wgb14's picture
Upload data/lang_bpe_500/unigram_500.vocab
21e4de8
<blk> 0
<sos/eos> 0
<unk> 0
S -2.91936
T -3.62226
▁THE -3.63907
▁A -3.91998
E -3.9774
▁AND -4.03888
▁TO -4.11528
N -4.13926
D -4.23828
▁OF -4.26126
' -4.32705
ING -4.36266
▁I -4.43026
Y -4.47664
▁IN -4.5039
ED -4.56388
▁THAT -4.56493
-4.61161
P -4.68867
R -4.69194
▁YOU -4.70013
M -4.73468
RE -4.77896
ER -4.79222
C -4.80441
O -4.84437
▁IT -4.84599
L -4.92876
A -5.01304
U -5.04339
G -5.07981
▁WE -5.15716
▁IS -5.16592
▁SO -5.20473
AL -5.20761
I -5.20892
▁S -5.21941
▁RE -5.25961
AR -5.26464
B -5.27126
▁FOR -5.28788
▁C -5.28918
▁BE -5.30209
LE -5.3038
F -5.31727
W -5.3626
▁E -5.39058
▁HE -5.3984
LL -5.39936
▁WAS -5.41947
LY -5.41982
OR -5.451
IN -5.51245
▁F -5.51686
VE -5.54551
▁THIS -5.54604
TH -5.55438
K -5.59782
▁ON -5.60492
IT -5.63051
▁B -5.64315
▁WITH -5.6692
▁BUT -5.69372
EN -5.69464
CE -5.70105
RI -5.74079
▁DO -5.75023
UR -5.75089
▁HAVE -5.75784
▁DE -5.78198
▁ME -5.78744
▁T -5.79218
ENT -5.84937
CH -5.86931
▁THEY -5.8741
▁NOT -5.88022
ES -5.90245
V -5.90528
▁AS -5.90745
RA -5.91436
▁P -5.91784
ON -5.91788
TER -5.92587
▁ARE -5.94781
▁WHAT -5.95664
IC -5.96785
▁ST -5.97911
▁LIKE -6.02232
ATION -6.04962
▁OR -6.05223
▁CA -6.05876
▁AT -6.0815
H -6.08965
▁KNOW -6.09389
▁G -6.09914
AN -6.10082
▁CON -6.1086
IL -6.12259
ND -6.12748
RO -6.13926
▁HIS -6.1401
▁CAN -6.14445
▁ALL -6.14626
TE -6.15654
▁THERE -6.16263
▁SU -6.18963
▁MO -6.19822
▁MA -6.21735
LI -6.24568
▁ONE -6.25177
▁ABOUT -6.253
LA -6.25309
▁CO -6.25588
- -6.26085
▁MY -6.27134
▁HAD -6.2739
CK -6.27737
NG -6.2891
▁NO -6.29472
MENT -6.30738
AD -6.31071
LO -6.31339
ME -6.3139
▁AN -6.31782
▁FROM -6.3267
NE -6.32822
▁IF -6.3309
VER -6.33734
▁JUST -6.34705
▁PRO -6.38157
ION -6.38203
▁PA -6.38311
▁WHO -6.389
▁SE -6.39145
EL -6.39577
IR -6.39902
▁US -6.40366
▁UP -6.40929
▁YOUR -6.41111
CI -6.41571
RY -6.42878
▁GO -6.43225
▁SHE -6.44576
▁LE -6.45467
▁OUT -6.4618
▁PO -6.46959
▁HO -6.47283
ATE -6.48248
▁BO -6.48598
▁BY -6.48743
▁FA -6.48779
▁MI -6.48972
AS -6.49552
MP -6.50825
▁HER -6.51444
VI -6.51584
▁THINK -6.51821
▁SOME -6.51966
▁WHEN -6.53955
▁AH -6.54789
▁PEOPLE -6.56579
IG -6.56619
▁WA -6.58446
▁TE -6.58708
▁LA -6.5924
▁WERE -6.59558
▁LI -6.59617
▁WOULD -6.60333
▁SEE -6.60421
▁WHICH -6.60769
DE -6.61146
GE -6.61214
▁K -6.61725
IGHT -6.63987
▁HA -6.64097
▁OUR -6.67441
UN -6.67953
▁HOW -6.68709
▁GET -6.6874
IS -6.69453
UT -6.70334
Z -6.70922
CO -6.71316
ET -6.71592
UL -6.71664
IES -6.72788
IVE -6.73038
AT -6.73107
▁O -6.73302
▁DON -6.73526
LU -6.73936
▁TIME -6.74787
▁WILL -6.75714
▁MORE -6.75772
▁SP -6.75795
▁NOW -6.76281
RU -6.76441
▁THEIR -6.76701
▁UN -6.77337
ITY -6.78846
OL -6.78991
X -6.79216
TI -6.79565
US -6.79815
▁VERY -6.81318
TION -6.81516
▁FI -6.81739
▁SAY -6.81764
▁BECAUSE -6.83879
▁EX -6.83974
▁RO -6.84322
ERS -6.8685
IST -6.87091
▁DA -6.87303
TING -6.87408
▁EN -6.88514
OM -6.88529
▁BA -6.8895
▁BEEN -6.89199
▁LO -6.89575
▁UM -6.89988
AGE -6.9046
ABLE -6.90556
▁WO -6.90762
▁RA -6.90807
▁OTHER -6.92762
▁REALLY -6.92772
ENCE -6.93464
▁GOING -6.93644
▁HIM -6.93782
▁HAS -6.9382
▁THEM -6.93852
▁DIS -6.94051
▁WANT -6.94824
ID -6.95197
TA -6.95466
▁LOOK -6.95859
KE -6.96683
▁DID -6.96973
▁SA -6.97504
▁VI -6.97815
▁SAID -6.98116
▁RIGHT -6.98233
▁THESE -6.98239
▁WORK -6.98267
▁COM -7.00591
ALLY -7.02101
FF -7.02191
QU -7.02982
AC -7.032
▁DR -7.03706
▁WAY -7.03766
▁INTO -7.04973
MO -7.05136
TED -7.05518
EST -7.06036
▁HERE -7.06279
OK -7.06659
▁COULD -7.07484
▁WELL -7.07681
MA -7.0798
▁PRE -7.08375
▁DI -7.08411
MAN -7.09183
▁COMP -7.09251
▁THEN -7.09311
IM -7.09454
▁PER -7.09471
▁NA -7.09814
▁WHERE -7.0995
▁TWO -7.10374
▁WI -7.10433
▁FE -7.12258
INE -7.13542
▁ANY -7.13685
TURE -7.13787
▁OVER -7.13806
BO -7.1436
ACH -7.15075
OW -7.16294
▁MAKE -7.16967
▁TRA -7.17924
HE -7.19414
UND -7.19438
▁EVEN -7.1973
ANCE -7.19936
▁YEAR -7.20074
HO -7.20126
AM -7.20803
▁CHA -7.20944
▁BACK -7.21247
VO -7.22034
ANT -7.24148
DI -7.24414
▁ALSO -7.24441
▁THOSE -7.2492
▁MAN -7.25828
CTION -7.25994
ICAL -7.27095
▁JO -7.27522
▁OP -7.27657
▁NEW -7.28026
▁MU -7.28457
▁HU -7.28719
▁KIND -7.29056
▁NE -7.29057
CA -7.29455
END -7.29991
TIC -7.30338
FUL -7.308
▁YEAH -7.30971
SH -7.31052
▁APP -7.31863
▁THINGS -7.31873
SIDE -7.31876
▁GOOD -7.32149
ONE -7.32385
▁TAKE -7.33148
CU -7.33525
▁EVERY -7.33606
▁MEAN -7.33916
▁FIRST -7.35633
OP -7.35807
▁TH -7.35816
▁MUCH -7.36035
▁PART -7.36303
UGH -7.38075
▁COME -7.39025
J -7.40206
▁THAN -7.4027
▁EXP -7.40635
▁AGAIN -7.40638
▁LITTLE -7.4123
MB -7.42061
▁NEED -7.42982
▁TALK -7.42993
IF -7.43499
FOR -7.43685
▁SH -7.43707
ISH -7.43834
▁STA -7.44406
ATED -7.44429
▁GU -7.4457
▁LET -7.44843
IA -7.45208
▁MAR -7.46218
▁DOWN -7.46252
▁DAY -7.46636
▁GA -7.46831
▁SOMETHING -7.47373
▁BU -7.47952
DUC -7.47968
HA -7.48577
▁LOT -7.48964
▁RU -7.49641
▁THOUGH -7.50103
▁GREAT -7.51571
AIN -7.53755
▁THROUGH -7.53814
▁THING -7.5397
OUS -7.54298
▁PRI -7.54663
▁GOT -7.54668
▁SHOULD -7.54854
▁AFTER -7.54887
▁HEAR -7.54921
▁TA -7.5583
▁ONLY -7.56318
▁CHI -7.56667
IOUS -7.58401
▁SHA -7.58711
▁MOST -7.5956
▁ACTUALLY -7.59878
▁START -7.60046
LIC -7.60951
▁VA -7.61021
▁RI -7.6118
DAY -7.61429
IAN -7.6194
▁DOES -7.62247
ROW -7.62941
▁GRA -7.63287
ITION -7.64608
▁MANY -7.6498
▁BEFORE -7.67839
▁GIVE -7.67892
PORT -7.68357
QUI -7.70117
▁LIFE -7.70155
▁WORLD -7.70833
▁PI -7.71249
▁LONG -7.71586
▁THREE -7.72143
IZE -7.72871
NESS -7.73046
▁SHOW -7.73117
PH -7.74408
▁WHY -7.75452
▁QUESTION -7.7659
WARD -7.76633
▁THANK -7.77763
▁PH -7.78092
▁DIFFERENT -7.79798
▁OWN -7.8008
▁FEEL -7.80762
▁MIGHT -7.81212
▁HAPPEN -7.82257
▁MADE -7.82361
▁BRO -7.83505
IBLE -7.83692
▁HI -7.83977
▁STATE -7.8432
▁HAND -7.85373
▁NEVER -7.8582
▁PLACE -7.8697
▁LOVE -7.87056
▁DU -7.87177
▁POINT -7.87926
▁HELP -7.88273
▁COUNT -7.88305
▁STILL -7.88446
▁MR -7.90123
▁FIND -7.90288
▁PERSON -7.92879
▁CAME -7.93
▁SAME -7.95337
▁LAST -7.97701
▁HIGH -7.97875
▁OLD -8.00689
▁UNDER -8.01208
▁FOUR -8.01237
▁AROUND -8.0163
▁SORT -8.0255
▁CHANGE -8.0293
▁YES -8.03364
SHIP -8.04202
▁ANOTHER -8.04909
ATIVE -8.07714
▁FOUND -8.09227
▁JA -8.09351
▁ALWAYS -8.10023
▁NEXT -8.10913
▁TURN -8.11079
▁JU -8.12961
▁SIX -8.13018
▁FACT -8.13809
▁INTEREST -8.14199
▁WORD -8.15103
▁THOUSAND -8.16173
▁HUNDRED -8.19128
▁NUMBER -8.19271
▁IDEA -8.2011
▁PLAN -8.21386
▁COURSE -8.21699
▁SCHOOL -8.22226
▁HOUSE -8.22885
▁TWENTY -8.23354
▁JE -8.23872
▁PLAY -8.2479
▁AWAY -8.25259
▁LEARN -8.25403
▁HARD -8.25523
▁WEEK -8.25715
▁BETTER -8.26711
▁WHILE -8.27626
▁FRIEND -8.28156
▁OKAY -8.28222
▁NINE -8.28927
▁UNDERSTAND -8.30685
▁KEEP -8.30703
▁GONNA -8.30908
▁SYSTEM -8.33115
▁AMERICA -8.33344
▁POWER -8.34085
▁IMPORTANT -8.34508
▁WITHOUT -8.35783
▁MAYBE -8.36369
▁SEVEN -8.36468
▁BETWEEN -8.36808
▁BUILD -8.38309
▁CERTAIN -8.38571
▁PROBLEM -8.40003
▁MONEY -8.40454
▁BELIEVE -8.42698
▁SECOND -8.43244
▁REASON -8.45837
▁TOGETHER -8.49857
▁PUBLIC -8.50598
▁ANYTHING -8.50789
▁SPEAK -8.51154
▁BUSINESS -8.5218
▁EVERYTHING -8.52868
▁CLOSE -8.52921
▁QUITE -8.5317
▁ANSWER -8.5436
▁ENOUGH -8.54754
Q -9.75572