DerivedFunction commited on
Commit
afe7dc7
·
verified ·
1 Parent(s): e5cf9c3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -109
README.md CHANGED
@@ -168,116 +168,115 @@ To generalize well on both the target language and code switching a circulumn is
168
  - Homogenous 25%: Single language + one foreign sentence to learn simple code switching
169
  - Spliced 10%: A foreign sentence is centered between two same-language sentence, with the first sentence's punctuation stripped, and second sentence's forced to be lowercased.
170
  - Mixed 10%: Generic mix of any languages.
171
-
172
-
173
- | lang | train | train % | eval | eval % | all_splits | all_splits % |
174
  | :--- | ---: | ---: | ---: | ---: | ---: | ---: |
175
- | en | 158088 | 2.45% | 2785 | 3.77% | 160873 | 2.46% |
176
- | ru | 125692 | 1.94% | 1915 | 2.59% | 127607 | 1.95% |
177
- | es | 125219 | 1.94% | 1809 | 2.45% | 127028 | 1.94% |
178
- | ja | 125212 | 1.94% | 1786 | 2.42% | 126998 | 1.94% |
179
- | fr | 123594 | 1.91% | 1803 | 2.44% | 125397 | 1.92% |
180
- | de | 121413 | 1.88% | 1714 | 2.32% | 123127 | 1.88% |
181
- | zh | 120667 | 1.87% | 1745 | 2.36% | 122412 | 1.87% |
182
- | pt | 119430 | 1.85% | 1749 | 2.37% | 121179 | 1.85% |
183
- | it | 117478 | 1.82% | 1596 | 2.16% | 119074 | 1.82% |
184
- | ar | 101539 | 1.57% | 1208 | 1.63% | 102747 | 1.57% |
185
- | fi | 100922 | 1.56% | 1490 | 2.02% | 102412 | 1.57% |
186
- | uk | 98233 | 1.52% | 1160 | 1.57% | 99393 | 1.52% |
187
- | pl | 96600 | 1.49% | 1144 | 1.55% | 97744 | 1.50% |
188
- | no | 93851 | 1.45% | 1471 | 1.99% | 95322 | 1.46% |
189
- | hu | 92941 | 1.44% | 1077 | 1.46% | 94018 | 1.44% |
190
- | tr | 92566 | 1.43% | 1053 | 1.42% | 93619 | 1.43% |
191
- | nl | 91431 | 1.41% | 1067 | 1.44% | 92498 | 1.41% |
192
- | he | 91496 | 1.42% | 832 | 1.13% | 92328 | 1.41% |
193
- | cs | 91275 | 1.41% | 989 | 1.34% | 92264 | 1.41% |
194
- | da | 87309 | 1.35% | 1223 | 1.65% | 88532 | 1.35% |
195
- | lt | 86897 | 1.34% | 935 | 1.26% | 87832 | 1.34% |
196
- | mk | 85658 | 1.33% | 824 | 1.11% | 86482 | 1.32% |
197
- | eo | 83778 | 1.30% | 794 | 1.07% | 84572 | 1.29% |
198
- | mr | 83264 | 1.29% | 744 | 1.01% | 84008 | 1.28% |
199
- | ko | 81829 | 1.27% | 1005 | 1.36% | 82834 | 1.27% |
200
- | hi | 81659 | 1.26% | 979 | 1.32% | 82638 | 1.26% |
201
- | tl | 79985 | 1.24% | 966 | 1.31% | 80951 | 1.24% |
202
- | hy | 76909 | 1.19% | 735 | 0.99% | 77644 | 1.19% |
203
- | el | 75369 | 1.17% | 728 | 0.98% | 76097 | 1.16% |
204
- | ro | 73559 | 1.14% | 763 | 1.03% | 74322 | 1.14% |
205
- | is | 72356 | 1.12% | 987 | 1.34% | 73343 | 1.12% |
206
- | sk | 71990 | 1.11% | 858 | 1.16% | 72848 | 1.11% |
207
- | la | 70651 | 1.09% | 745 | 1.01% | 71396 | 1.09% |
208
- | be | 70521 | 1.09% | 867 | 1.17% | 71388 | 1.09% |
209
- | fa | 70584 | 1.09% | 717 | 0.97% | 71301 | 1.09% |
210
- | bg | 69684 | 1.08% | 673 | 0.91% | 70357 | 1.08% |
211
- | lv | 67627 | 1.05% | 691 | 0.93% | 68318 | 1.04% |
212
- | ms | 66271 | 1.03% | 770 | 1.04% | 67041 | 1.03% |
213
- | af | 64699 | 1.00% | 982 | 1.33% | 65681 | 1.00% |
214
- | ckb | 64368 | 1.00% | 587 | 0.79% | 64955 | 0.99% |
215
- | kk | 63640 | 0.98% | 621 | 0.84% | 64261 | 0.98% |
216
- | eu | 63398 | 0.98% | 673 | 0.91% | 64071 | 0.98% |
217
- | ka | 63201 | 0.98% | 523 | 0.71% | 63724 | 0.97% |
218
- | mn | 62551 | 0.97% | 641 | 0.87% | 63192 | 0.97% |
219
- | hr | 62427 | 0.97% | 711 | 0.96% | 63138 | 0.97% |
220
- | oc | 62292 | 0.96% | 661 | 0.89% | 62953 | 0.96% |
221
- | id | 62134 | 0.96% | 732 | 0.99% | 62866 | 0.96% |
222
- | ky | 61634 | 0.95% | 637 | 0.86% | 62271 | 0.95% |
223
- | ba | 61637 | 0.95% | 584 | 0.79% | 62221 | 0.95% |
224
- | ur | 61550 | 0.95% | 578 | 0.78% | 62128 | 0.95% |
225
- | th | 60731 | 0.94% | 576 | 0.78% | 61307 | 0.94% |
226
- | bn | 60588 | 0.94% | 415 | 0.56% | 61003 | 0.93% |
227
- | ps | 60342 | 0.93% | 533 | 0.72% | 60875 | 0.93% |
228
- | sv | 59918 | 0.93% | 937 | 1.27% | 60855 | 0.93% |
229
- | tt | 60177 | 0.93% | 634 | 0.86% | 60811 | 0.93% |
230
- | pa | 60137 | 0.93% | 599 | 0.81% | 60736 | 0.93% |
231
- | sw | 60148 | 0.93% | 558 | 0.75% | 60706 | 0.93% |
232
- | kn | 60037 | 0.93% | 631 | 0.85% | 60668 | 0.93% |
233
- | as | 59839 | 0.93% | 374 | 0.51% | 60213 | 0.92% |
234
- | cy | 58188 | 0.90% | 655 | 0.89% | 58843 | 0.90% |
235
- | jv | 57805 | 0.89% | 508 | 0.69% | 58313 | 0.89% |
236
- | bs | 57399 | 0.89% | 655 | 0.89% | 58054 | 0.89% |
237
- | ga | 57233 | 0.89% | 672 | 0.91% | 57905 | 0.89% |
238
- | ca | 56547 | 0.87% | 606 | 0.82% | 57153 | 0.87% |
239
- | gl | 55312 | 0.86% | 577 | 0.78% | 55889 | 0.85% |
240
- | sl | 55017 | 0.85% | 598 | 0.81% | 55615 | 0.85% |
241
- | ku | 54674 | 0.85% | 537 | 0.73% | 55211 | 0.84% |
242
- | ne | 54102 | 0.84% | 440 | 0.60% | 54542 | 0.83% |
243
- | uz | 53777 | 0.83% | 507 | 0.69% | 54284 | 0.83% |
244
- | tg | 50762 | 0.79% | 502 | 0.68% | 51264 | 0.78% |
245
- | br | 49263 | 0.76% | 554 | 0.75% | 49817 | 0.76% |
246
- | et | 49249 | 0.76% | 511 | 0.69% | 49760 | 0.76% |
247
- | lb | 48192 | 0.75% | 492 | 0.67% | 48684 | 0.74% |
248
- | su | 48185 | 0.75% | 480 | 0.65% | 48665 | 0.74% |
249
- | mt | 47694 | 0.74% | 446 | 0.60% | 48140 | 0.74% |
250
- | sr | 47385 | 0.73% | 458 | 0.62% | 47843 | 0.73% |
251
- | sq | 45528 | 0.70% | 514 | 0.70% | 46042 | 0.70% |
252
- | ml | 43461 | 0.67% | 429 | 0.58% | 43890 | 0.67% |
253
- | or | 41301 | 0.64% | 413 | 0.56% | 41714 | 0.64% |
254
- | te | 40065 | 0.62% | 381 | 0.52% | 40446 | 0.62% |
255
- | yi | 38484 | 0.60% | 353 | 0.48% | 38837 | 0.59% |
256
- | ta | 35897 | 0.56% | 378 | 0.51% | 36275 | 0.55% |
257
- | mg | 35133 | 0.54% | 342 | 0.46% | 35475 | 0.54% |
258
- | si | 34611 | 0.54% | 343 | 0.46% | 34954 | 0.53% |
259
- | gu | 29347 | 0.45% | 298 | 0.40% | 29645 | 0.45% |
260
- | vi | 28448 | 0.44% | 329 | 0.45% | 28777 | 0.44% |
261
- | rm | 27668 | 0.43% | 252 | 0.34% | 27920 | 0.43% |
262
- | bo | 25636 | 0.40% | 217 | 0.29% | 25853 | 0.40% |
263
- | ug | 23932 | 0.37% | 213 | 0.29% | 24145 | 0.37% |
264
- | dv | 22580 | 0.35% | 204 | 0.28% | 22784 | 0.35% |
265
- | am | 22498 | 0.35% | 227 | 0.31% | 22725 | 0.35% |
266
- | yo | 22441 | 0.35% | 229 | 0.31% | 22670 | 0.35% |
267
- | my | 21832 | 0.34% | 210 | 0.28% | 22042 | 0.34% |
268
- | so | 21058 | 0.33% | 201 | 0.27% | 21259 | 0.33% |
269
- | km | 21064 | 0.33% | 187 | 0.25% | 21251 | 0.33% |
270
- | sd | 20471 | 0.32% | 199 | 0.27% | 20670 | 0.32% |
271
- | zu | 19688 | 0.30% | 186 | 0.25% | 19874 | 0.30% |
272
- | lo | 18555 | 0.29% | 188 | 0.25% | 18743 | 0.29% |
273
- | ti | 18116 | 0.28% | 193 | 0.26% | 18309 | 0.28% |
274
- | ce | 16789 | 0.26% | 181 | 0.24% | 16970 | 0.26% |
275
- | ny | 16544 | 0.26% | 159 | 0.22% | 16703 | 0.26% |
276
- | gd | 14012 | 0.22% | 142 | 0.19% | 14154 | 0.22% |
277
- | xh | 9373 | 0.15% | 96 | 0.13% | 9469 | 0.14% |
278
- | om | 6113 | 0.09% | 55 | 0.07% | 6168 | 0.09% |
279
- | sco | 3362 | 0.05% | 30 | 0.04% | 3392 | 0.05% |
280
- | **total** | 6463786 | 100.00% | 73931 | 100.00% | 6537717 | 100.00% |
 
281
 
282
 
283
 
 
168
  - Homogenous 25%: Single language + one foreign sentence to learn simple code switching
169
  - Spliced 10%: A foreign sentence is centered between two same-language sentence, with the first sentence's punctuation stripped, and second sentence's forced to be lowercased.
170
  - Mixed 10%: Generic mix of any languages.
171
+ | lang | train sentences | train tokens | eval sentences | eval tokens | all sentences | all tokens |
 
 
172
  | :--- | ---: | ---: | ---: | ---: | ---: | ---: |
173
+ | en | 342138 (2.14%) | 8515554 (1.58%) | 2925 (3.89%) | 29279 (1.57%) | 345063 (2.14%) | 8544833 (1.58%) |
174
+ | es | 290248 (1.81%) | 8250416 (1.53%) | 1864 (2.48%) | 19826 (1.06%) | 292112 (1.82%) | 8270242 (1.53%) |
175
+ | ru | 289806 (1.81%) | 7911565 (1.47%) | 1963 (2.61%) | 19501 (1.04%) | 291769 (1.81%) | 7931066 (1.47%) |
176
+ | ja | 288677 (1.80%) | 6935500 (1.29%) | 1836 (2.44%) | 20115 (1.08%) | 290513 (1.81%) | 6955615 (1.29%) |
177
+ | fr | 285022 (1.78%) | 8950594 (1.66%) | 1849 (2.46%) | 22785 (1.22%) | 286871 (1.78%) | 8973379 (1.66%) |
178
+ | zh | 282136 (1.76%) | 6585294 (1.22%) | 1780 (2.37%) | 17110 (0.92%) | 283916 (1.76%) | 6602404 (1.22%) |
179
+ | de | 279766 (1.75%) | 7421366 (1.38%) | 1761 (2.34%) | 20090 (1.08%) | 281527 (1.75%) | 7441456 (1.37%) |
180
+ | pt | 277705 (1.73%) | 7518951 (1.39%) | 1789 (2.38%) | 16872 (0.90%) | 279494 (1.74%) | 7535823 (1.39%) |
181
+ | it | 274463 (1.71%) | 7647936 (1.42%) | 1641 (2.18%) | 14284 (0.77%) | 276104 (1.72%) | 7662220 (1.42%) |
182
+ | uk | 244679 (1.53%) | 6480580 (1.20%) | 1187 (1.58%) | 9893 (0.53%) | 245866 (1.53%) | 6490473 (1.20%) |
183
+ | fi | 243388 (1.52%) | 5886670 (1.09%) | 1521 (2.02%) | 14613 (0.78%) | 244909 (1.52%) | 5901283 (1.09%) |
184
+ | ar | 243319 (1.52%) | 5055410 (0.94%) | 1237 (1.65%) | 18277 (0.98%) | 244556 (1.52%) | 5073687 (0.94%) |
185
+ | pl | 239763 (1.50%) | 6747779 (1.25%) | 1162 (1.55%) | 11588 (0.62%) | 240925 (1.50%) | 6759367 (1.25%) |
186
+ | he | 235680 (1.47%) | 6872873 (1.27%) | 842 (1.12%) | 7301 (0.39%) | 236522 (1.47%) | 6880174 (1.27%) |
187
+ | hu | 234082 (1.46%) | 6422364 (1.19%) | 1093 (1.45%) | 10598 (0.57%) | 235175 (1.46%) | 6432962 (1.19%) |
188
+ | tr | 231785 (1.45%) | 5649577 (1.05%) | 1078 (1.43%) | 9102 (0.49%) | 232863 (1.45%) | 5658679 (1.05%) |
189
+ | cs | 229623 (1.43%) | 6157905 (1.14%) | 1010 (1.34%) | 8638 (0.46%) | 230633 (1.43%) | 6166543 (1.14%) |
190
+ | nl | 227744 (1.42%) | 5208953 (0.97%) | 1086 (1.45%) | 9966 (0.53%) | 228830 (1.42%) | 5218919 (0.96%) |
191
+ | lt | 220746 (1.38%) | 5523460 (1.02%) | 953 (1.27%) | 8390 (0.45%) | 221699 (1.38%) | 5531850 (1.02%) |
192
+ | mk | 219568 (1.37%) | 6321823 (1.17%) | 830 (1.10%) | 7363 (0.39%) | 220398 (1.37%) | 6329186 (1.17%) |
193
+ | mr | 218564 (1.36%) | 5737670 (1.06%) | 755 (1.00%) | 6419 (0.34%) | 219319 (1.36%) | 5744089 (1.06%) |
194
+ | eo | 214879 (1.34%) | 5575371 (1.03%) | 806 (1.07%) | 9199 (0.49%) | 215685 (1.34%) | 5584570 (1.03%) |
195
+ | no | 212572 (1.33%) | 6119841 (1.13%) | 1520 (2.02%) | 46805 (2.51%) | 214092 (1.33%) | 6166646 (1.14%) |
196
+ | da | 210913 (1.32%) | 5244616 (0.97%) | 1244 (1.66%) | 11307 (0.61%) | 212157 (1.32%) | 5255923 (0.97%) |
197
+ | tl | 198531 (1.24%) | 5385091 (1.00%) | 980 (1.30%) | 11451 (0.61%) | 199511 (1.24%) | 5396542 (1.00%) |
198
+ | hy | 197579 (1.23%) | 6260512 (1.16%) | 741 (0.99%) | 14164 (0.76%) | 198320 (1.23%) | 6274676 (1.16%) |
199
+ | hi | 196290 (1.23%) | 7473616 (1.39%) | 995 (1.32%) | 43438 (2.33%) | 197285 (1.23%) | 7517054 (1.39%) |
200
+ | ko | 196247 (1.23%) | 6256562 (1.16%) | 1021 (1.36%) | 28154 (1.51%) | 197268 (1.23%) | 6284716 (1.16%) |
201
+ | el | 192981 (1.21%) | 7010969 (1.30%) | 739 (0.98%) | 17209 (0.92%) | 193720 (1.20%) | 7028178 (1.30%) |
202
+ | ro | 185669 (1.16%) | 6171646 (1.14%) | 771 (1.03%) | 21626 (1.16%) | 186440 (1.16%) | 6193272 (1.14%) |
203
+ | fa | 182012 (1.14%) | 5634518 (1.04%) | 724 (0.96%) | 21266 (1.14%) | 182736 (1.14%) | 5655784 (1.04%) |
204
+ | sk | 181257 (1.13%) | 5323589 (0.99%) | 868 (1.16%) | 30324 (1.62%) | 182125 (1.13%) | 5353913 (0.99%) |
205
+ | la | 178735 (1.12%) | 4452161 (0.83%) | 752 (1.00%) | 7803 (0.42%) | 179487 (1.12%) | 4459964 (0.82%) |
206
+ | bg | 178477 (1.11%) | 5772043 (1.07%) | 681 (0.91%) | 18306 (0.98%) | 179158 (1.11%) | 5790349 (1.07%) |
207
+ | is | 174213 (1.09%) | 6024579 (1.12%) | 1005 (1.34%) | 47601 (2.55%) | 175218 (1.09%) | 6072180 (1.12%) |
208
+ | be | 174166 (1.09%) | 6368950 (1.18%) | 880 (1.17%) | 30097 (1.61%) | 175046 (1.09%) | 6399047 (1.18%) |
209
+ | lv | 170404 (1.06%) | 5706364 (1.06%) | 702 (0.93%) | 35541 (1.90%) | 171106 (1.06%) | 5741905 (1.06%) |
210
+ | ckb | 166543 (1.04%) | 7530043 (1.40%) | 591 (0.79%) | 25103 (1.35%) | 167134 (1.04%) | 7555146 (1.40%) |
211
+ | ms | 165285 (1.03%) | 4430830 (0.82%) | 778 (1.04%) | 24919 (1.34%) | 166063 (1.03%) | 4455749 (0.82%) |
212
+ | kk | 163582 (1.02%) | 4925313 (0.91%) | 629 (0.84%) | 17536 (0.94%) | 164211 (1.02%) | 4942849 (0.91%) |
213
+ | ka | 162558 (1.02%) | 5244466 (0.97%) | 527 (0.70%) | 16440 (0.88%) | 163085 (1.01%) | 5260906 (0.97%) |
214
+ | bn | 162058 (1.01%) | 6155732 (1.14%) | 416 (0.55%) | 14535 (0.78%) | 162474 (1.01%) | 6170267 (1.14%) |
215
+ | eu | 160479 (1.00%) | 5375791 (1.00%) | 675 (0.90%) | 34708 (1.86%) | 161154 (1.00%) | 5410499 (1.00%) |
216
+ | as | 160525 (1.00%) | 8228319 (1.53%) | 377 (0.50%) | 20723 (1.11%) | 160902 (1.00%) | 8249042 (1.52%) |
217
+ | mn | 160161 (1.00%) | 5433430 (1.01%) | 645 (0.86%) | 19610 (1.05%) | 160806 (1.00%) | 5453040 (1.01%) |
218
+ | ur | 158216 (0.99%) | 5101965 (0.95%) | 582 (0.77%) | 19433 (1.04%) | 158798 (0.99%) | 5121398 (0.95%) |
219
+ | ky | 157623 (0.98%) | 4996516 (0.93%) | 640 (0.85%) | 18469 (0.99%) | 158263 (0.98%) | 5014985 (0.93%) |
220
+ | ba | 157391 (0.98%) | 7998542 (1.48%) | 591 (0.79%) | 30781 (1.65%) | 157982 (0.98%) | 8029323 (1.48%) |
221
+ | oc | 157265 (0.98%) | 5676181 (1.05%) | 669 (0.89%) | 25130 (1.35%) | 157934 (0.98%) | 5701311 (1.05%) |
222
+ | th | 156439 (0.98%) | 5222662 (0.97%) | 579 (0.77%) | 20033 (1.07%) | 157018 (0.98%) | 5242695 (0.97%) |
223
+ | hr | 156094 (0.97%) | 4838805 (0.90%) | 716 (0.95%) | 31608 (1.69%) | 156810 (0.97%) | 4870413 (0.90%) |
224
+ | af | 155450 (0.97%) | 4536957 (0.84%) | 995 (1.32%) | 29783 (1.60%) | 156445 (0.97%) | 4566740 (0.84%) |
225
+ | ps | 155591 (0.97%) | 4514560 (0.84%) | 537 (0.71%) | 15173 (0.81%) | 156128 (0.97%) | 4529733 (0.84%) |
226
+ | id | 154998 (0.97%) | 4010110 (0.74%) | 737 (0.98%) | 18766 (1.01%) | 155735 (0.97%) | 4028876 (0.74%) |
227
+ | pa | 155053 (0.97%) | 7277866 (1.35%) | 602 (0.80%) | 29831 (1.60%) | 155655 (0.97%) | 7307697 (1.35%) |
228
+ | sw | 154323 (0.96%) | 4695422 (0.87%) | 562 (0.75%) | 20760 (1.11%) | 154885 (0.96%) | 4716182 (0.87%) |
229
+ | tt | 152959 (0.96%) | 5329166 (0.99%) | 642 (0.85%) | 9018 (0.48%) | 153601 (0.95%) | 5338184 (0.99%) |
230
+ | jv | 149846 (0.94%) | 4508978 (0.84%) | 512 (0.68%) | 18744 (1.00%) | 150358 (0.93%) | 4527722 (0.84%) |
231
+ | cy | 147138 (0.92%) | 5344455 (0.99%) | 664 (0.88%) | 27600 (1.48%) | 147802 (0.92%) | 5372055 (0.99%) |
232
+ | ga | 144559 (0.90%) | 5145701 (0.95%) | 681 (0.91%) | 28351 (1.52%) | 145240 (0.90%) | 5174052 (0.96%) |
233
+ | bs | 142871 (0.89%) | 4246487 (0.79%) | 664 (0.88%) | 23293 (1.25%) | 143535 (0.89%) | 4269780 (0.79%) |
234
+ | ca | 142813 (0.89%) | 5286099 (0.98%) | 614 (0.82%) | 20417 (1.09%) | 143427 (0.89%) | 5306516 (0.98%) |
235
+ | kn | 142453 (0.89%) | 14440106 (2.68%) | 636 (0.85%) | 48433 (2.60%) | 143089 (0.89%) | 14488539 (2.68%) |
236
+ | ne | 141617 (0.88%) | 4633072 (0.86%) | 441 (0.59%) | 13357 (0.72%) | 142058 (0.88%) | 4646429 (0.86%) |
237
+ | gl | 140293 (0.88%) | 4370302 (0.81%) | 580 (0.77%) | 17719 (0.95%) | 140873 (0.88%) | 4388021 (0.81%) |
238
+ | ku | 140150 (0.88%) | 4681613 (0.87%) | 539 (0.72%) | 25315 (1.36%) | 140689 (0.87%) | 4706928 (0.87%) |
239
+ | uz | 137971 (0.86%) | 4402565 (0.82%) | 512 (0.68%) | 18239 (0.98%) | 138483 (0.86%) | 4420804 (0.82%) |
240
+ | sl | 137474 (0.86%) | 3689209 (0.68%) | 602 (0.80%) | 15975 (0.86%) | 138076 (0.86%) | 3705184 (0.68%) |
241
+ | sv | 136227 (0.85%) | 3888997 (0.72%) | 951 (1.27%) | 7503 (0.40%) | 137178 (0.85%) | 3896500 (0.72%) |
242
+ | tg | 129047 (0.81%) | 7212798 (1.34%) | 507 (0.67%) | 30575 (1.64%) | 129554 (0.81%) | 7243373 (1.34%) |
243
+ | et | 125334 (0.78%) | 3134904 (0.58%) | 516 (0.69%) | 13566 (0.73%) | 125850 (0.78%) | 3148470 (0.58%) |
244
+ | br | 124276 (0.78%) | 4304633 (0.80%) | 555 (0.74%) | 16741 (0.90%) | 124831 (0.78%) | 4321374 (0.80%) |
245
+ | su | 123580 (0.77%) | 3996363 (0.74%) | 485 (0.65%) | 18936 (1.01%) | 124065 (0.77%) | 4015299 (0.74%) |
246
+ | lb | 123335 (0.77%) | 4218363 (0.78%) | 494 (0.66%) | 18236 (0.98%) | 123829 (0.77%) | 4236599 (0.78%) |
247
+ | mt | 122262 (0.76%) | 6326484 (1.17%) | 448 (0.60%) | 23893 (1.28%) | 122710 (0.76%) | 6350377 (1.17%) |
248
+ | sr | 121328 (0.76%) | 3374324 (0.63%) | 461 (0.61%) | 4054 (0.22%) | 121789 (0.76%) | 3378378 (0.62%) |
249
+ | sq | 114178 (0.71%) | 3917105 (0.73%) | 519 (0.69%) | 17283 (0.93%) | 114697 (0.71%) | 3934388 (0.73%) |
250
+ | or | 105680 (0.66%) | 3746174 (0.69%) | 415 (0.55%) | 13597 (0.73%) | 106095 (0.66%) | 3759771 (0.69%) |
251
+ | ml | 104847 (0.65%) | 10467180 (1.94%) | 432 (0.58%) | 34289 (1.84%) | 105279 (0.65%) | 10501469 (1.94%) |
252
+ | yi | 99296 (0.62%) | 4037607 (0.75%) | 356 (0.47%) | 7656 (0.41%) | 99652 (0.62%) | 4045263 (0.75%) |
253
+ | te | 96687 (0.60%) | 9339722 (1.73%) | 383 (0.51%) | 32688 (1.75%) | 97070 (0.60%) | 9372410 (1.73%) |
254
+ | ta | 89670 (0.56%) | 7564484 (1.40%) | 378 (0.50%) | 25504 (1.37%) | 90048 (0.56%) | 7589988 (1.40%) |
255
+ | mg | 89513 (0.56%) | 3128095 (0.58%) | 343 (0.46%) | 11046 (0.59%) | 89856 (0.56%) | 3139141 (0.58%) |
256
+ | si | 88038 (0.55%) | 5030862 (0.93%) | 345 (0.46%) | 17895 (0.96%) | 88383 (0.55%) | 5048757 (0.93%) |
257
+ | rm | 71273 (0.45%) | 2704067 (0.50%) | 254 (0.34%) | 10060 (0.54%) | 71527 (0.44%) | 2714127 (0.50%) |
258
+ | vi | 70788 (0.44%) | 2476955 (0.46%) | 333 (0.44%) | 3428 (0.18%) | 71121 (0.44%) | 2480383 (0.46%) |
259
+ | gu | 67542 (0.42%) | 7557129 (1.40%) | 299 (0.40%) | 28080 (1.50%) | 67841 (0.42%) | 7585209 (1.40%) |
260
+ | bo | 66467 (0.42%) | 1308971 (0.24%) | 218 (0.29%) | 4357 (0.23%) | 66685 (0.41%) | 1313328 (0.24%) |
261
+ | ug | 61389 (0.38%) | 1398443 (0.26%) | 213 (0.28%) | 4674 (0.25%) | 61602 (0.38%) | 1403117 (0.26%) |
262
+ | dv | 57776 (0.36%) | 1485603 (0.28%) | 205 (0.27%) | 5705 (0.31%) | 57981 (0.36%) | 1491308 (0.28%) |
263
+ | am | 56487 (0.35%) | 2563835 (0.48%) | 227 (0.30%) | 11582 (0.62%) | 56714 (0.35%) | 2575417 (0.48%) |
264
+ | yo | 56313 (0.35%) | 3444596 (0.64%) | 230 (0.31%) | 18061 (0.97%) | 56543 (0.35%) | 3462657 (0.64%) |
265
+ | my | 55960 (0.35%) | 2062131 (0.38%) | 212 (0.28%) | 8300 (0.44%) | 56172 (0.35%) | 2070431 (0.38%) |
266
+ | km | 53890 (0.34%) | 2889004 (0.54%) | 188 (0.25%) | 9842 (0.53%) | 54078 (0.34%) | 2898846 (0.54%) |
267
+ | so | 53862 (0.34%) | 1963263 (0.36%) | 202 (0.27%) | 7961 (0.43%) | 54064 (0.34%) | 1971224 (0.36%) |
268
+ | sd | 52494 (0.33%) | 3075283 (0.57%) | 200 (0.27%) | 10379 (0.56%) | 52694 (0.33%) | 3085662 (0.57%) |
269
+ | zu | 50081 (0.31%) | 2287742 (0.42%) | 187 (0.25%) | 8913 (0.48%) | 50268 (0.31%) | 2296655 (0.42%) |
270
+ | lo | 47982 (0.30%) | 1659406 (0.31%) | 188 (0.25%) | 5980 (0.32%) | 48170 (0.30%) | 1665386 (0.31%) |
271
+ | ti | 45884 (0.29%) | 2804218 (0.52%) | 193 (0.26%) | 11862 (0.64%) | 46077 (0.29%) | 2816080 (0.52%) |
272
+ | ce | 43040 (0.27%) | 2319707 (0.43%) | 181 (0.24%) | 9398 (0.50%) | 43221 (0.27%) | 2329105 (0.43%) |
273
+ | ny | 41897 (0.26%) | 1969591 (0.37%) | 159 (0.21%) | 8122 (0.44%) | 42056 (0.26%) | 1977713 (0.37%) |
274
+ | gd | 35576 (0.22%) | 1240445 (0.23%) | 142 (0.19%) | 3449 (0.18%) | 35718 (0.22%) | 1243894 (0.23%) |
275
+ | xh | 23590 (0.15%) | 877812 (0.16%) | 96 (0.13%) | 3597 (0.19%) | 23686 (0.15%) | 881409 (0.16%) |
276
+ | om | 14738 (0.09%) | 523551 (0.10%) | 55 (0.07%) | 1935 (0.10%) | 14793 (0.09%) | 525486 (0.10%) |
277
+ | sco | 8374 (0.05%) | 224424 (0.04%) | 30 (0.04%) | 1055 (0.06%) | 8404 (0.05%) | 225479 (0.04%) |
278
+ | **total** | 16012306 (100.00%) | 539378202 (100.00%) | 75126 (100.00%) | 1866305 (100.00%) | 16087432 (100.00%) | 541244507 (100.00%) |
279
+
280
 
281
 
282