uz_tokenizers / uz_tokenizer_lower_1000.vocab
aslon1213's picture
Upload folder using huggingface_hub
1c6a554 verified
<unk> 0
<s> 0
</s> 0
la -0
sh -1
an -2
▁b -3
in -4
da -5
lar -6
li -7
▁t -8
▁o -9
di -10
ma -11
ch -12
ar -13
▁q -14
▁k -15
ti -16
si -17
ga -18
on -19
▁y -20
▁a -21
ri -22
gan -23
▁bo -24
▁h -25
ing -26
▁m -27
▁s -28
at -29
▁u -30
ni -31
il -32
▁e -33
ra -34
▁v -35
shi -36
▁ma -37
iy -38
ta -39
dan -40
gi -41
ir -42
am -43
un -44
▁sh -45
▁i -46
▁va -47
lari -48
chi -49
▁tu -50
or -51
cha -52
lik -53
ini -54
▁qo -55
ning -56
oq -57
iz -58
lan -59
▁ta -60
▁ke -61
sa -62
▁x -63
▁ko -64
▁mu -65
ki -66
▁d -67
ay -68
▁to -69
▁j -70
▁yo -71
▁n -72
en -73
lo -74
ya -75
ot -76
zi -77
▁p -78
er -79
▁f -80
man -81
▁bu -82
al -83
▁qi -84
st -85
lash -86
ur -87
▁bi -88
om -89
ka -90
▁ham -91
ov -92
▁bir -93
▁1 -94
ida -95
▁( -96
▁2 -97
oy -98
mon -99
▁so -100
lgan -101
▁da -102
lib -103
▁de -104
asi -105
ek -106
▁c -107
ladi -108
ol -109
ati -110
tlar -111
ab -112
im -113
uv -114
▁bilan -115
rib -116
yi -117
qa -118
kin -119
ul -120
▁– -121
vo -122
re -123
▁g -124
af -125
qi -126
▁be -127
▁ch -128
▁bosh -129
▁yu -130
ro -131
ari -132
ining -133
▁tuman -134
lishi -135
mi -136
▁ho -137
rish -138
lab -139
aq -140
.. -141
lish -142
30 -143
yo -144
um -145
▁uch -146
ldi -147
▁tumani -148
so -149
▁mum -150
▁si -151
ah -152
dagi -153
▁ki -154
ce -155
▁mumkin -156
adi -157
▁ish -158
moq -159
day -160
▁“ -161
ston -162
▁— -163
▁ay -164
bat -165
ea -166
to -167
as -168
mas -169
▁com -170
tib -171
▁common -172
miz -173
larni -174
ligi -175
▁shar -176
mal -177
lay -178
may -179
uz -180
▁z -181
larga -182
zb -183
▁chi -184
mo -185
ak -186
▁qil -187
▁uchun -188
▁tur -189
dir -190
ril -191
av -192
▁tar -193
siya -194
us -195
larning -196
ng -197
▁te -198
qo -199
ud -200
ax -201
▁qar -202
lani -203
lashti -204
▁yan -205
moqda -206
lit -207
▁dav -208
▁av -209
yicha -210
et -211
▁tash -212
bo -213
uq -214
▁an -215
ziy -216
loh -217
▁shu -218
▁amal -219
▁ku -220
). -221
bi -222
▁mat -223
▁uz -224
shim -225
00 -226
radi -227
otgan -228
▁ga -229
▁qu -230
shar -231
▁xo -232
latlar -233
sil -234
ve -235
52 -236
▁at -237
▁0 -238
▁shun -239
dam -240
larini -241
tish -242
▁ni -243
do -244
▁ra -245
12 -246
▁in -247
lat -248
kiston -249
▁har -250
az -251
ik -252
▁ol -253
ash -254
larda -255
98 -256
mma -257
▁edi -258
lohida -259
01 -260
▁alohida -261
▁su -262
biy -263
31 -264
71 -265
kan -266
sen -267
uvchi -268
▁qan -269
▁bor -270
siz -271
▁matn -272
oni -273
04 -274
mp -275
▁yil -276
le -277
liy -278
shimcha -279
zbe -280
▁or -281
tion -282
▁qilishi -283
ba -284
san -285
▁mil -286
sti -287
▁omma -288
sp -289
68 -290
ona -291
zbekiston -292
▁holatlar -293
rilmoqda -294
▁lit -295
mat -296
62 -297
afsil -298
senziy -299
▁shartlar -300
▁litsenziy -301
... -302
▁att -303
▁holatlarda -304
▁cre -305
▁ha -306
ribu -307
ev -308
lashtirilmoqda -309
tgan -310
▁litsenziyasi -311
like -312
ative -313
ribution -314
▁commons -315
ealike -316
batafsil -317
▁creative -318
sharealike -319
▁attribution -320
oh -321
langan -322
▁boshqa -323
sida -324
rak -325
rta -326
siy -327
▁ber -328
es -329
iya -330
▁qay -331
yil -332
ae -333
lim -334
▁man -335
▁ba -336
rov -337
oya -338
▁joy -339
▁as -340
ish -341
▁me -342
02 -343
▁deb -344
ja -345
▁un -346
▁re -347
▁3 -348
ub -349
▁r -350
gar -351
fd -352
is -353
qar -354
ingiz -355
63 -356
▁hay -357
▁am -358
dc -359
oli -360
▁al -361
lardan -362
dim -363
maydi -364
ent -365
▁do -366
▁ah -367
magan -368
iq -369
fa -370
lum -371
▁bun -372
bu -373
▁uning -374
▁bar -375
od -376
iyat -377
79 -378
▁ar -379
▁bola -380
▁aso -381
kil -382
liq -383
diy -384
na -385
yin -386
enti -387
riy -388
larida -389
▁muh -390
lig -391
▁qanday -392
▁haq -393
▁19 -394
ice -395
ina -396
voice -397
chilik -398
▁yuz -399
▁yi -400
▁ye -401
lariga -402
▁cho -403
▁il -404
▁ik -405
ut -406
oz -407
▁ro -408
uk -409
▁yangi -410
tir -411
giz -412
▁xal -413
lek -414
▁ti -415
bd -416
▁biz -417
id -418
▁yer -419
cf -420
▁qilish -421
▁tw -422
▁gap -423
tdi -424
layotgan -425
▁qa -426
▁yoki -427
▁uy -428
no -429
▁lo -430
▁qiz -431
bf -432
▁esa -433
ilgan -434
▁tashkil -435
lov -436
roq -437
lsa -438
91 -439
▁is -440
▁chiq -441
▁tan -442
tadi -443
tar -444
▁odam -445
▁tomon -446
idan -447
dek -448
▁tush -449
75 -450
▁men -451
▁ekan -452
▁say -453
son -454
enties -455
▁twenties -456
ush -457
84 -458
aning -459
jon -460
hri -461
shib -462
▁kun -463
▁yana -464
14 -465
▁af -466
▁ij -467
53 -468
▁kerak -469
▁yar -470
ang -471
▁kat -472
▁qis -473
▁maqo -474
▁" -475
89 -476
tik -477
▁olib -478
56 -479
▁shah -480
dar -481
▁ammo -482
▁emas -483
os -484
rin -485
▁fa -486
▁maqola -487
lanish -488
bor -489
▁uni -490
oti -491
25 -492
36 -493
▁nima -494
▁sho -495
▁may -496
▁mar -497
34 -498
▁er -499
▁haqida -500
▁san -501
iga -502
sat -503
pa -504
▁kel -505
▁eti -506
zir -507
▁vil -508
▁yoz -509
ib -510
▁en -511
▁mah -512
xon -513
▁dar -514
▁4 -515
▁bog -516
lashgan -517
og -518
avo -519
oyda -520
0- -521
▁davlat -522
lumot -523
▁siz -524
300 -525
▁jam -526
▁tosh -527
lanadi -528
rilgan -529
▁cha -530
ko -531
it -532
▁qat -533
▁yosh -534
▁keyin -535
sus -536
df -537
▁ne -538
lak -539
▁foyda -540
▁yax -541
hrir -542
kor -543
siga -544
asida -545
▁katta -546
sha -547
te -548
▁ri -549
▁top -550
▁yor -551
qib -552
mu -553
▁ka -554
dor -555
▁suv -556
laridan -557
tirish -558
zim -559
▁kim -560
81 -561
▁pay -562
▁ya -563
ahi -564
▁kishi -565
inchi -566
▁qilin -567
▁yaxshi -568
zbek -569
▁sa -570
iso -571
de -572
▁ega -573
931 -574
▁qilib -575
rgan -576
ligini -577
xsh -578
ani -579
99 -580
loq -581
▁dedi -582
ha -583
va -584
), -585
ug -586
larining -587
zg -588
fda -589
▁far -590
▁ikki -591
lagan -592
abi -593
▁eng -594
▁mav -595
▁nom -596
bir -597
tab -598
▁hiso -599
▁og -600
▁se -601
▁male -602
638 -603
▁bil -604
▁ush -605
315 -606
797 -607
▁bergan -608
▁« -609
537 -610
104 -611
812 -612
571 -613
ublik -614
fdd -615
ji -616
za -617
▁shi -618
275 -619
min -620
▁degan -621
▁03 -622
▁xalq -623
▁ota -624
6898 -625
sini -626
baae -627
5289 -628
5230 -629
7315 -630
25931 -631
571537 -632
fddbaae -633
68985230 -634
73155289 -635
▁resp -636
▁sahi -637
ron -638
▁respublik -639
ydi -640
▁aholi -641
arish -642
aro -643
ech -644
rida -645
▁mo -646
▁bel -647
tob -648
rik -649
kent -650
qsa -651
▁5 -652
▁nar -653
▁qora -654
▁oy -655
tin -656
▁lek -657
sin -658
▁oldi -659
▁ada -660
tka -661
▁(1 -662
bar -663
▁ju -664
▁tari -665
zo -666
lam -667
▁ular -668
▁lekin -669
▁mam -670
▁hisob -671
▁mak -672
ort -673
▁til -674
▁qoldi -675
▁mun -676
log -677
orat -678
▁no -679
sta -680
▁shax -681
▁sab -682
▁naz -683
rat -684
▁ming -685
uh -686
yor -687
▁ur -688
qat -689
▁hech -690
▁oshi -691
11 -692
miy -693
▁min -694
qiy -695
▁shunday -696
▁um -697
▁qon -698
▁vaq -699
▁ushbu -700
pe -701
▁adabiy -702
▁par -703
▁ak -704
lanib -705
din -706
▁turk -707
▁kelayotgan -708
ladigan -709
▁sug -710
uj -711
730 -712
▁olish -713
▁yordam -714
su -715
qish -716
atida -717
▁hozir -718
oyati -719
▁di -720
▁rah -721
dda -722
▁yaq -723
laydi -724
madi -725
▁inson -726
▁dara -727
▁mayd -728
qan -729
▁rivo -730
oqda -731
▁im -732
▁yet -733
▁viloyati -734
▁hol -735
ed -736
▁masa -737
”, -738
aqat -739
▁zar -740
matik -741
oyat -742
▁sif -743
siyasi -744
_2 -745
▁oq -746
▁tarix -747
▁rivoj -748
▁barcha -749
liklar -750
▁kelgan -751
lida -752
▁afsus -753
▁tarki -754
▁avto -755
tiq -756
▁- -757
gina -758
▁tiz -759
▁sahifa -760
▁yur -761
▁ora -762
▁yash -763
ziga -764
▁ax -765
ardi -766
▁qish -767
▁kam -768
idagi -769
▁belgi -770
90 -771
▁xiz -772
▁shuning -773
▁30 -774
▁toshkent -775
fo -776
yap -777
▁tog -778
▁jo -779
▁taq -780
▁po -781
▁etish -782
rsat -783
▁go -784
▁kar -785
iki -786
▁aj -787
▁iq -788
ulla -789
▁et -790
ara -791
▁quril -792
▁mash -793
masi -794
▁bah -795
▁marka -796
iston -797
▁shak -798
diya -799
riga -800
ku -801
▁hamda -802
qal -803
asini -804
▁aka -805
zm -806
▁asar -807
▁berish -808
51 -809
ss -810
▁joylashgan -811
▁shahar -812
▁kelib -813
_30 -814
▁kiri -815
xona -816
▁avtomatik -817
▁km -818
a -819
-820
i -821
o -822
n -823
l -824
r -825
s -826
t -827
h -828
d -829
m -830
b -831
g -832
u -833
y -834
e -835
k -836
q -837
ʻ -838
z -839
c -840
v -841
. -842
, -843
f -844
1 -845
p -846
2 -847
0 -848
x -849
j -850
3 -851
- -852
9 -853
5 -854
8 -855
7 -856
6 -857
4 -858
ʼ -859
) -860
( -861
-862
_ -863
-864
: -865
-866
-867
? -868
" -869
! -870
w -871
' -872
/ -873
; -874
а -875
` -876
и -877
-878
[ -879
] -880
р -881
-882
л -883
к -884
с -885
« -886
» -887
о -888
т -889
н -890
е -891
* -892
-893
| -894
= -895
+ -896
у -897
б -898
\ -899
м -900
° -901
д -902
} -903
в -904
% -905
й -906
г -907
з -908
ə -909
ь -910
ы -911
ш -912
@ -913
-914
я -915
ó -916
п -917
ا -918
> -919
ر -920
< -921
қ -922
& -923
-924
ç -925
N -926
ч -927
{ -928
á -929
ü -930
ñ -931
х -932
í -933
ı -934
ў -935
-936
~ -937
# -938
č -939
š -940
ե -941
ی -942
λ -943
© -944
-945
ա -946
$ -947
ي -948
ҳ -949
-950
· -951
é -952
س -953
-954
ب -955
-956
-957
â -958
­ -959
ن -960
ع -961
-962
و -963
ц -964
ъ -965
ր -966
ю -967
à -968
^ -969
י -970
ف -971
ն -972
-973
ل -974
-975
-976
-977
ж -978
ф -979
د -980
ї -981
-982
ε -983
э -984
ê -985
-986
-987
-988
հ -989
յ -990
-991
-992
ά -993
-994
ё -995
ҷ -996