uz_tokenizers / uz_tokenizer_1000.vocab
aslon1213's picture
Upload folder using huggingface_hub
1c6a554 verified
<unk> 0
<s> 0
</s> 0
la -0
sh -1
an -2
in -3
da -4
▁b -5
lar -6
li -7
di -8
ar -9
▁t -10
ch -11
▁o -12
ti -13
ma -14
▁q -15
▁k -16
ga -17
on -18
si -19
ri -20
gan -21
▁y -22
▁bo -23
at -24
ing -25
▁h -26
▁a -27
ni -28
il -29
▁m -30
▁s -31
ra -32
▁u -33
shi -34
iy -35
▁e -36
▁v -37
am -38
dan -39
gi -40
ir -41
ta -42
un -43
▁va -44
lari -45
or -46
chi -47
lik -48
cha -49
um -50
ini -51
iz -52
oq -53
ay -54
ning -55
▁ma -56
lan -57
▁sh -58
▁i -59
▁M -60
▁qo -61
▁B -62
ur -63
▁ke -64
ki -65
sa -66
▁A -67
om -68
▁ta -69
▁S -70
ot -71
en -72
▁ko -73
▁d -74
oy -75
al -76
ov -77
er -78
▁x -79
▁O -80
zi -81
▁j -82
▁yo -83
st -84
asi -85
lash -86
ol -87
▁qi -88
ati -89
▁bi -90
▁n -91
ani -92
▁ham -93
▁1 -94
▁( -95
▁2 -96
ida -97
ul -98
▁T -99
lib -100
ab -101
▁f -102
ek -103
lgan -104
▁p -105
▁to -106
ladi -107
ka -108
uv -109
im -110
▁bir -111
▁de -112
▁da -113
siy -114
▁tu -115
tlar -116
▁so -117
aq -118
▁C -119
▁bilan -120
rib -121
ola -122
mon -123
kin -124
▁– -125
av -126
oh -127
af -128
ah -129
ob -130
▁K -131
uz -132
yi -133
ari -134
ining -135
▁Q -136
qa -137
lishi -138
▁tum -139
▁mu -140
▁be -141
qi -142
rish -143
lab -144
▁bu -145
▁tumani -146
.. -147
lish -148
re -149
▁U -150
30 -151
▁bosh -152
as -153
mi -154
adi -155
ldi -156
os -157
dagi -158
▁Y -159
▁uch -160
▁mum -161
▁ch -162
ce -163
▁mumkin -164
▁I -165
oz -166
moq -167
day -168
▁“ -169
ston -170
▁— -171
ak -172
▁ki -173
▁Sh -174
▁ish -175
og -176
mas -177
▁g -178
bat -179
▁H -180
▁N -181
may -182
us -183
tib -184
mal -185
ommon -186
larni -187
lay -188
ligi -189
▁al -190
uq -191
▁ay -192
miz -193
larga -194
zb -195
ax -196
osh -197
▁uchun -198
▁qil -199
▁Bu -200
dir -201
ng -202
▁shar -203
▁chi -204
ril -205
larning -206
od -207
man -208
ub -209
is -210
ash -211
ud -212
ro -213
et -214
ziy -215
vo -216
lashti -217
▁as -218
moqda -219
lit -220
yicha -221
oni -222
lani -223
▁X -224
liy -225
▁R -226
es -227
▁tar -228
siz -229
▁amal -230
). -231
▁qar -232
shim -233
sil -234
otgan -235
▁dav -236
00 -237
radi -238
▁tash -239
az -240
▁te -241
▁ku -242
▁av -243
▁E -244
52 -245
ori -246
larini -247
▁tur -248
▁0 -249
tish -250
har -251
dam -252
▁hola -253
12 -254
▁D -255
ya -256
ve -257
▁uz -258
kiston -259
▁P -260
ana -261
larda -262
▁ga -263
ohida -264
ik -265
98 -266
atn -267
mma -268
tt -269
▁edi -270
01 -271
ang -272
▁alohida -273
31 -274
71 -275
mo -276
▁z -277
uvchi -278
sen -279
uti -280
bi -281
04 -282
iya -283
▁qu -284
shimcha -285
zbe -286
tlarda -287
▁bor -288
▁qilishi -289
angi -290
yo -291
ev -292
▁yil -293
siya -294
db -295
68 -296
▁omma -297
zbekiston -298
ona -299
▁in -300
rilmoqda -301
▁ol -302
▁lit -303
▁V -304
mat -305
Shar -306
62 -307
afsil -308
▁F -309
▁Matn -310
senziy -311
▁shartlar -312
▁litsenziy -313
▁har -314
ug -315
... -316
uk -317
▁holatlarda -318
lashtirilmoqda -319
kan -320
ttrib -321
ution -322
▁litsenziyasi -323
▁Cre -324
like -325
ommons -326
eA -327
ative -328
▁Commons -329
ShareA -330
▁Attrib -331
batafsil -332
▁Creative -333
ShareAlike -334
▁Attribution -335
▁qan -336
langan -337
rak -338
ish -339
▁or -340
lim -341
▁G -342
ae -343
▁ni -344
▁c -345
sti -346
tgan -347
le -348
yil -349
sida -350
mp -351
rov -352
▁joy -353
oli -354
ut -355
02 -356
▁haq -357
▁ber -358
▁deb -359
odi -360
lat -361
▁J -362
ja -363
▁3 -364
fd -365
▁boshqa -366
▁ra -367
▁l -368
▁shu -369
▁qay -370
ora -371
ingiz -372
qar -373
oti -374
63 -375
dc -376
▁shun -377
ea -378
biy -379
lardan -380
maydi -381
▁maq -382
gar -383
to -384
magan -385
rta -386
ent -387
▁si -388
uh -389
fa -390
iyat -391
▁tom -392
na -393
lum -394
79 -395
kil -396
enti -397
liq -398
larida -399
▁L -400
lig -401
▁19 -402
ice -403
ib -404
voice -405
▁common -406
ina -407
chilik -408
▁qanday -409
iq -410
lariga -411
tdi -412
▁ba -413
▁hay -414
id -415
ush -416
▁yuz -417
it -418
▁un -419
▁me -420
yin -421
bu -422
cf -423
▁qilish -424
layotgan -425
sp -426
roq -427
▁ye -428
▁yi -429
ilgan -430
bf -431
▁r -432
▁esa -433
dek -434
dim -435
▁yoki -436
91 -437
tir -438
▁chiq -439
▁tw -440
aning -441
▁gap -442
tadi -443
▁his -444
lsa -445
▁bar -446
75 -447
▁tush -448
ad -449
riy -450
enties -451
▁twenties -452
tik -453
84 -454
shib -455
▁yu -456
▁il -457
te -458
14 -459
lak -460
▁uning -461
53 -462
▁yer -463
tar -464
rir -465
jon -466
▁ekan -467
▁" -468
osi -469
▁Ch -470
89 -471
▁kerak -472
▁uy -473
56 -474
▁olib -475
lov -476
▁kun -477
mmo -478
and -479
▁ik -480
iga -481
▁Mil -482
▁emas -483
dar -484
▁xal -485
▁yar -486
son -487
orat -488
lanish -489
25 -490
▁tashkil -491
36 -492
▁man -493
34 -494
asida -495
▁haqida -496
▁Bir -497
rin -498
iloy -499
▁ar -500
▁ij -501
▁eti -502
▁odam -503
▁mar -504
pa -505
▁4 -506
diy -507
lashgan -508
▁qiz -509
oyda -510
0- -511
atta -512
lumot -513
xon -514
300 -515
▁bola -516
▁do -517
▁shah -518
lanadi -519
ali -520
▁kel -521
▁qis -522
sus -523
ekin -524
▁uni -525
▁viloy -526
bd -527
▁ah -528
xsh -529
rilgan -530
giz -531
ech -532
axshi -533
kor -534
▁ti -535
▁muh -536
rs -537
▁top -538
ron -539
▁yana -540
qib -541
ahi -542
laridan -543
zim -544
81 -545
▁cho -546
▁To -547
▁Af -548
tirish -549
zbek -550
▁qilin -551
ed -552
▁foyda -553
inchi -554
el -555
▁re -556
▁cha -557
rgan -558
abi -559
df -560
▁pay -561
931 -562
▁qilib -563
▁Ma -564
▁mil -565
▁kishi -566
tab -567
ligini -568
99 -569
larining -570
▁dedi -571
), -572
no -573
▁biz -574
▁Z -575
▁maqola -576
oya -577
▁yoz -578
fda -579
▁fa -580
▁yangi -581
▁nima -582
sta -583
▁bun -584
▁ega -585
lagan -586
▁katta -587
▁male -588
▁qa -589
min -590
638 -591
315 -592
797 -593
atida -594
loq -595
▁suv -596
zg -597
▁bergan -598
▁« -599
537 -600
104 -601
812 -602
▁yor -603
▁ammo -604
▁davlat -605
ba -606
571 -607
oliy -608
ublik -609
275 -610
▁03 -611
▁degan -612
▁yaxshi -613
aro -614
dba -615
▁ho -616
6898 -617
5289 -618
5230 -619
7315 -620
25931 -621
dbaae -622
571537 -623
fddbaae -624
68985230 -625
73155289 -626
rik -627
ndi -628
▁yosh -629
siyo -630
arish -631
▁ri -632
▁og -633
uni -634
ji -635
ardi -636
▁say -637
dor -638
▁5 -639
kent -640
▁san -641
▁mah -642
▁nom -643
▁(1 -644
ydi -645
ih -646
do -647
▁ikki -648
▁oldi -649
sha -650
▁bog -651
▁jam -652
ort -653
▁Shun -654
▁oy -655
▁keyin -656
lam -657
▁an -658
▁kim -659
tka -660
▁mav -661
▁tah -662
▁qoldi -663
▁hisob -664
ozir -665
of -666
sin -667
▁bil -668
▁bel -669
siga -670
▁nar -671
qo -672
rat -673
▁Qo -674
11 -675
tiq -676
▁um -677
▁qat -678
dabiy -679
▁oshi -680
▁at -681
▁men -682
yor -683
shbu -684
▁tan -685
▁Tosh -686
▁Ko -687
ara -688
ekt -689
miy -690
siyasi -691
uj -692
▁ro -693
▁kelayotgan -694
uda -695
ladigan -696
asini -697
lanib -698
730 -699
arq -700
▁olish -701
pe -702
▁er -703
san -704
azar -705
▁min -706
▁Tur -707
arix -708
tob -709
madi -710
ahifa -711
qish -712
▁Siz -713
lo -714
▁mam -715
aqat -716
oqda -717
”, -718
din -719
▁dar -720
▁xalq -721
ulla -722
laydi -723
matik -724
▁ming -725
za -726
▁dara -727
▁aso -728
rida -729
voj -730
▁vaq -731
_2 -732
▁sif -733
oda -734
▁ka -735
▁sho -736
uy -737
▁et -738
arib -739
idan -740
liklar -741
▁- -742
▁hech -743
▁yash -744
▁kelgan -745
▁yet -746
gina -747
▁hol -748
90 -749
▁rivoj -750
ziga -751
▁tiz -752
▁mak -753
sul -754
▁30 -755
▁tarki -756
▁eng -757
avo -758
▁belgi -759
▁ne -760
▁avto -761
▁im -762
onidan -763
ila -764
▁etish -765
tda -766
▁taq -767
asiga -768
rsat -769
-770
a -771
i -772
o -773
n -774
l -775
r -776
s -777
t -778
h -779
d -780
m -781
g -782
u -783
b -784
y -785
e -786
k -787
q -788
ʻ -789
z -790
. -791
v -792
c -793
, -794
f -795
1 -796
2 -797
0 -798
p -799
x -800
3 -801
j -802
- -803
9 -804
5 -805
8 -806
7 -807
A -808
S -809
6 -810
M -811
4 -812
B -813
O -814
ʼ -815
T -816
) -817
( -818
C -819
I -820
-821
K -822
Q -823
_ -824
U -825
Y -826
-827
: -828
H -829
-830
N -831
-832
R -833
X -834
? -835
E -836
D -837
P -838
V -839
" -840
F -841
! -842
G -843
' -844
L -845
/ -846
w -847
; -848
J -849
а -850
` -851
и -852
-853
Z -854
[ -855
] -856
-857
р -858
л -859
« -860
» -861
к -862
с -863
о -864
т -865
н -866
* -867
е -868
-869
| -870
= -871
+ -872
\ -873
у -874
° -875
} -876
д -877
в -878
% -879
б -880
й -881
м -882
г -883
з -884
ə -885
ь -886
ы -887
@ -888
-889
ш -890
ó -891
ا -892
> -893
ر -894
К -895
я -896
< -897
W -898
& -899
п -900
-901
ç -902
{ -903
ñ -904
ч -905
ü -906
Б -907
Р -908
á -909
ı -910
С -911
-912
х -913
í -914
қ -915
И -916
~ -917
А -918
# -919
М -920
Т -921
š -922
ե -923
ی -924
λ -925
О -926
У -927
© -928
ў -929
-930
$ -931
Н -932
ي -933
-934
· -935
س -936
-937
é -938
ب -939
ҳ -940
-941
Е -942
-943
â -944
­ -945
ن -946
ع -947
-948
و -949
ъ -950
Қ -951
ա -952
ր -953
à -954
ю -955
^ -956
ц -957
י -958
ف -959
ն -960
-961
ل -962
-963
Č -964
-965
-966
د -967
ї -968
-969
č -970
ê -971
Ў -972
ж -973
-974
-975
-976
յ -977
-978
-979
Ε -980
ά -981
-982
Д -983
ҷ -984
-985
ة -986
ё -987
ų -988
ι -989
η -990
ú -991
κ -992
Հ -993
і -994
ế -995
э -996