added text

Browse files

Files changed (7) hide show

data/lang_bpe_500/bpe.model +3 -0
data/lang_bpe_500/lexicon.txt +0 -0
data/lang_bpe_500/lexicon_disambig.txt +0 -0
data/lang_bpe_500/tokens.txt +502 -0
data/lang_bpe_500/unigram_500.model +3 -0
data/lang_bpe_500/unigram_500.vocab +500 -0
data/lang_bpe_500/words.txt +0 -0

data/lang_bpe_500/bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d403566c4bb5ecd4acceb5e77d63f62254d567d881d1b12f7bc88f7042b12391
+size 244849

data/lang_bpe_500/lexicon.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

data/lang_bpe_500/lexicon_disambig.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

data/lang_bpe_500/tokens.txt ADDED Viewed

	@@ -0,0 +1,502 @@

+<blk> 0
+<sos/eos> 1
+<unk> 2
+S 3
+▁THE 4
+T 5
+▁A 6
+E 7
+▁AND 8
+ED 9
+D 10
+▁TO 11
+▁OF 12
+N 13
+ING 14
+C 15
+▁IN 16
+Y 17
+O 18
+M 19
+▁I 20
+A 21
+I 22
+▁S 23
+P 24
+▁HE 25
+R 26
+▁ 27
+▁IT 28
+LY 29
+▁WAS 30
+▁F 31
+▁THAT 32
+AR 33
+ER 34
+L 35
+B 36
+' 37
+▁BE 38
+▁YOU 39
+RE 40
+▁FOR 41
+▁RE 42
+▁HIS 43
+LE 44
+OR 45
+AL 46
+U 47
+IN 48
+G 49
+V 50
+▁P 51
+ON 52
+▁WITH 53
+▁C 54
+W 55
+▁E 56
+IT 57
+▁AS 58
+K 59
+▁HAD 60
+EN 61
+▁HER 62
+▁W 63
+ST 64
+▁IS 65
+LL 66
+▁NOT 67
+F 68
+▁SHE 69
+▁BUT 70
+CE 71
+▁SO 72
+TH 73
+TER 74
+▁DE 75
+▁ON 76
+▁ME 77
+H 78
+RI 79
+▁AT 80
+CH 81
+VE 82
+▁ST 83
+SE 84
+IC 85
+IL 86
+ES 87
+▁DO 88
+▁B 89
+▁G 90
+ENT 91
+IR 92
+▁' 93
+UR 94
+ION 95
+▁HIM 96
+NG 97
+▁HAVE 98
+▁NO 99
+▁WE 100
+NE 101
+▁ALL 102
+▁MY 103
+▁THIS 104
+▁SAID 105
+AN 106
+RO 107
+▁GO 108
+LA 109
+▁THEY 110
+CK 111
+▁BY 112
+▁MO 113
+AT 114
+▁FROM 115
+▁WHICH 116
+VER 117
+LO 118
+▁TH 119
+▁CON 120
+▁ONE 121
+RA 122
+AD 123
+▁WERE 124
+▁WHO 125
+▁CA 126
+▁O 127
+▁AN 128
+▁OR 129
+▁BO 130
+▁THERE 131
+LI 132
+▁T 133
+▁MAN 134
+▁SH 135
+▁SU 136
+EL 137
+▁EX 138
+TE 139
+▁WHAT 140
+▁LA 141
+ID 142
+ET 143
+▁TR 144
+ATION 145
+THER 146
+▁WOULD 147
+▁WHEN 148
+OW 149
+▁FA 150
+▁PRO 151
+RY 152
+IS 153
+▁ARE 154
+▁WILL 155
+▁OUT 156
+▁HO 157
+▁MA 158
+PP 159
+AS 160
+▁IF 161
+▁UP 162
+▁BR 163
+▁PA 164
+RU 165
+US 166
+▁K 167
+▁LI 168
+▁SEE 169
+▁HA 170
+▁RO 171
+UT 172
+UN 173
+IGHT 174
+OL 175
+▁PO 176
+PE 177
+▁DR 178
+▁LO 179
+▁THEIR 180
+UL 181
+▁BEEN 182
+TED 183
+ANT 184
+▁UN 185
+▁CH 186
+▁RA 187
+ATE 188
+▁COULD 189
+ISH 190
+▁EN 191
+IVE 192
+▁LE 193
+URE 194
+▁WA 195
+▁YOUR 196
+AM 197
+IG 198
+▁MI 199
+EST 200
+MENT 201
+▁THEM 202
+▁DIS 203
+▁SP 204
+OO 205
+▁KNOW 206
+GE 207
+▁CO 208
+▁SOME 209
+▁US 210
+AIN 211
+▁NE 212
+ENCE 213
+▁TIME 214
+▁INTO 215
+▁MR 216
+▁MORE 217
+▁NOW 218
+▁DID 219
+▁VERY 220
+UND 221
+AGE 222
+ANCE 223
+▁LOOK 224
+▁CAN 225
+▁LIKE 226
+ME 227
+ARD 228
+ITY 229
+KE 230
+IE 231
+TY 232
+▁DI 233
+UGH 234
+LU 235
+▁LITTLE 236
+FF 237
+ABLE 238
+Z 239
+▁ABOUT 240
+▁OTHER 241
+▁BA 242
+FUL 243
+IF 244
+X 245
+▁THAN 246
+OUR 247
+TEN 248
+▁SA 249
+PER 250
+▁AR 251
+▁HAS 252
+▁PRE 253
+▁CHA 254
+▁ANY 255
+▁OVER 256
+▁DA 257
+▁AGAIN 258
+▁DAY 259
+ERS 260
+▁AFTER 261
+▁HU 262
+BLE 263
+▁THEN 264
+NESS 265
+IM 266
+▁HAND 267
+HE 268
+▁WELL 269
+▁COM 270
+IES 271
+IST 272
+▁MAR 273
+▁GOOD 274
+▁GREAT 275
+AND 276
+▁VI 277
+SH 278
+▁ONLY 279
+▁SHOULD 280
+▁PU 281
+DER 282
+ROW 283
+▁UPON 284
+▁COME 285
+▁SAY 286
+▁GA 287
+▁DOWN 288
+▁TWO 289
+▁MUST 290
+▁DON 291
+OUS 292
+IOUS 293
+▁BEFORE 294
+▁THINK 295
+▁OUR 296
+▁AM 297
+UM 298
+▁CAR 299
+INE 300
+CTI 301
+▁MADE 302
+▁RI 303
+▁HOW 304
+▁EVERY 305
+▁GRA 306
+▁OLD 307
+FOR 308
+▁NEVER 309
+SIDE 310
+▁EVEN 311
+▁CAME 312
+▁LONG 313
+▁TAKE 314
+WARD 315
+EM 316
+MAN 317
+LESS 318
+LED 319
+▁OFF 320
+▁QU 321
+▁WHERE 322
+AK 323
+▁MUCH 324
+▁BACK 325
+▁SUCH 326
+▁LET 327
+RESS 328
+UD 329
+▁JO 330
+▁PART 331
+▁THOUGHT 332
+▁WAY 333
+▁JUST 334
+J 335
+▁DU 336
+▁FIRST 337
+▁MAY 338
+▁COMP 339
+▁STO 340
+▁BU 341
+▁MAKE 342
+▁WENT 343
+▁TA 344
+GG 345
+▁HIMSELF 346
+▁VA 347
+▁GET 348
+▁OWN 349
+▁GIVE 350
+▁PLACE 351
+▁MEN 352
+▁IMP 353
+▁HERE 354
+▁MIGHT 355
+ATED 356
+▁AWAY 357
+▁HOUSE 358
+▁PER 359
+▁LOVE 360
+▁TURN 361
+HA 362
+TRA 363
+▁TELL 364
+LAND 365
+▁MU 366
+▁THROUGH 367
+▁COL 368
+▁UNDER 369
+▁SHALL 370
+▁LIFE 371
+▁PASS 372
+▁HEAD 373
+▁EYES 374
+QUI 375
+▁NIGHT 376
+▁WITHOUT 377
+▁NOTHING 378
+▁STILL 379
+▁LAST 380
+▁NA 381
+▁FACE 382
+▁WORK 383
+▁MOST 384
+▁NEW 385
+▁TI 386
+▁WANT 387
+▁THOSE 388
+▁MEAN 389
+▁WORD 390
+▁FOUND 391
+▁PEOPLE 392
+▁SAW 393
+▁YES 394
+▁THREE 395
+▁ASKED 396
+▁RIGHT 397
+▁FRIEND 398
+▁ROOM 399
+▁YEAR 400
+▁COUNT 401
+▁HI 402
+▁CHILD 403
+▁WHILE 404
+▁GU 405
+▁ANOTHER 406
+▁FATHER 407
+▁TOOK 408
+▁SEA 409
+▁WHY 410
+▁YET 411
+▁HEART 412
+▁OPEN 413
+▁SAME 414
+▁MOMENT 415
+▁LIGHT 416
+QUE 417
+▁ANSWER 418
+▁SOMETHING 419
+▁THOUGH 420
+PORT 421
+▁LEFT 422
+▁MIND 423
+▁JA 424
+▁SEEMED 425
+▁FIND 426
+▁JU 427
+▁HOME 428
+▁GIRL 429
+▁ALWAYS 430
+▁TOLD 431
+▁QUITE 432
+▁MISS 433
+▁FEEL 434
+▁FOLLOW 435
+▁BECAUSE 436
+▁WORLD 437
+▁FELL 438
+▁NI 439
+▁RETURN 440
+▁WOMAN 441
+▁EACH 442
+IZE 443
+▁KNEW 444
+▁NAME 445
+▁HARD 446
+▁KIND 447
+▁JE 448
+▁CERTAIN 449
+▁HIGH 450
+▁COURSE 451
+▁BETTER 452
+▁PRINCE 453
+▁BEGAN 454
+▁APPEAR 455
+▁HALF 456
+▁FEW 457
+▁ENOUGH 458
+▁SPEAK 459
+▁PRESENT 460
+▁WALK 461
+SHIP 462
+▁CLOSE 463
+▁CRIED 464
+▁KEEP 465
+QUA 466
+▁HELP 467
+▁VOICE 468
+▁LADY 469
+▁TALK 470
+▁ALSO 471
+▁BELIEVE 472
+▁MATTER 473
+▁TEA 474
+▁MORNING 475
+▁REPLIED 476
+▁FELT 477
+▁PERSON 478
+▁MYSELF 479
+▁WHITE 480
+▁HOWEVER 481
+▁POWER 482
+▁POINT 483
+▁SIX 484
+▁ANYTHING 485
+▁PERHAPS 486
+▁STOOD 487
+▁FULL 488
+▁SMALL 489
+▁BETWEEN 490
+▁HERSELF 491
+▁ALMOST 492
+▁HAVING 493
+▁HORSE 494
+▁UNTIL 495
+▁NEXT 496
+▁DARK 497
+▁LEAVE 498
+Q 499
+#0 500
+#1 501

data/lang_bpe_500/unigram_500.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d403566c4bb5ecd4acceb5e77d63f62254d567d881d1b12f7bc88f7042b12391
+size 244849

data/lang_bpe_500/unigram_500.vocab ADDED Viewed

	@@ -0,0 +1,500 @@

+<blk>	0
+<sos/eos>	0
+<unk>	0
+S	-3.26806
+▁THE	-3.42283
+T	-3.813
+▁A	-3.96081
+E	-4.00767
+▁AND	-4.10198
+ED	-4.10752
+D	-4.12778
+▁TO	-4.13935
+▁OF	-4.21424
+N	-4.29763
+ING	-4.32495
+C	-4.49206
+▁IN	-4.49393
+Y	-4.50721
+O	-4.5398
+M	-4.55505
+▁I	-4.61343
+A	-4.64651
+I	-4.68241
+▁S	-4.68567
+P	-4.7061
+▁HE	-4.73438
+R	-4.86263
+▁	-4.86769
+▁IT	-4.94454
+LY	-4.98293
+▁WAS	-5.00383
+▁F	-5.02251
+▁THAT	-5.03573
+AR	-5.04137
+ER	-5.06052
+L	-5.07788
+B	-5.11854
+'	-5.13138
+▁BE	-5.14198
+▁YOU	-5.1913
+RE	-5.21182
+▁FOR	-5.24464
+▁RE	-5.29597
+▁HIS	-5.30207
+LE	-5.31568
+OR	-5.32379
+AL	-5.35531
+U	-5.39444
+IN	-5.40083
+G	-5.40717
+V	-5.41274
+▁P	-5.42113
+ON	-5.4307
+▁WITH	-5.46416
+▁C	-5.46428
+W	-5.50273
+▁E	-5.52695
+IT	-5.53011
+▁AS	-5.5373
+K	-5.54426
+▁HAD	-5.55559
+EN	-5.55738
+▁HER	-5.57448
+▁W	-5.58371
+ST	-5.58655
+▁IS	-5.59221
+LL	-5.59532
+▁NOT	-5.60248
+F	-5.61972
+▁SHE	-5.62417
+▁BUT	-5.62459
+CE	-5.62505
+▁SO	-5.62964
+TH	-5.64812
+TER	-5.65261
+▁DE	-5.67711
+▁ON	-5.69521
+▁ME	-5.70687
+H	-5.71491
+RI	-5.73441
+▁AT	-5.73504
+CH	-5.75188
+VE	-5.79131
+▁ST	-5.81848
+SE	-5.85206
+IC	-5.86505
+IL	-5.87186
+ES	-5.87198
+▁DO	-5.88053
+▁B	-5.88818
+▁G	-5.89388
+ENT	-5.91022
+IR	-5.91173
+▁'	-5.92988
+UR	-5.93499
+ION	-5.93965
+▁HIM	-5.95224
+NG	-5.97099
+▁HAVE	-5.97195
+▁NO	-5.97614
+▁WE	-5.99673
+NE	-6.02958
+▁ALL	-6.0308
+▁MY	-6.04507
+▁THIS	-6.04549
+▁SAID	-6.06664
+AN	-6.08498
+RO	-6.1068
+▁GO	-6.11077
+LA	-6.11969
+▁THEY	-6.12408
+CK	-6.1268
+▁BY	-6.12797
+▁MO	-6.14867
+AT	-6.18214
+▁FROM	-6.19799
+▁WHICH	-6.20941
+VER	-6.21223
+LO	-6.2138
+▁TH	-6.23257
+▁CON	-6.23783
+▁ONE	-6.2451
+RA	-6.24621
+AD	-6.25284
+▁WERE	-6.26026
+▁WHO	-6.26367
+▁CA	-6.27476
+▁O	-6.29608
+▁AN	-6.2968
+▁OR	-6.30646
+▁BO	-6.30784
+▁THERE	-6.31671
+LI	-6.32363
+▁T	-6.33584
+▁MAN	-6.33722
+▁SH	-6.35405
+▁SU	-6.36679
+EL	-6.36696
+▁EX	-6.37253
+TE	-6.37837
+▁WHAT	-6.3806
+▁LA	-6.38184
+ID	-6.39116
+ET	-6.40727
+▁TR	-6.41748
+ATION	-6.43309
+THER	-6.43339
+▁WOULD	-6.45087
+▁WHEN	-6.45319
+OW	-6.45917
+▁FA	-6.47343
+▁PRO	-6.48264
+RY	-6.48452
+IS	-6.49298
+▁ARE	-6.49575
+▁WILL	-6.49933
+▁OUT	-6.50549
+▁HO	-6.51246
+▁MA	-6.51301
+PP	-6.51591
+AS	-6.52566
+▁IF	-6.54186
+▁UP	-6.54568
+▁BR	-6.54914
+▁PA	-6.55753
+RU	-6.56231
+US	-6.56968
+▁K	-6.57229
+▁LI	-6.57593
+▁SEE	-6.58542
+▁HA	-6.59402
+▁RO	-6.60403
+UT	-6.60766
+UN	-6.61445
+IGHT	-6.62267
+OL	-6.62335
+▁PO	-6.62603
+PE	-6.65854
+▁DR	-6.66177
+▁LO	-6.66965
+▁THEIR	-6.6718
+UL	-6.67273
+▁BEEN	-6.67884
+TED	-6.68348
+ANT	-6.68682
+▁UN	-6.68976
+▁CH	-6.68981
+▁RA	-6.69182
+ATE	-6.70168
+▁COULD	-6.72205
+ISH	-6.72792
+▁EN	-6.73452
+IVE	-6.73475
+▁LE	-6.73657
+URE	-6.73786
+▁WA	-6.74014
+▁YOUR	-6.76098
+AM	-6.76754
+IG	-6.77275
+▁MI	-6.77357
+EST	-6.77798
+MENT	-6.78085
+▁THEM	-6.78354
+▁DIS	-6.78413
+▁SP	-6.78506
+OO	-6.80374
+▁KNOW	-6.80656
+GE	-6.81448
+▁CO	-6.81674
+▁SOME	-6.82443
+▁US	-6.82607
+AIN	-6.82894
+▁NE	-6.83446
+ENCE	-6.84007
+▁TIME	-6.85437
+▁INTO	-6.86168
+▁MR	-6.86458
+▁MORE	-6.86717
+▁NOW	-6.86825
+▁DID	-6.87287
+▁VERY	-6.87751
+UND	-6.87989
+AGE	-6.87998
+ANCE	-6.88172
+▁LOOK	-6.88419
+▁CAN	-6.88684
+▁LIKE	-6.88806
+ME	-6.89371
+ARD	-6.89478
+ITY	-6.89845
+KE	-6.90112
+IE	-6.91369
+TY	-6.92013
+▁DI	-6.92874
+UGH	-6.93077
+LU	-6.95036
+▁LITTLE	-6.9534
+FF	-6.95822
+ABLE	-6.97807
+Z	-6.98322
+▁ABOUT	-6.98723
+▁OTHER	-7.00861
+▁BA	-7.01422
+FUL	-7.02129
+IF	-7.02367
+X	-7.02408
+▁THAN	-7.02467
+OUR	-7.02703
+TEN	-7.03367
+▁SA	-7.03609
+PER	-7.04158
+▁AR	-7.04986
+▁HAS	-7.05447
+▁PRE	-7.05909
+▁CHA	-7.06039
+▁ANY	-7.06707
+▁OVER	-7.07182
+▁DA	-7.07201
+▁AGAIN	-7.07811
+▁DAY	-7.08178
+ERS	-7.08196
+▁AFTER	-7.08674
+▁HU	-7.08751
+BLE	-7.08928
+▁THEN	-7.1043
+NESS	-7.13066
+IM	-7.13086
+▁HAND	-7.14218
+HE	-7.14407
+▁WELL	-7.14469
+▁COM	-7.15227
+IES	-7.15232
+IST	-7.15316
+▁MAR	-7.15339
+▁GOOD	-7.15723
+▁GREAT	-7.15827
+AND	-7.15945
+▁VI	-7.16333
+SH	-7.16413
+▁ONLY	-7.16745
+▁SHOULD	-7.16758
+▁PU	-7.18853
+DER	-7.1909
+ROW	-7.19216
+▁UPON	-7.19372
+▁COME	-7.19606
+▁SAY	-7.19859
+▁GA	-7.20234
+▁DOWN	-7.20297
+▁TWO	-7.2241
+▁MUST	-7.22518
+▁DON	-7.22622
+OUS	-7.2298
+IOUS	-7.23203
+▁BEFORE	-7.23398
+▁THINK	-7.251
+▁OUR	-7.25521
+▁AM	-7.25628
+UM	-7.26398
+▁CAR	-7.27245
+INE	-7.27368
+CTI	-7.28001
+▁MADE	-7.28221
+▁RI	-7.28443
+▁HOW	-7.28682
+▁EVERY	-7.2894
+▁GRA	-7.29263
+▁OLD	-7.29531
+FOR	-7.2975
+▁NEVER	-7.30589
+SIDE	-7.30666
+▁EVEN	-7.30948
+▁CAME	-7.31074
+▁LONG	-7.31134
+▁TAKE	-7.31617
+WARD	-7.31822
+EM	-7.322
+MAN	-7.32405
+LESS	-7.32432
+LED	-7.32747
+▁OFF	-7.33562
+▁QU	-7.34481
+▁WHERE	-7.34669
+AK	-7.35585
+▁MUCH	-7.3705
+▁BACK	-7.37705
+▁SUCH	-7.38402
+▁LET	-7.39888
+RESS	-7.40483
+UD	-7.41069
+▁JO	-7.41726
+▁PART	-7.42844
+▁THOUGHT	-7.42913
+▁WAY	-7.43397
+▁JUST	-7.43846
+J	-7.44745
+▁DU	-7.45794
+▁FIRST	-7.46259
+▁MAY	-7.4663
+▁COMP	-7.47137
+▁STO	-7.47201
+▁BU	-7.47236
+▁MAKE	-7.47415
+▁WENT	-7.49227
+▁TA	-7.49738
+GG	-7.51687
+▁HIMSELF	-7.53381
+▁VA	-7.56181
+▁GET	-7.56644
+▁OWN	-7.56698
+▁GIVE	-7.57542
+▁PLACE	-7.58556
+▁MEN	-7.58969
+▁IMP	-7.59723
+▁HERE	-7.6047
+▁MIGHT	-7.60864
+ATED	-7.61064
+▁AWAY	-7.6302
+▁HOUSE	-7.64472
+▁PER	-7.65041
+▁LOVE	-7.65505
+▁TURN	-7.65727
+HA	-7.6584
+TRA	-7.66493
+▁TELL	-7.66498
+LAND	-7.66521
+▁MU	-7.6655
+▁THROUGH	-7.66656
+▁COL	-7.6743
+▁UNDER	-7.68842
+▁SHALL	-7.68955
+▁LIFE	-7.69394
+▁PASS	-7.69628
+▁HEAD	-7.70152
+▁EYES	-7.70559
+QUI	-7.70761
+▁NIGHT	-7.70802
+▁WITHOUT	-7.71033
+▁NOTHING	-7.72291
+▁STILL	-7.72669
+▁LAST	-7.72908
+▁NA	-7.73435
+▁FACE	-7.74546
+▁WORK	-7.74883
+▁MOST	-7.76148
+▁NEW	-7.76501
+▁TI	-7.76623
+▁WANT	-7.77113
+▁THOSE	-7.79484
+▁MEAN	-7.79639
+▁WORD	-7.80371
+▁FOUND	-7.8038
+▁PEOPLE	-7.81034
+▁SAW	-7.81393
+▁YES	-7.81724
+▁THREE	-7.82377
+▁ASKED	-7.83325
+▁RIGHT	-7.83442
+▁FRIEND	-7.83855
+▁ROOM	-7.83871
+▁YEAR	-7.83943
+▁COUNT	-7.85149
+▁HI	-7.8555
+▁CHILD	-7.87872
+▁WHILE	-7.8824
+▁GU	-7.88246
+▁ANOTHER	-7.8825
+▁FATHER	-7.88272
+▁TOOK	-7.89486
+▁SEA	-7.90384
+▁WHY	-7.90775
+▁YET	-7.91695
+▁HEART	-7.94612
+▁OPEN	-7.95817
+▁SAME	-7.95956
+▁MOMENT	-7.96006
+▁LIGHT	-7.96712
+QUE	-7.96757
+▁ANSWER	-7.97163
+▁SOMETHING	-7.98098
+▁THOUGH	-7.98355
+PORT	-7.99375
+▁LEFT	-7.99597
+▁MIND	-8.00434
+▁JA	-8.00689
+▁SEEMED	-8.01776
+▁FIND	-8.01953
+▁JU	-8.02428
+▁HOME	-8.0243
+▁GIRL	-8.03381
+▁ALWAYS	-8.0504
+▁TOLD	-8.06496
+▁QUITE	-8.08052
+▁MISS	-8.08465
+▁FEEL	-8.10786
+▁FOLLOW	-8.10943
+▁BECAUSE	-8.1137
+▁WORLD	-8.11371
+▁FELL	-8.13055
+▁NI	-8.13072
+▁RETURN	-8.13535
+▁WOMAN	-8.16652
+▁EACH	-8.16927
+IZE	-8.17198
+▁KNEW	-8.17494
+▁NAME	-8.18323
+▁HARD	-8.18558
+▁KIND	-8.18658
+▁JE	-8.19761
+▁CERTAIN	-8.1979
+▁HIGH	-8.20291
+▁COURSE	-8.20579
+▁BETTER	-8.21754
+▁PRINCE	-8.23008
+▁BEGAN	-8.23353
+▁APPEAR	-8.23782
+▁HALF	-8.24407
+▁FEW	-8.24769
+▁ENOUGH	-8.25151
+▁SPEAK	-8.25516
+▁PRESENT	-8.26869
+▁WALK	-8.2744
+SHIP	-8.27843
+▁CLOSE	-8.27987
+▁CRIED	-8.28029
+▁KEEP	-8.28141
+QUA	-8.29094
+▁HELP	-8.30047
+▁VOICE	-8.30528
+▁LADY	-8.30616
+▁TALK	-8.31383
+▁ALSO	-8.31665
+▁BELIEVE	-8.31816
+▁MATTER	-8.32356
+▁TEA	-8.33231
+▁MORNING	-8.33475
+▁REPLIED	-8.3376
+▁FELT	-8.33762
+▁PERSON	-8.34054
+▁MYSELF	-8.35343
+▁WHITE	-8.35416
+▁HOWEVER	-8.35935
+▁POWER	-8.36233
+▁POINT	-8.36735
+▁SIX	-8.37947
+▁ANYTHING	-8.38454
+▁PERHAPS	-8.38773
+▁STOOD	-8.39033
+▁FULL	-8.40071
+▁SMALL	-8.40632
+▁BETWEEN	-8.40668
+▁HERSELF	-8.41013
+▁ALMOST	-8.41127
+▁HAVING	-8.41434
+▁HORSE	-8.42195
+▁UNTIL	-8.42869
+▁NEXT	-8.44022
+▁DARK	-8.44185
+▁LEAVE	-8.44386
+Q	-9.55468

data/lang_bpe_500/words.txt ADDED Viewed

The diff for this file is too large to render. See raw diff