uz_tokenizers / uz_tokenizer_upper_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
▁N -70
▁J -71
▁YO -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
▁NI -242
TISH -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
LIQ -382
KIL -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
▁ODAM -444
TAR -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
RIN -484
OS -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
IB -509
▁YOZ -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
▁YA -562
▁PAY -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
SINI -625
6898 -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
MASI -792
▁QURIL -793
▁MASH -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
SS -809
51 -810
▁JOYLASHGAN -811
▁SHAHAR -812
▁KELIB -813
_30 -814
▁KIRI -815
XONA -816
▁AVTOMATIK -817
▁KM -818
▁BUG -819
A -820
-821
I -822
O -823
N -824
L -825
R -826
S -827
T -828
H -829
D -830
M -831
B -832
G -833
U -834
Y -835
E -836
K -837
Q -838
ʻ -839
Z -840
C -841
V -842
. -843
, -844
F -845
1 -846
P -847
2 -848
0 -849
X -850
J -851
3 -852
- -853
9 -854
5 -855
8 -856
7 -857
6 -858
4 -859
ʼ -860
) -861
( -862
-863
_ -864
-865
: -866
-867
-868
? -869
" -870
! -871
W -872
' -873
/ -874
; -875
А -876
` -877
И -878
-879
[ -880
] -881
Р -882
-883
Л -884
К -885
С -886
« -887
» -888
О -889
Т -890
Н -891
Е -892
* -893
-894
| -895
= -896
+ -897
У -898
Б -899
\ -900
М -901
° -902
Д -903
} -904
В -905
% -906
Й -907
Г -908
З -909
Ə -910
Ь -911
Ы -912
Ш -913
@ -914
-915
Я -916
Ó -917
П -918
ا -919
> -920
ر -921
< -922
Қ -923
& -924
-925
Ç -926
o -927
Ч -928
{ -929
Á -930
Ü -931
Ñ -932
Х -933
Í -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
 -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