<|اÙĨ|>": 50801,
|
| 166 |
+
"<|ت|>": 50800,
|
| 167 |
+
"<|د|>": 50803,
|
| 168 |
+
"<|ر|>": 50797,
|
| 169 |
+
"<|س|>": 50807,
|
| 170 |
+
"<|Ù|>": 50684,
|
| 171 |
+
"<|Ùħ|>": 50804,
|
| 172 |
+
"<|ÙĨ|>": 50796,
|
| 173 |
+
"<|ÙĪ|>": 50795,
|
| 174 |
+
"<|Ú|>": 50685,
|
| 175 |
+
"<|Ú©|>": 50798,
|
| 176 |
+
"<|Û|>": 50686,
|
| 177 |
+
"<|ÛĨ|>": 50806,
|
| 178 |
+
"<|ÛĮ|>": 50792,
|
| 179 |
+
"<|Ûİ|>": 50802,
|
| 180 |
+
"<|Ûķ|>": 50791,
|
| 181 |
+
"<|Ü|>": 50687,
|
| 182 |
+
"<|Ý|>": 50688,
|
| 183 |
+
"<|Þ|>": 50689,
|
| 184 |
+
"<|ß|>": 50690,
|
| 185 |
+
"<|à|>": 50691,
|
| 186 |
+
"<|á|>": 50692,
|
| 187 |
+
"<|â|>": 50693,
|
| 188 |
+
"<|ã|>": 50694,
|
| 189 |
+
"<|ä|>": 50695,
|
| 190 |
+
"<|å|>": 50696,
|
| 191 |
+
"<|æ|>": 50697,
|
| 192 |
+
"<|ç|>": 50698,
|
| 193 |
+
"<|è|>": 50699,
|
| 194 |
+
"<|é|>": 50700,
|
| 195 |
+
"<|ê|>": 50701,
|
| 196 |
+
"<|ë|>": 50702,
|
| 197 |
+
"<|ì|>": 50703,
|
| 198 |
+
"<|í|>": 50704,
|
| 199 |
+
"<|î|>": 50705,
|
| 200 |
+
"<|ï|>": 50706,
|
| 201 |
+
"<|ð|>": 50707,
|
| 202 |
+
"<|ñ|>": 50708,
|
| 203 |
+
"<|ò|>": 50709,
|
| 204 |
+
"<|ó|>": 50710,
|
| 205 |
+
"<|ô|>": 50711,
|
| 206 |
+
"<|õ|>": 50712,
|
| 207 |
+
"<|ö|>": 50713,
|
| 208 |
+
"<|÷|>": 50714,
|
| 209 |
+
"<|ø|>": 50715,
|
| 210 |
+
"<|ù|>": 50716,
|
| 211 |
+
"<|ú|>": 50717,
|
| 212 |
+
"<|û|>": 50718,
|
| 213 |
+
"<|ü|>": 50719,
|
| 214 |
+
"<|ý|>": 50720,
|
| 215 |
+
"<|þ|>": 50721,
|
| 216 |
+
"<|ÿ|>": 50722,
|
| 217 |
+
"<|Ā|>": 50723,
|
| 218 |
+
"<|ā|>": 50724,
|
| 219 |
+
"<|Ă|>": 50725,
|
| 220 |
+
"<|ă|>": 50726,
|
| 221 |
+
"<|Ą|>": 50727,
|
| 222 |
+
"<|ą|>": 50728,
|
| 223 |
+
"<|Ć|>": 50729,
|
| 224 |
+
"<|ć|>": 50730,
|
| 225 |
+
"<|Ĉ|>": 50731,
|
| 226 |
+
"<|ĉ|>": 50732,
|
| 227 |
+
"<|Ċ|>": 50733,
|
| 228 |
+
"<|ċ|>": 50734,
|
| 229 |
+
"<|Č|>": 50735,
|
| 230 |
+
"<|č|>": 50736,
|
| 231 |
+
"<|Ď|>": 50737,
|
| 232 |
+
"<|ď|>": 50738,
|
| 233 |
+
"<|Đ|>": 50739,
|
| 234 |
+
"<|đ|>": 50740,
|
| 235 |
+
"<|Ē|>": 50741,
|
| 236 |
+
"<|ē|>": 50742,
|
| 237 |
+
"<|Ĕ|>": 50743,
|
| 238 |
+
"<|ĕ|>": 50744,
|
| 239 |
+
"<|Ė|>": 50745,
|
| 240 |
+
"<|ė|>": 50746,
|
| 241 |
+
"<|Ę|>": 50747,
|
| 242 |
+
"<|ę|>": 50748,
|
| 243 |
+
"<|Ě|>": 50749,
|
| 244 |
+
"<|ě|>": 50750,
|
| 245 |
+
"<|Ĝ|>": 50751,
|
| 246 |
+
"<|ĝ|>": 50752,
|
| 247 |
+
"<|Ğ|>": 50753,
|
| 248 |
+
"<|ğ|>": 50754,
|
| 249 |
+
"<|Ġ|>": 50755,
|
| 250 |
+
"<|ĠØ|>": 50794,
|
| 251 |
+
"<|Ġب|>": 50805,
|
| 252 |
+
"<|ĠÙ|>": 50799,
|
| 253 |
+
"<|ġ|>": 50756,
|
| 254 |
+
"<|Ģ|>": 50757,
|
| 255 |
+
"<|ģ|>": 50758,
|
| 256 |
+
"<|Ĥ|>": 50759,
|
| 257 |
+
"<|ĥ|>": 50760,
|
| 258 |
+
"<|Ħ|>": 50761,
|
| 259 |
+
"<|ħ|>": 50762,
|
| 260 |
+
"<|Ĩ|>": 50763,
|
| 261 |
+
"<|ĩ|>": 50764,
|
| 262 |
+
"<|Ī|>": 50765,
|
| 263 |
+
"<|ī|>": 50766,
|
| 264 |
+
"<|Ĭ|>": 50767,
|
| 265 |
+
"<|ĭ|>": 50768,
|
| 266 |
+
"<|Į|>": 50769,
|
| 267 |
+
"<|į|>": 50770,
|
| 268 |
+
"<|İ|>": 50771,
|
| 269 |
+
"<|ı|>": 50772,
|
| 270 |
+
"<|IJ|>": 50773,
|
| 271 |
+
"<|ij|>": 50774,
|
| 272 |
+
"<|Ĵ|>": 50775,
|
| 273 |
+
"<|ĵ|>": 50776,
|
| 274 |
+
"<|Ķ|>": 50777,
|
| 275 |
+
"<|ķ|>": 50778,
|
| 276 |
+
"<|ĸ|>": 50779,
|
| 277 |
+
"<|Ĺ|>": 50780,
|
| 278 |
+
"<|ĺ|>": 50781,
|
| 279 |
+
"<|Ļ|>": 50782,
|
| 280 |
+
"<|ļ|>": 50783,
|
| 281 |
+
"<|Ľ|>": 50784,
|
| 282 |
+
"<|ľ|>": 50785,
|
| 283 |
+
"<|Ŀ|>": 50786,
|
| 284 |
+
"<|ŀ|>": 50787,
|
| 285 |
+
"<|Ł|>": 50788,
|
| 286 |
+
"<|ł|>": 50789,
|
| 287 |
+
"<|Ń|>": 50790
|
| 288 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|startoftranscript|>",
|
| 5 |
+
"<|¡|>",
|
| 6 |
+
"<|¢|>",
|
| 7 |
+
"<|£|>",
|
| 8 |
+
"<|¤|>",
|
| 9 |
+
"<|¥|>",
|
| 10 |
+
"<|¦|>",
|
| 11 |
+
"<|§|>",
|
| 12 |
+
"<|¨|>",
|
| 13 |
+
"<|©|>",
|
| 14 |
+
"<|ª|>",
|
| 15 |
+
"<|«|>",
|
| 16 |
+
"<|¬|>",
|
| 17 |
+
"<|®|>",
|
| 18 |
+
"<|¯|>",
|
| 19 |
+
"<|°|>",
|
| 20 |
+
"<|±|>",
|
| 21 |
+
"<|²|>",
|
| 22 |
+
"<|³|>",
|
| 23 |
+
"<|´|>",
|
| 24 |
+
"<|µ|>",
|
| 25 |
+
"<|¶|>",
|
| 26 |
+
"<|·|>",
|
| 27 |
+
"<|¸|>",
|
| 28 |
+
"<|¹|>",
|
| 29 |
+
"<|º|>",
|
| 30 |
+
"<|»|>",
|
| 31 |
+
"<|¼|>",
|
| 32 |
+
"<|½|>",
|
| 33 |
+
"<|¾|>",
|
| 34 |
+
"<|¿|>",
|
| 35 |
+
"<|À|>",
|
| 36 |
+
"<|Á|>",
|
| 37 |
+
"<|Â|>",
|
| 38 |
+
"<|Ã|>",
|
| 39 |
+
"<|Ä|>",
|
| 40 |
+
"<|Å|>",
|
| 41 |
+
"<|Æ|>",
|
| 42 |
+
"<|Ç|>",
|
| 43 |
+
"<|È|>",
|
| 44 |
+
"<|É|>",
|
| 45 |
+
"<|Ê|>",
|
| 46 |
+
"<|Ë|>",
|
| 47 |
+
"<|Ì|>",
|
| 48 |
+
"<|Í|>",
|
| 49 |
+
"<|Î|>",
|
| 50 |
+
"<|Ï|>",
|
| 51 |
+
"<|Ð|>",
|
| 52 |
+
"<|Ñ|>",
|
| 53 |
+
"<|Ò|>",
|
| 54 |
+
"<|Ó|>",
|
| 55 |
+
"<|Ô|>",
|
| 56 |
+
"<|Õ|>",
|
| 57 |
+
"<|Ö|>",
|
| 58 |
+
"<|×|>",
|
| 59 |
+
"<|Ø|>",
|
| 60 |
+
"<|Ù|>",
|
| 61 |
+
"<|Ú|>",
|
| 62 |
+
"<|Û|>",
|
| 63 |
+
"<|Ü|>",
|
| 64 |
+
"<|Ý|>",
|
| 65 |
+
"<|Þ|>",
|
| 66 |
+
"<|ß|>",
|
| 67 |
+
"<|à|>",
|
| 68 |
+
"<|á|>",
|
| 69 |
+
"<|â|>",
|
| 70 |
+
"<|ã|>",
|
| 71 |
+
"<|ä|>",
|
| 72 |
+
"<|å|>",
|
| 73 |
+
"<|æ|>",
|
| 74 |
+
"<|ç|>",
|
| 75 |
+
"<|è|>",
|
| 76 |
+
"<|é|>",
|
| 77 |
+
"<|ê|>",
|
| 78 |
+
"<|ë|>",
|
| 79 |
+
"<|ì|>",
|
| 80 |
+
"<|í|>",
|
| 81 |
+
"<|î|>",
|
| 82 |
+
"<|ï|>",
|
| 83 |
+
"<|ð|>",
|
| 84 |
+
"<|ñ|>",
|
| 85 |
+
"<|ò|>",
|
| 86 |
+
"<|ó|>",
|
| 87 |
+
"<|ô|>",
|
| 88 |
+
"<|õ|>",
|
| 89 |
+
"<|ö|>",
|
| 90 |
+
"<|÷|>",
|
| 91 |
+
"<|ø|>",
|
| 92 |
+
"<|ù|>",
|
| 93 |
+
"<|ú|>",
|
| 94 |
+
"<|û|>",
|
| 95 |
+
"<|ü|>",
|
| 96 |
+
"<|ý|>",
|
| 97 |
+
"<|þ|>",
|
| 98 |
+
"<|ÿ|>",
|
| 99 |
+
"<|Ā|>",
|
| 100 |
+
"<|ā|>",
|
| 101 |
+
"<|Ă|>",
|
| 102 |
+
"<|ă|>",
|
| 103 |
+
"<|Ą|>",
|
| 104 |
+
"<|ą|>",
|
| 105 |
+
"<|Ć|>",
|
| 106 |
+
"<|ć|>",
|
| 107 |
+
"<|Ĉ|>",
|
| 108 |
+
"<|ĉ|>",
|
| 109 |
+
"<|Ċ|>",
|
| 110 |
+
"<|ċ|>",
|
| 111 |
+
"<|Č|>",
|
| 112 |
+
"<|č|>",
|
| 113 |
+
"<|Ď|>",
|
| 114 |
+
"<|ď|>",
|
| 115 |
+
"<|Đ|>",
|
| 116 |
+
"<|đ|>",
|
| 117 |
+
"<|Ē|>",
|
| 118 |
+
"<|ē|>",
|
| 119 |
+
"<|Ĕ|>",
|
| 120 |
+
"<|ĕ|>",
|
| 121 |
+
"<|Ė|>",
|
| 122 |
+
"<|ė|>",
|
| 123 |
+
"<|Ę|>",
|
| 124 |
+
"<|ę|>",
|
| 125 |
+
"<|Ě|>",
|
| 126 |
+
"<|ě|>",
|
| 127 |
+
"<|Ĝ|>",
|
| 128 |
+
"<|ĝ|>",
|
| 129 |
+
"<|Ğ|>",
|
| 130 |
+
"<|ğ|>",
|
| 131 |
+
"<|Ġ|>",
|
| 132 |
+
"<|ġ|>",
|
| 133 |
+
"<|Ģ|>",
|
| 134 |
+
"<|ģ|>",
|
| 135 |
+
"<|Ĥ|>",
|
| 136 |
+
"<|ĥ|>",
|
| 137 |
+
"<|Ħ|>",
|
| 138 |
+
"<|ħ|>",
|
| 139 |
+
"<|Ĩ|>",
|
| 140 |
+
"<|ĩ|>",
|
| 141 |
+
"<|Ī|>",
|
| 142 |
+
"<|ī|>",
|
| 143 |
+
"<|Ĭ|>",
|
| 144 |
+
"<|ĭ|>",
|
| 145 |
+
"<|Į|>",
|
| 146 |
+
"<|į|>",
|
| 147 |
+
"<|İ|>",
|
| 148 |
+
"<|ı|>",
|
| 149 |
+
"<|IJ|>",
|
| 150 |
+
"<|ij|>",
|
| 151 |
+
"<|Ĵ|>",
|
| 152 |
+
"<|ĵ|>",
|
| 153 |
+
"<|Ķ|>",
|
| 154 |
+
"<|ķ|>",
|
| 155 |
+
"<|ĸ|>",
|
| 156 |
+
"<|Ĺ|>",
|
| 157 |
+
"<|ĺ|>",
|
| 158 |
+
"<|Ļ|>",
|
| 159 |
+
"<|ļ|>",
|
| 160 |
+
"<|Ľ|>",
|
| 161 |
+
"<|ľ|>",
|
| 162 |
+
"<|Ŀ|>",
|
| 163 |
+
"<|ŀ|>",
|
| 164 |
+
"<|Ł|>",
|
| 165 |
+
"<|ł|>",
|
| 166 |
+
"<|Ń|>",
|
| 167 |
+
"<|Ûķ|>",
|
| 168 |
+
"<|ÛĮ|>",
|
| 169 |
+
"<|ا|>",
|
| 170 |
+
"<|ĠØ|>",
|
| 171 |
+
"<|ÙĪ|>",
|
| 172 |
+
"<|ÙĨ|>",
|
| 173 |
+
"<|ر|>",
|
| 174 |
+
"<|Ú©|>",
|
| 175 |
+
"<|ĠÙ|>",
|
| 176 |
+
"<|ت|>",
|
| 177 |
+
"<|اÙĨ|>",
|
| 178 |
+
"<|Ûİ|>",
|
| 179 |
+
"<|د|>",
|
| 180 |
+
"<|Ùħ|>",
|
| 181 |
+
"<|Ġب|>",
|
| 182 |
+
"<|ÛĨ|>",
|
| 183 |
+
"<|س|>",
|
| 184 |
+
"<|translate|>",
|
| 185 |
+
"<|transcribe|>",
|
| 186 |
+
"<|startoflm|>",
|
| 187 |
+
"<|startofprev|>",
|
| 188 |
+
"<|nocaptions|>",
|
| 189 |
+
"<|notimestamps|>"
|
| 190 |
+
],
|
| 191 |
+
"bos_token": {
|
| 192 |
+
"content": "<|endoftext|>",
|
| 193 |
+
"lstrip": false,
|
| 194 |
+
"normalized": true,
|
| 195 |
+
"rstrip": false,
|
| 196 |
+
"single_word": false
|
| 197 |
+
},
|
| 198 |
+
"eos_token": {
|
| 199 |
+
"content": "<|endoftext|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false
|
| 204 |
+
},
|
| 205 |
+
"pad_token": {
|
| 206 |
+
"content": "<|endoftext|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false
|
| 211 |
+
},
|
| 212 |
+
"unk_token": {
|
| 213 |
+
"content": "<|endoftext|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false
|
| 218 |
+
}
|
| 219 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50522": {
|
| 6 |
+
"content": "<|startoftranscript|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50523": {
|
| 14 |
+
"content": "<|en|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"50524": {
|
| 22 |
+
"content": "<|zh|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"50525": {
|
| 30 |
+
"content": "<|de|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"50526": {
|
| 38 |
+
"content": "<|es|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"50527": {
|
| 46 |
+
"content": "<|ru|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"50528": {
|
| 54 |
+
"content": "<|ko|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"50529": {
|
| 62 |
+
"content": "<|fr|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"50530": {
|
| 70 |
+
"content": "<|ja|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"50531": {
|
| 78 |
+
"content": "<|pt|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"50532": {
|
| 86 |
+
"content": "<|tr|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"50533": {
|
| 94 |
+
"content": "<|pl|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"50534": {
|
| 102 |
+
"content": "<|ca|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"50535": {
|
| 110 |
+
"content": "<|nl|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"50536": {
|
| 118 |
+
"content": "<|ar|>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"50537": {
|
| 126 |
+
"content": "<|sv|>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"50538": {
|
| 134 |
+
"content": "<|it|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"50539": {
|
| 142 |
+
"content": "<|id|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"50540": {
|
| 150 |
+
"content": "<|hi|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"50541": {
|
| 158 |
+
"content": "<|fi|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"50542": {
|
| 166 |
+
"content": "<|vi|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"50543": {
|
| 174 |
+
"content": "<|he|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"50544": {
|
| 182 |
+
"content": "<|uk|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"50545": {
|
| 190 |
+
"content": "<|el|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": true,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"50546": {
|
| 198 |
+
"content": "<|ms|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": true,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"50547": {
|
| 206 |
+
"content": "<|cs|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": true,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"50548": {
|
| 214 |
+
"content": "<|ro|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": true,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"50549": {
|
| 222 |
+
"content": "<|da|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"50550": {
|
| 230 |
+
"content": "<|hu|>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": true,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"50551": {
|
| 238 |
+
"content": "<|ta|>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": true,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"50552": {
|
| 246 |
+
"content": "<|no|>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": true,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"50553": {
|
| 254 |
+
"content": "<|th|>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": true,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"50554": {
|
| 262 |
+
"content": "<|ur|>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": true,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"50555": {
|
| 270 |
+
"content": "<|hr|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": true,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"50556": {
|
| 278 |
+
"content": "<|bg|>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": true,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"50557": {
|
| 286 |
+
"content": "<|lt|>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": true,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"50558": {
|
| 294 |
+
"content": "<|la|>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": true,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"50559": {
|
| 302 |
+
"content": "<|mi|>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": true,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"50560": {
|
| 310 |
+
"content": "<|ml|>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": true,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"50561": {
|
| 318 |
+
"content": "<|cy|>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": true,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"50562": {
|
| 326 |
+
"content": "<|sk|>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": true,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"50563": {
|
| 334 |
+
"content": "<|te|>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": true,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"50564": {
|
| 342 |
+
"content": "<|fa|>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": true,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"50565": {
|
| 350 |
+
"content": "<|lv|>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": true,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"50566": {
|
| 358 |
+
"content": "<|bn|>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": true,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"50567": {
|
| 366 |
+
"content": "<|sr|>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": true,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"50568": {
|
| 374 |
+
"content": "<|az|>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": true,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"50569": {
|
| 382 |
+
"content": "<|sl|>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": true,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"50570": {
|
| 390 |
+
"content": "<|kn|>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": true,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"50571": {
|
| 398 |
+
"content": "<|et|>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": true,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"50572": {
|
| 406 |
+
"content": "<|mk|>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": true,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"50573": {
|
| 414 |
+
"content": "<|br|>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": true,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"50574": {
|
| 422 |
+
"content": "<|eu|>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": true,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"50575": {
|
| 430 |
+
"content": "<|is|>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": true,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"50576": {
|
| 438 |
+
"content": "<|hy|>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": true,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"50577": {
|
| 446 |
+
"content": "<|ne|>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": true,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"50578": {
|
| 454 |
+
"content": "<|mn|>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": true,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"50579": {
|
| 462 |
+
"content": "<|bs|>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": true,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"50580": {
|
| 470 |
+
"content": "<|kk|>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": true,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"50581": {
|
| 478 |
+
"content": "<|sq|>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": true,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"50582": {
|
| 486 |
+
"content": "<|sw|>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": true,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"50583": {
|
| 494 |
+
"content": "<|gl|>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": true,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"50584": {
|
| 502 |
+
"content": "<|mr|>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": true,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"50585": {
|
| 510 |
+
"content": "<|pa|>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": true,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"50586": {
|
| 518 |
+
"content": "<|si|>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": true,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"50587": {
|
| 526 |
+
"content": "<|km|>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": true,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"50588": {
|
| 534 |
+
"content": "<|sn|>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": true,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"50589": {
|
| 542 |
+
"content": "<|yo|>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": true,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"50590": {
|
| 550 |
+
"content": "<|so|>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": true,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"50591": {
|
| 558 |
+
"content": "<|af|>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": true,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"50592": {
|
| 566 |
+
"content": "<|oc|>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": true,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"50593": {
|
| 574 |
+
"content": "<|ka|>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": true,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"50594": {
|
| 582 |
+
"content": "<|be|>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": true,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"50595": {
|
| 590 |
+
"content": "<|tg|>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": true,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"50596": {
|
| 598 |
+
"content": "<|sd|>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": true,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"50597": {
|
| 606 |
+
"content": "<|gu|>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": true,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"50598": {
|
| 614 |
+
"content": "<|am|>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": true,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"50599": {
|
| 622 |
+
"content": "<|yi|>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": true,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"50600": {
|
| 630 |
+
"content": "<|lo|>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": true,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"50601": {
|
| 638 |
+
"content": "<|uz|>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": true,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"50602": {
|
| 646 |
+
"content": "<|fo|>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": true,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"50603": {
|
| 654 |
+
"content": "<|ht|>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": true,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"50604": {
|
| 662 |
+
"content": "<|ps|>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": true,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"50605": {
|
| 670 |
+
"content": "<|tk|>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": true,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"50606": {
|
| 678 |
+
"content": "<|nn|>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": true,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"50607": {
|
| 686 |
+
"content": "<|mt|>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": true,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"50608": {
|
| 694 |
+
"content": "<|sa|>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": true,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"50609": {
|
| 702 |
+
"content": "<|lb|>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": true,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"50610": {
|
| 710 |
+
"content": "<|my|>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": true,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"50611": {
|
| 718 |
+
"content": "<|bo|>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": true,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"50612": {
|
| 726 |
+
"content": "<|tl|>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": true,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"50613": {
|
| 734 |
+
"content": "<|mg|>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": true,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"50614": {
|
| 742 |
+
"content": "<|as|>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": true,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"50615": {
|
| 750 |
+
"content": "<|tt|>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": true,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"50616": {
|
| 758 |
+
"content": "<|haw|>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": true,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"50617": {
|
| 766 |
+
"content": "<|ln|>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": true,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"50618": {
|
| 774 |
+
"content": "<|ha|>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": true,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"50619": {
|
| 782 |
+
"content": "<|ba|>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": true,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"50620": {
|
| 790 |
+
"content": "<|jw|>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": true,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"50621": {
|
| 798 |
+
"content": "<|su|>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": true,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"50622": {
|
| 806 |
+
"content": "<|translate|>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": true
|
| 812 |
+
},
|
| 813 |
+
"50623": {
|
| 814 |
+
"content": "<|transcribe|>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
"50624": {
|
| 822 |
+
"content": "<|startoflm|>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": true
|
| 828 |
+
},
|
| 829 |
+
"50625": {
|
| 830 |
+
"content": "<|startofprev|>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": true
|
| 836 |
+
},
|
| 837 |
+
"50626": {
|
| 838 |
+
"content": "<|nocaptions|>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": true
|
| 844 |
+
},
|
| 845 |
+
"50627": {
|
| 846 |
+
"content": "<|notimestamps|>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": true
|
| 852 |
+
},
|
| 853 |
+
"50628": {
|
| 854 |
+
"content": "<|endoftext|>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": true,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"50629": {
|
| 862 |
+
"content": "<|¡|>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"50630": {
|
| 870 |
+
"content": "<|¢|>",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": true
|
| 876 |
+
},
|
| 877 |
+
"50631": {
|
| 878 |
+
"content": "<|£|>",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": true
|
| 884 |
+
},
|
| 885 |
+
"50632": {
|
| 886 |
+
"content": "<|¤|>",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": true
|
| 892 |
+
},
|
| 893 |
+
"50633": {
|
| 894 |
+
"content": "<|¥|>",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": true
|
| 900 |
+
},
|
| 901 |
+
"50634": {
|
| 902 |
+
"content": "<|¦|>",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": true
|
| 908 |
+
},
|
| 909 |
+
"50635": {
|
| 910 |
+
"content": "<|§|>",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": true
|
| 916 |
+
},
|
| 917 |
+
"50636": {
|
| 918 |
+
"content": "<|¨|>",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": true
|
| 924 |
+
},
|
| 925 |
+
"50637": {
|
| 926 |
+
"content": "<|©|>",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": true
|
| 932 |
+
},
|
| 933 |
+
"50638": {
|
| 934 |
+
"content": "<|ª|>",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": true
|
| 940 |
+
},
|
| 941 |
+
"50639": {
|
| 942 |
+
"content": "<|«|>",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": true
|
| 948 |
+
},
|
| 949 |
+
"50640": {
|
| 950 |
+
"content": "<|¬|>",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": true
|
| 956 |
+
},
|
| 957 |
+
"50641": {
|
| 958 |
+
"content": "<|®|>",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": true
|
| 964 |
+
},
|
| 965 |
+
"50642": {
|
| 966 |
+
"content": "<|¯|>",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": true
|
| 972 |
+
},
|
| 973 |
+
"50643": {
|
| 974 |
+
"content": "<|°|>",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": true
|
| 980 |
+
},
|
| 981 |
+
"50644": {
|
| 982 |
+
"content": "<|±|>",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": true
|
| 988 |
+
},
|
| 989 |
+
"50645": {
|
| 990 |
+
"content": "<|²|>",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": true
|
| 996 |
+
},
|
| 997 |
+
"50646": {
|
| 998 |
+
"content": "<|³|>",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": true
|
| 1004 |
+
},
|
| 1005 |
+
"50647": {
|
| 1006 |
+
"content": "<|´|>",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": true
|
| 1012 |
+
},
|
| 1013 |
+
"50648": {
|
| 1014 |
+
"content": "<|µ|>",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": true
|
| 1020 |
+
},
|
| 1021 |
+
"50649": {
|
| 1022 |
+
"content": "<|¶|>",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": true
|
| 1028 |
+
},
|
| 1029 |
+
"50650": {
|
| 1030 |
+
"content": "<|·|>",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": true
|
| 1036 |
+
},
|
| 1037 |
+
"50651": {
|
| 1038 |
+
"content": "<|¸|>",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": true
|
| 1044 |
+
},
|
| 1045 |
+
"50652": {
|
| 1046 |
+
"content": "<|¹|>",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": true
|
| 1052 |
+
},
|
| 1053 |
+
"50653": {
|
| 1054 |
+
"content": "<|º|>",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": true
|
| 1060 |
+
},
|
| 1061 |
+
"50654": {
|
| 1062 |
+
"content": "<|»|>",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": true
|
| 1068 |
+
},
|
| 1069 |
+
"50655": {
|
| 1070 |
+
"content": "<|¼|>",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": true
|
| 1076 |
+
},
|
| 1077 |
+
"50656": {
|
| 1078 |
+
"content": "<|½|>",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": true
|
| 1084 |
+
},
|
| 1085 |
+
"50657": {
|
| 1086 |
+
"content": "<|¾|>",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": true
|
| 1092 |
+
},
|
| 1093 |
+
"50658": {
|
| 1094 |
+
"content": "<|¿|>",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": true
|
| 1100 |
+
},
|
| 1101 |
+
"50659": {
|
| 1102 |
+
"content": "<|À|>",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": true
|
| 1108 |
+
},
|
| 1109 |
+
"50660": {
|
| 1110 |
+
"content": "<|Á|>",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": true
|
| 1116 |
+
},
|
| 1117 |
+
"50661": {
|
| 1118 |
+
"content": "<|Â|>",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": true
|
| 1124 |
+
},
|
| 1125 |
+
"50662": {
|
| 1126 |
+
"content": "<|Ã|>",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": true
|
| 1132 |
+
},
|
| 1133 |
+
"50663": {
|
| 1134 |
+
"content": "<|Ä|>",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": true
|
| 1140 |
+
},
|
| 1141 |
+
"50664": {
|
| 1142 |
+
"content": "<|Å|>",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": true
|
| 1148 |
+
},
|
| 1149 |
+
"50665": {
|
| 1150 |
+
"content": "<|Æ|>",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": true
|
| 1156 |
+
},
|
| 1157 |
+
"50666": {
|
| 1158 |
+
"content": "<|Ç|>",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": true
|
| 1164 |
+
},
|
| 1165 |
+
"50667": {
|
| 1166 |
+
"content": "<|È|>",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": true
|
| 1172 |
+
},
|
| 1173 |
+
"50668": {
|
| 1174 |
+
"content": "<|É|>",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": true
|
| 1180 |
+
},
|
| 1181 |
+
"50669": {
|
| 1182 |
+
"content": "<|Ê|>",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": true
|
| 1188 |
+
},
|
| 1189 |
+
"50670": {
|
| 1190 |
+
"content": "<|Ë|>",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": true
|
| 1196 |
+
},
|
| 1197 |
+
"50671": {
|
| 1198 |
+
"content": "<|Ì|>",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": true
|
| 1204 |
+
},
|
| 1205 |
+
"50672": {
|
| 1206 |
+
"content": "<|Í|>",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": true
|
| 1212 |
+
},
|
| 1213 |
+
"50673": {
|
| 1214 |
+
"content": "<|Î|>",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": true
|
| 1220 |
+
},
|
| 1221 |
+
"50674": {
|
| 1222 |
+
"content": "<|Ï|>",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": true
|
| 1228 |
+
},
|
| 1229 |
+
"50675": {
|
| 1230 |
+
"content": "<|Ð|>",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": true
|
| 1236 |
+
},
|
| 1237 |
+
"50676": {
|
| 1238 |
+
"content": "<|Ñ|>",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": true
|
| 1244 |
+
},
|
| 1245 |
+
"50677": {
|
| 1246 |
+
"content": "<|Ò|>",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": true
|
| 1252 |
+
},
|
| 1253 |
+
"50678": {
|
| 1254 |
+
"content": "<|Ó|>",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": true
|
| 1260 |
+
},
|
| 1261 |
+
"50679": {
|
| 1262 |
+
"content": "<|Ô|>",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": true
|
| 1268 |
+
},
|
| 1269 |
+
"50680": {
|
| 1270 |
+
"content": "<|Õ|>",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": true
|
| 1276 |
+
},
|
| 1277 |
+
"50681": {
|
| 1278 |
+
"content": "<|Ö|>",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": true
|
| 1284 |
+
},
|
| 1285 |
+
"50682": {
|
| 1286 |
+
"content": "<|×|>",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": true
|
| 1292 |
+
},
|
| 1293 |
+
"50683": {
|
| 1294 |
+
"content": "<|Ø|>",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": true
|
| 1300 |
+
},
|
| 1301 |
+
"50684": {
|
| 1302 |
+
"content": "<|Ù|>",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": true
|
| 1308 |
+
},
|
| 1309 |
+
"50685": {
|
| 1310 |
+
"content": "<|Ú|>",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": true
|
| 1316 |
+
},
|
| 1317 |
+
"50686": {
|
| 1318 |
+
"content": "<|Û|>",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": true
|
| 1324 |
+
},
|
| 1325 |
+
"50687": {
|
| 1326 |
+
"content": "<|Ü|>",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": true
|
| 1332 |
+
},
|
| 1333 |
+
"50688": {
|
| 1334 |
+
"content": "<|Ý|>",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": true
|
| 1340 |
+
},
|
| 1341 |
+
"50689": {
|
| 1342 |
+
"content": "<|Þ|>",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": true
|
| 1348 |
+
},
|
| 1349 |
+
"50690": {
|
| 1350 |
+
"content": "<|ß|>",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": true
|
| 1356 |
+
},
|
| 1357 |
+
"50691": {
|
| 1358 |
+
"content": "<|à|>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": true
|
| 1364 |
+
},
|
| 1365 |
+
"50692": {
|
| 1366 |
+
"content": "<|á|>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": true
|
| 1372 |
+
},
|
| 1373 |
+
"50693": {
|
| 1374 |
+
"content": "<|â|>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": true
|
| 1380 |
+
},
|
| 1381 |
+
"50694": {
|
| 1382 |
+
"content": "<|ã|>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": true
|
| 1388 |
+
},
|
| 1389 |
+
"50695": {
|
| 1390 |
+
"content": "<|ä|>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": true
|
| 1396 |
+
},
|
| 1397 |
+
"50696": {
|
| 1398 |
+
"content": "<|å|>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": true
|
| 1404 |
+
},
|
| 1405 |
+
"50697": {
|
| 1406 |
+
"content": "<|æ|>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": true
|
| 1412 |
+
},
|
| 1413 |
+
"50698": {
|
| 1414 |
+
"content": "<|ç|>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": true
|
| 1420 |
+
},
|
| 1421 |
+
"50699": {
|
| 1422 |
+
"content": "<|è|>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": true
|
| 1428 |
+
},
|
| 1429 |
+
"50700": {
|
| 1430 |
+
"content": "<|é|>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": true
|
| 1436 |
+
},
|
| 1437 |
+
"50701": {
|
| 1438 |
+
"content": "<|ê|>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": true
|
| 1444 |
+
},
|
| 1445 |
+
"50702": {
|
| 1446 |
+
"content": "<|ë|>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": true
|
| 1452 |
+
},
|
| 1453 |
+
"50703": {
|
| 1454 |
+
"content": "<|ì|>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": true
|
| 1460 |
+
},
|
| 1461 |
+
"50704": {
|
| 1462 |
+
"content": "<|í|>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": true
|
| 1468 |
+
},
|
| 1469 |
+
"50705": {
|
| 1470 |
+
"content": "<|î|>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": true
|
| 1476 |
+
},
|
| 1477 |
+
"50706": {
|
| 1478 |
+
"content": "<|ï|>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": true
|
| 1484 |
+
},
|
| 1485 |
+
"50707": {
|
| 1486 |
+
"content": "<|ð|>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": true
|
| 1492 |
+
},
|
| 1493 |
+
"50708": {
|
| 1494 |
+
"content": "<|ñ|>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": true
|
| 1500 |
+
},
|
| 1501 |
+
"50709": {
|
| 1502 |
+
"content": "<|ò|>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": true
|
| 1508 |
+
},
|
| 1509 |
+
"50710": {
|
| 1510 |
+
"content": "<|ó|>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": true
|
| 1516 |
+
},
|
| 1517 |
+
"50711": {
|
| 1518 |
+
"content": "<|ô|>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": true
|
| 1524 |
+
},
|
| 1525 |
+
"50712": {
|
| 1526 |
+
"content": "<|õ|>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": true
|
| 1532 |
+
},
|
| 1533 |
+
"50713": {
|
| 1534 |
+
"content": "<|ö|>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": true
|
| 1540 |
+
},
|
| 1541 |
+
"50714": {
|
| 1542 |
+
"content": "<|÷|>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": true
|
| 1548 |
+
},
|
| 1549 |
+
"50715": {
|
| 1550 |
+
"content": "<|ø|>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": true
|
| 1556 |
+
},
|
| 1557 |
+
"50716": {
|
| 1558 |
+
"content": "<|ù|>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": true
|
| 1564 |
+
},
|
| 1565 |
+
"50717": {
|
| 1566 |
+
"content": "<|ú|>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": true
|
| 1572 |
+
},
|
| 1573 |
+
"50718": {
|
| 1574 |
+
"content": "<|û|>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": true
|
| 1580 |
+
},
|
| 1581 |
+
"50719": {
|
| 1582 |
+
"content": "<|ü|>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": true
|
| 1588 |
+
},
|
| 1589 |
+
"50720": {
|
| 1590 |
+
"content": "<|ý|>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": true
|
| 1596 |
+
},
|
| 1597 |
+
"50721": {
|
| 1598 |
+
"content": "<|þ|>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": true
|
| 1604 |
+
},
|
| 1605 |
+
"50722": {
|
| 1606 |
+
"content": "<|ÿ|>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": true
|
| 1612 |
+
},
|
| 1613 |
+
"50723": {
|
| 1614 |
+
"content": "<|Ā|>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": true
|
| 1620 |
+
},
|
| 1621 |
+
"50724": {
|
| 1622 |
+
"content": "<|ā|>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": true
|
| 1628 |
+
},
|
| 1629 |
+
"50725": {
|
| 1630 |
+
"content": "<|Ă|>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": true
|
| 1636 |
+
},
|
| 1637 |
+
"50726": {
|
| 1638 |
+
"content": "<|ă|>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": true
|
| 1644 |
+
},
|
| 1645 |
+
"50727": {
|
| 1646 |
+
"content": "<|Ą|>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": true
|
| 1652 |
+
},
|
| 1653 |
+
"50728": {
|
| 1654 |
+
"content": "<|ą|>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": true
|
| 1660 |
+
},
|
| 1661 |
+
"50729": {
|
| 1662 |
+
"content": "<|Ć|>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": true
|
| 1668 |
+
},
|
| 1669 |
+
"50730": {
|
| 1670 |
+
"content": "<|ć|>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": true
|
| 1676 |
+
},
|
| 1677 |
+
"50731": {
|
| 1678 |
+
"content": "<|Ĉ|>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": true
|
| 1684 |
+
},
|
| 1685 |
+
"50732": {
|
| 1686 |
+
"content": "<|ĉ|>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": true
|
| 1692 |
+
},
|
| 1693 |
+
"50733": {
|
| 1694 |
+
"content": "<|Ċ|>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": true
|
| 1700 |
+
},
|
| 1701 |
+
"50734": {
|
| 1702 |
+
"content": "<|ċ|>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": true
|
| 1708 |
+
},
|
| 1709 |
+
"50735": {
|
| 1710 |
+
"content": "<|Č|>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": true
|
| 1716 |
+
},
|
| 1717 |
+
"50736": {
|
| 1718 |
+
"content": "<|č|>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": true
|
| 1724 |
+
},
|
| 1725 |
+
"50737": {
|
| 1726 |
+
"content": "<|Ď|>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": true
|
| 1732 |
+
},
|
| 1733 |
+
"50738": {
|
| 1734 |
+
"content": "<|ď|>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": true
|
| 1740 |
+
},
|
| 1741 |
+
"50739": {
|
| 1742 |
+
"content": "<|Đ|>",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": true
|
| 1748 |
+
},
|
| 1749 |
+
"50740": {
|
| 1750 |
+
"content": "<|đ|>",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": true
|
| 1756 |
+
},
|
| 1757 |
+
"50741": {
|
| 1758 |
+
"content": "<|Ē|>",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": true
|
| 1764 |
+
},
|
| 1765 |
+
"50742": {
|
| 1766 |
+
"content": "<|ē|>",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": true
|
| 1772 |
+
},
|
| 1773 |
+
"50743": {
|
| 1774 |
+
"content": "<|Ĕ|>",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": true
|
| 1780 |
+
},
|
| 1781 |
+
"50744": {
|
| 1782 |
+
"content": "<|ĕ|>",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": true
|
| 1788 |
+
},
|
| 1789 |
+
"50745": {
|
| 1790 |
+
"content": "<|Ė|>",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": true
|
| 1796 |
+
},
|
| 1797 |
+
"50746": {
|
| 1798 |
+
"content": "<|ė|>",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": true
|
| 1804 |
+
},
|
| 1805 |
+
"50747": {
|
| 1806 |
+
"content": "<|Ę|>",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": true
|
| 1812 |
+
},
|
| 1813 |
+
"50748": {
|
| 1814 |
+
"content": "<|ę|>",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": true
|
| 1820 |
+
},
|
| 1821 |
+
"50749": {
|
| 1822 |
+
"content": "<|Ě|>",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": true
|
| 1828 |
+
},
|
| 1829 |
+
"50750": {
|
| 1830 |
+
"content": "<|ě|>",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": true
|
| 1836 |
+
},
|
| 1837 |
+
"50751": {
|
| 1838 |
+
"content": "<|Ĝ|>",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": true
|
| 1844 |
+
},
|
| 1845 |
+
"50752": {
|
| 1846 |
+
"content": "<|ĝ|>",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": true
|
| 1852 |
+
},
|
| 1853 |
+
"50753": {
|
| 1854 |
+
"content": "<|Ğ|>",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": true
|
| 1860 |
+
},
|
| 1861 |
+
"50754": {
|
| 1862 |
+
"content": "<|ğ|>",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": true
|
| 1868 |
+
},
|
| 1869 |
+
"50755": {
|
| 1870 |
+
"content": "<|Ġ|>",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": true
|
| 1876 |
+
},
|
| 1877 |
+
"50756": {
|
| 1878 |
+
"content": "<|ġ|>",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": true
|
| 1884 |
+
},
|
| 1885 |
+
"50757": {
|
| 1886 |
+
"content": "<|Ģ|>",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": true
|
| 1892 |
+
},
|
| 1893 |
+
"50758": {
|
| 1894 |
+
"content": "<|ģ|>",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": true
|
| 1900 |
+
},
|
| 1901 |
+
"50759": {
|
| 1902 |
+
"content": "<|Ĥ|>",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": true
|
| 1908 |
+
},
|
| 1909 |
+
"50760": {
|
| 1910 |
+
"content": "<|ĥ|>",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": true
|
| 1916 |
+
},
|
| 1917 |
+
"50761": {
|
| 1918 |
+
"content": "<|Ħ|>",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": true
|
| 1924 |
+
},
|
| 1925 |
+
"50762": {
|
| 1926 |
+
"content": "<|ħ|>",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": true
|
| 1932 |
+
},
|
| 1933 |
+
"50763": {
|
| 1934 |
+
"content": "<|Ĩ|>",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": true
|
| 1940 |
+
},
|
| 1941 |
+
"50764": {
|
| 1942 |
+
"content": "<|ĩ|>",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": true
|
| 1948 |
+
},
|
| 1949 |
+
"50765": {
|
| 1950 |
+
"content": "<|Ī|>",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": true
|
| 1956 |
+
},
|
| 1957 |
+
"50766": {
|
| 1958 |
+
"content": "<|ī|>",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": true
|
| 1964 |
+
},
|
| 1965 |
+
"50767": {
|
| 1966 |
+
"content": "<|Ĭ|>",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": true
|
| 1972 |
+
},
|
| 1973 |
+
"50768": {
|
| 1974 |
+
"content": "<|ĭ|>",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": true
|
| 1980 |
+
},
|
| 1981 |
+
"50769": {
|
| 1982 |
+
"content": "<|Į|>",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": true
|
| 1988 |
+
},
|
| 1989 |
+
"50770": {
|
| 1990 |
+
"content": "<|į|>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": true
|
| 1996 |
+
},
|
| 1997 |
+
"50771": {
|
| 1998 |
+
"content": "<|İ|>",
|
| 1999 |
+
"lstrip": false,
|
| 2000 |
+
"normalized": false,
|
| 2001 |
+
"rstrip": false,
|
| 2002 |
+
"single_word": false,
|
| 2003 |
+
"special": true
|
| 2004 |
+
},
|
| 2005 |
+
"50772": {
|
| 2006 |
+
"content": "<|ı|>",
|
| 2007 |
+
"lstrip": false,
|
| 2008 |
+
"normalized": false,
|
| 2009 |
+
"rstrip": false,
|
| 2010 |
+
"single_word": false,
|
| 2011 |
+
"special": true
|
| 2012 |
+
},
|
| 2013 |
+
"50773": {
|
| 2014 |
+
"content": "<|IJ|>",
|
| 2015 |
+
"lstrip": false,
|
| 2016 |
+
"normalized": false,
|
| 2017 |
+
"rstrip": false,
|
| 2018 |
+
"single_word": false,
|
| 2019 |
+
"special": true
|
| 2020 |
+
},
|
| 2021 |
+
"50774": {
|
| 2022 |
+
"content": "<|ij|>",
|
| 2023 |
+
"lstrip": false,
|
| 2024 |
+
"normalized": false,
|
| 2025 |
+
"rstrip": false,
|
| 2026 |
+
"single_word": false,
|
| 2027 |
+
"special": true
|
| 2028 |
+
},
|
| 2029 |
+
"50775": {
|
| 2030 |
+
"content": "<|Ĵ|>",
|
| 2031 |
+
"lstrip": false,
|
| 2032 |
+
"normalized": false,
|
| 2033 |
+
"rstrip": false,
|
| 2034 |
+
"single_word": false,
|
| 2035 |
+
"special": true
|
| 2036 |
+
},
|
| 2037 |
+
"50776": {
|
| 2038 |
+
"content": "<|ĵ|>",
|
| 2039 |
+
"lstrip": false,
|
| 2040 |
+
"normalized": false,
|
| 2041 |
+
"rstrip": false,
|
| 2042 |
+
"single_word": false,
|
| 2043 |
+
"special": true
|
| 2044 |
+
},
|
| 2045 |
+
"50777": {
|
| 2046 |
+
"content": "<|Ķ|>",
|
| 2047 |
+
"lstrip": false,
|
| 2048 |
+
"normalized": false,
|
| 2049 |
+
"rstrip": false,
|
| 2050 |
+
"single_word": false,
|
| 2051 |
+
"special": true
|
| 2052 |
+
},
|
| 2053 |
+
"50778": {
|
| 2054 |
+
"content": "<|ķ|>",
|
| 2055 |
+
"lstrip": false,
|
| 2056 |
+
"normalized": false,
|
| 2057 |
+
"rstrip": false,
|
| 2058 |
+
"single_word": false,
|
| 2059 |
+
"special": true
|
| 2060 |
+
},
|
| 2061 |
+
"50779": {
|
| 2062 |
+
"content": "<|ĸ|>",
|
| 2063 |
+
"lstrip": false,
|
| 2064 |
+
"normalized": false,
|
| 2065 |
+
"rstrip": false,
|
| 2066 |
+
"single_word": false,
|
| 2067 |
+
"special": true
|
| 2068 |
+
},
|
| 2069 |
+
"50780": {
|
| 2070 |
+
"content": "<|Ĺ|>",
|
| 2071 |
+
"lstrip": false,
|
| 2072 |
+
"normalized": false,
|
| 2073 |
+
"rstrip": false,
|
| 2074 |
+
"single_word": false,
|
| 2075 |
+
"special": true
|
| 2076 |
+
},
|
| 2077 |
+
"50781": {
|
| 2078 |
+
"content": "<|ĺ|>",
|
| 2079 |
+
"lstrip": false,
|
| 2080 |
+
"normalized": false,
|
| 2081 |
+
"rstrip": false,
|
| 2082 |
+
"single_word": false,
|
| 2083 |
+
"special": true
|
| 2084 |
+
},
|
| 2085 |
+
"50782": {
|
| 2086 |
+
"content": "<|Ļ|>",
|
| 2087 |
+
"lstrip": false,
|
| 2088 |
+
"normalized": false,
|
| 2089 |
+
"rstrip": false,
|
| 2090 |
+
"single_word": false,
|
| 2091 |
+
"special": true
|
| 2092 |
+
},
|
| 2093 |
+
"50783": {
|
| 2094 |
+
"content": "<|ļ|>",
|
| 2095 |
+
"lstrip": false,
|
| 2096 |
+
"normalized": false,
|
| 2097 |
+
"rstrip": false,
|
| 2098 |
+
"single_word": false,
|
| 2099 |
+
"special": true
|
| 2100 |
+
},
|
| 2101 |
+
"50784": {
|
| 2102 |
+
"content": "<|Ľ|>",
|
| 2103 |
+
"lstrip": false,
|
| 2104 |
+
"normalized": false,
|
| 2105 |
+
"rstrip": false,
|
| 2106 |
+
"single_word": false,
|
| 2107 |
+
"special": true
|
| 2108 |
+
},
|
| 2109 |
+
"50785": {
|
| 2110 |
+
"content": "<|ľ|>",
|
| 2111 |
+
"lstrip": false,
|
| 2112 |
+
"normalized": false,
|
| 2113 |
+
"rstrip": false,
|
| 2114 |
+
"single_word": false,
|
| 2115 |
+
"special": true
|
| 2116 |
+
},
|
| 2117 |
+
"50786": {
|
| 2118 |
+
"content": "<|Ŀ|>",
|
| 2119 |
+
"lstrip": false,
|
| 2120 |
+
"normalized": false,
|
| 2121 |
+
"rstrip": false,
|
| 2122 |
+
"single_word": false,
|
| 2123 |
+
"special": true
|
| 2124 |
+
},
|
| 2125 |
+
"50787": {
|
| 2126 |
+
"content": "<|ŀ|>",
|
| 2127 |
+
"lstrip": false,
|
| 2128 |
+
"normalized": false,
|
| 2129 |
+
"rstrip": false,
|
| 2130 |
+
"single_word": false,
|
| 2131 |
+
"special": true
|
| 2132 |
+
},
|
| 2133 |
+
"50788": {
|
| 2134 |
+
"content": "<|Ł|>",
|
| 2135 |
+
"lstrip": false,
|
| 2136 |
+
"normalized": false,
|
| 2137 |
+
"rstrip": false,
|
| 2138 |
+
"single_word": false,
|
| 2139 |
+
"special": true
|
| 2140 |
+
},
|
| 2141 |
+
"50789": {
|
| 2142 |
+
"content": "<|ł|>",
|
| 2143 |
+
"lstrip": false,
|
| 2144 |
+
"normalized": false,
|
| 2145 |
+
"rstrip": false,
|
| 2146 |
+
"single_word": false,
|
| 2147 |
+
"special": true
|
| 2148 |
+
},
|
| 2149 |
+
"50790": {
|
| 2150 |
+
"content": "<|Ń|>",
|
| 2151 |
+
"lstrip": false,
|
| 2152 |
+
"normalized": false,
|
| 2153 |
+
"rstrip": false,
|
| 2154 |
+
"single_word": false,
|
| 2155 |
+
"special": true
|
| 2156 |
+
},
|
| 2157 |
+
"50791": {
|
| 2158 |
+
"content": "<|Ûķ|>",
|
| 2159 |
+
"lstrip": false,
|
| 2160 |
+
"normalized": false,
|
| 2161 |
+
"rstrip": false,
|
| 2162 |
+
"single_word": false,
|
| 2163 |
+
"special": true
|
| 2164 |
+
},
|
| 2165 |
+
"50792": {
|
| 2166 |
+
"content": "<|ÛĮ|>",
|
| 2167 |
+
"lstrip": false,
|
| 2168 |
+
"normalized": false,
|
| 2169 |
+
"rstrip": false,
|
| 2170 |
+
"single_word": false,
|
| 2171 |
+
"special": true
|
| 2172 |
+
},
|
| 2173 |
+
"50793": {
|
| 2174 |
+
"content": "<|ا|>",
|
| 2175 |
+
"lstrip": false,
|
| 2176 |
+
"normalized": false,
|
| 2177 |
+
"rstrip": false,
|
| 2178 |
+
"single_word": false,
|
| 2179 |
+
"special": true
|
| 2180 |
+
},
|
| 2181 |
+
"50794": {
|
| 2182 |
+
"content": "<|ĠØ|>",
|
| 2183 |
+
"lstrip": false,
|
| 2184 |
+
"normalized": false,
|
| 2185 |
+
"rstrip": false,
|
| 2186 |
+
"single_word": false,
|
| 2187 |
+
"special": true
|
| 2188 |
+
},
|
| 2189 |
+
"50795": {
|
| 2190 |
+
"content": "<|ÙĪ|>",
|
| 2191 |
+
"lstrip": false,
|
| 2192 |
+
"normalized": false,
|
| 2193 |
+
"rstrip": false,
|
| 2194 |
+
"single_word": false,
|
| 2195 |
+
"special": true
|
| 2196 |
+
},
|
| 2197 |
+
"50796": {
|
| 2198 |
+
"content": "<|ÙĨ|>",
|
| 2199 |
+
"lstrip": false,
|
| 2200 |
+
"normalized": false,
|
| 2201 |
+
"rstrip": false,
|
| 2202 |
+
"single_word": false,
|
| 2203 |
+
"special": true
|
| 2204 |
+
},
|
| 2205 |
+
"50797": {
|
| 2206 |
+
"content": "<|ر|>",
|
| 2207 |
+
"lstrip": false,
|
| 2208 |
+
"normalized": false,
|
| 2209 |
+
"rstrip": false,
|
| 2210 |
+
"single_word": false,
|
| 2211 |
+
"special": true
|
| 2212 |
+
},
|
| 2213 |
+
"50798": {
|
| 2214 |
+
"content": "<|Ú©|>",
|
| 2215 |
+
"lstrip": false,
|
| 2216 |
+
"normalized": false,
|
| 2217 |
+
"rstrip": false,
|
| 2218 |
+
"single_word": false,
|
| 2219 |
+
"special": true
|
| 2220 |
+
},
|
| 2221 |
+
"50799": {
|
| 2222 |
+
"content": "<|ĠÙ|>",
|
| 2223 |
+
"lstrip": false,
|
| 2224 |
+
"normalized": false,
|
| 2225 |
+
"rstrip": false,
|
| 2226 |
+
"single_word": false,
|
| 2227 |
+
"special": true
|
| 2228 |
+
},
|
| 2229 |
+
"50800": {
|
| 2230 |
+
"content": "<|ت|>",
|
| 2231 |
+
"lstrip": false,
|
| 2232 |
+
"normalized": false,
|
| 2233 |
+
"rstrip": false,
|
| 2234 |
+
"single_word": false,
|
| 2235 |
+
"special": true
|
| 2236 |
+
},
|
| 2237 |
+
"50801": {
|
| 2238 |
+
"content": "<|اÙĨ|>",
|
| 2239 |
+
"lstrip": false,
|
| 2240 |
+
"normalized": false,
|
| 2241 |
+
"rstrip": false,
|
| 2242 |
+
"single_word": false,
|
| 2243 |
+
"special": true
|
| 2244 |
+
},
|
| 2245 |
+
"50802": {
|
| 2246 |
+
"content": "<|Ûİ|>",
|
| 2247 |
+
"lstrip": false,
|
| 2248 |
+
"normalized": false,
|
| 2249 |
+
"rstrip": false,
|
| 2250 |
+
"single_word": false,
|
| 2251 |
+
"special": true
|
| 2252 |
+
},
|
| 2253 |
+
"50803": {
|
| 2254 |
+
"content": "<|د|>",
|
| 2255 |
+
"lstrip": false,
|
| 2256 |
+
"normalized": false,
|
| 2257 |
+
"rstrip": false,
|
| 2258 |
+
"single_word": false,
|
| 2259 |
+
"special": true
|
| 2260 |
+
},
|
| 2261 |
+
"50804": {
|
| 2262 |
+
"content": "<|Ùħ|>",
|
| 2263 |
+
"lstrip": false,
|
| 2264 |
+
"normalized": false,
|
| 2265 |
+
"rstrip": false,
|
| 2266 |
+
"single_word": false,
|
| 2267 |
+
"special": true
|
| 2268 |
+
},
|
| 2269 |
+
"50805": {
|
| 2270 |
+
"content": "<|Ġب|>",
|
| 2271 |
+
"lstrip": false,
|
| 2272 |
+
"normalized": false,
|
| 2273 |
+
"rstrip": false,
|
| 2274 |
+
"single_word": false,
|
| 2275 |
+
"special": true
|
| 2276 |
+
},
|
| 2277 |
+
"50806": {
|
| 2278 |
+
"content": "<|ÛĨ|>",
|
| 2279 |
+
"lstrip": false,
|
| 2280 |
+
"normalized": false,
|
| 2281 |
+
"rstrip": false,
|
| 2282 |
+
"single_word": false,
|
| 2283 |
+
"special": true
|
| 2284 |
+
},
|
| 2285 |
+
"50807": {
|
| 2286 |
+
"content": "<|س|>",
|
| 2287 |
+
"lstrip": false,
|
| 2288 |
+
"normalized": false,
|
| 2289 |
+
"rstrip": false,
|
| 2290 |
+
"single_word": false,
|
| 2291 |
+
"special": true
|
| 2292 |
+
}
|
| 2293 |
+
},
|
| 2294 |
+
"additional_special_tokens": [
|
| 2295 |
+
"<|endoftext|>",
|
| 2296 |
+
"<|startoftranscript|>",
|
| 2297 |
+
"<|¡|>",
|
| 2298 |
+
"<|¢|>",
|
| 2299 |
+
"<|£|>",
|
| 2300 |
+
"<|¤|>",
|
| 2301 |
+
"<|¥|>",
|
| 2302 |
+
"<|¦|>",
|
| 2303 |
+
"<|§|>",
|
| 2304 |
+
"<|¨|>",
|
| 2305 |
+
"<|©|>",
|
| 2306 |
+
"<|ª|>",
|
| 2307 |
+
"<|«|>",
|
| 2308 |
+
"<|¬|>",
|
| 2309 |
+
"<|®|>",
|
| 2310 |
+
"<|¯|>",
|
| 2311 |
+
"<|°|>",
|
| 2312 |
+
"<|±|>",
|
| 2313 |
+
"<|²|>",
|
| 2314 |
+
"<|³|>",
|
| 2315 |
+
"<|´|>",
|
| 2316 |
+
"<|µ|>",
|
| 2317 |
+
"<|¶|>",
|
| 2318 |
+
"<|·|>",
|
| 2319 |
+
"<|¸|>",
|
| 2320 |
+
"<|¹|>",
|
| 2321 |
+
"<|º|>",
|
| 2322 |
+
"<|»|>",
|
| 2323 |
+
"<|¼|>",
|
| 2324 |
+
"<|½|>",
|
| 2325 |
+
"<|¾|>",
|
| 2326 |
+
"<|¿|>",
|
| 2327 |
+
"<|À|>",
|
| 2328 |
+
"<|Á|>",
|
| 2329 |
+
"<|Â|>",
|
| 2330 |
+
"<|Ã|>",
|
| 2331 |
+
"<|Ä|>",
|
| 2332 |
+
"<|Å|>",
|
| 2333 |
+
"<|Æ|>",
|
| 2334 |
+
"<|Ç|>",
|
| 2335 |
+
"<|È|>",
|
| 2336 |
+
"<|É|>",
|
| 2337 |
+
"<|Ê|>",
|
| 2338 |
+
"<|Ë|>",
|
| 2339 |
+
"<|Ì|>",
|
| 2340 |
+
"<|Í|>",
|
| 2341 |
+
"<|Î|>",
|
| 2342 |
+
"<|Ï|>",
|
| 2343 |
+
"<|Ð|>",
|
| 2344 |
+
"<|Ñ|>",
|
| 2345 |
+
"<|Ò|>",
|
| 2346 |
+
"<|Ó|>",
|
| 2347 |
+
"<|Ô|>",
|
| 2348 |
+
"<|Õ|>",
|
| 2349 |
+
"<|Ö|>",
|
| 2350 |
+
"<|×|>",
|
| 2351 |
+
"<|Ø|>",
|
| 2352 |
+
"<|Ù|>",
|
| 2353 |
+
"<|Ú|>",
|
| 2354 |
+
"<|Û|>",
|
| 2355 |
+
"<|Ü|>",
|
| 2356 |
+
"<|Ý|>",
|
| 2357 |
+
"<|Þ|>",
|
| 2358 |
+
"<|ß|>",
|
| 2359 |
+
"<|à|>",
|
| 2360 |
+
"<|á|>",
|
| 2361 |
+
"<|â|>",
|
| 2362 |
+
"<|ã|>",
|
| 2363 |
+
"<|ä|>",
|
| 2364 |
+
"<|å|>",
|
| 2365 |
+
"<|æ|>",
|
| 2366 |
+
"<|ç|>",
|
| 2367 |
+
"<|è|>",
|
| 2368 |
+
"<|é|>",
|
| 2369 |
+
"<|ê|>",
|
| 2370 |
+
"<|ë|>",
|
| 2371 |
+
"<|ì|>",
|
| 2372 |
+
"<|í|>",
|
| 2373 |
+
"<|î|>",
|
| 2374 |
+
"<|ï|>",
|
| 2375 |
+
"<|ð|>",
|
| 2376 |
+
"<|ñ|>",
|
| 2377 |
+
"<|ò|>",
|
| 2378 |
+
"<|ó|>",
|
| 2379 |
+
"<|ô|>",
|
| 2380 |
+
"<|õ|>",
|
| 2381 |
+
"<|ö|>",
|
| 2382 |
+
"<|÷|>",
|
| 2383 |
+
"<|ø|>",
|
| 2384 |
+
"<|ù|>",
|
| 2385 |
+
"<|ú|>",
|
| 2386 |
+
"<|û|>",
|
| 2387 |
+
"<|ü|>",
|
| 2388 |
+
"<|ý|>",
|
| 2389 |
+
"<|þ|>",
|
| 2390 |
+
"<|ÿ|>",
|
| 2391 |
+
"<|Ā|>",
|
| 2392 |
+
"<|ā|>",
|
| 2393 |
+
"<|Ă|>",
|
| 2394 |
+
"<|ă|>",
|
| 2395 |
+
"<|Ą|>",
|
| 2396 |
+
"<|ą|>",
|
| 2397 |
+
"<|Ć|>",
|
| 2398 |
+
"<|ć|>",
|
| 2399 |
+
"<|Ĉ|>",
|
| 2400 |
+
"<|ĉ|>",
|
| 2401 |
+
"<|Ċ|>",
|
| 2402 |
+
"<|ċ|>",
|
| 2403 |
+
"<|Č|>",
|
| 2404 |
+
"<|č|>",
|
| 2405 |
+
"<|Ď|>",
|
| 2406 |
+
"<|ď|>",
|
| 2407 |
+
"<|Đ|>",
|
| 2408 |
+
"<|đ|>",
|
| 2409 |
+
"<|Ē|>",
|
| 2410 |
+
"<|ē|>",
|
| 2411 |
+
"<|Ĕ|>",
|
| 2412 |
+
"<|ĕ|>",
|
| 2413 |
+
"<|Ė|>",
|
| 2414 |
+
"<|ė|>",
|
| 2415 |
+
"<|Ę|>",
|
| 2416 |
+
"<|ę|>",
|
| 2417 |
+
"<|Ě|>",
|
| 2418 |
+
"<|ě|>",
|
| 2419 |
+
"<|Ĝ|>",
|
| 2420 |
+
"<|ĝ|>",
|
| 2421 |
+
"<|Ğ|>",
|
| 2422 |
+
"<|ğ|>",
|
| 2423 |
+
"<|Ġ|>",
|
| 2424 |
+
"<|ġ|>",
|
| 2425 |
+
"<|Ģ|>",
|
| 2426 |
+
"<|ģ|>",
|
| 2427 |
+
"<|Ĥ|>",
|
| 2428 |
+
"<|ĥ|>",
|
| 2429 |
+
"<|Ħ|>",
|
| 2430 |
+
"<|ħ|>",
|
| 2431 |
+
"<|Ĩ|>",
|
| 2432 |
+
"<|ĩ|>",
|
| 2433 |
+
"<|Ī|>",
|
| 2434 |
+
"<|ī|>",
|
| 2435 |
+
"<|Ĭ|>",
|
| 2436 |
+
"<|ĭ|>",
|
| 2437 |
+
"<|Į|>",
|
| 2438 |
+
"<|į|>",
|
| 2439 |
+
"<|İ|>",
|
| 2440 |
+
"<|ı|>",
|
| 2441 |
+
"<|IJ|>",
|
| 2442 |
+
"<|ij|>",
|
| 2443 |
+
"<|Ĵ|>",
|
| 2444 |
+
"<|ĵ|>",
|
| 2445 |
+
"<|Ķ|>",
|
| 2446 |
+
"<|ķ|>",
|
| 2447 |
+
"<|ĸ|>",
|
| 2448 |
+
"<|Ĺ|>",
|
| 2449 |
+
"<|ĺ|>",
|
| 2450 |
+
"<|Ļ|>",
|
| 2451 |
+
"<|ļ|>",
|
| 2452 |
+
"<|Ľ|>",
|
| 2453 |
+
"<|ľ|>",
|
| 2454 |
+
"<|Ŀ|>",
|
| 2455 |
+
"<|ŀ|>",
|
| 2456 |
+
"<|Ł|>",
|
| 2457 |
+
"<|ł|>",
|
| 2458 |
+
"<|Ń|>",
|
| 2459 |
+
"<|Ûķ|>",
|
| 2460 |
+
"<|ÛĮ|>",
|
| 2461 |
+
"<|ا|>",
|
| 2462 |
+
"<|ĠØ|>",
|
| 2463 |
+
"<|ÙĪ|>",
|
| 2464 |
+
"<|ÙĨ|>",
|
| 2465 |
+
"<|ر|>",
|
| 2466 |
+
"<|Ú©|>",
|
| 2467 |
+
"<|ĠÙ|>",
|
| 2468 |
+
"<|ت|>",
|
| 2469 |
+
"<|اÙĨ|>",
|
| 2470 |
+
"<|Ûİ|>",
|
| 2471 |
+
"<|د|>",
|
| 2472 |
+
"<|Ùħ|>",
|
| 2473 |
+
"<|Ġب|>",
|
| 2474 |
+
"<|ÛĨ|>",
|
| 2475 |
+
"<|س|>",
|
| 2476 |
+
"<|translate|>",
|
| 2477 |
+
"<|transcribe|>",
|
| 2478 |
+
"<|startoflm|>",
|
| 2479 |
+
"<|startofprev|>",
|
| 2480 |
+
"<|nocaptions|>",
|
| 2481 |
+
"<|notimestamps|>"
|
| 2482 |
+
],
|
| 2483 |
+
"bos_token": "<|endoftext|>",
|
| 2484 |
+
"clean_up_tokenization_spaces": true,
|
| 2485 |
+
"eos_token": "<|endoftext|>",
|
| 2486 |
+
"errors": "replace",
|
| 2487 |
+
"model_max_length": 1024,
|
| 2488 |
+
"pad_token": "<|endoftext|>",
|
| 2489 |
+
"processor_class": "WhisperProcessor",
|
| 2490 |
+
"return_attention_mask": false,
|
| 2491 |
+
"tokenizer_class": "WhisperTokenizer",
|
| 2492 |
+
"unk_token": "<|endoftext|>"
|
| 2493 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|