parakeet-tdt-1.1b / tokenizer.vocab
senstella's picture
Upload folder using huggingface_hub
75ea698 verified
<unk> 0
▁t -0
▁th -1
▁a -2
▁i -3
▁the -4
re -5
▁w -6
▁s -7
▁o -8
in -9
at -10
er -11
ou -12
nd -13
▁c -14
▁b -15
▁h -16
on -17
▁m -18
▁f -19
ing -20
▁to -21
en -22
▁p -23
▁and -24
▁d -25
es -26
or -27
an -28
ll -29
▁y -30
▁l -31
ed -32
▁of -33
▁in -34
it -35
is -36
▁you -37
▁that -38
ar -39
▁g -40
▁n -41
as -42
om -43
▁it -44
ic -45
ve -46
▁e -47
▁wh -48
▁be -49
us -50
le -51
al -52
ion -53
ow -54
▁we -55
▁re -56
▁is -57
ut -58
ot -59
ent -60
▁on -61
et -62
▁ha -63
ay -64
ct -65
▁he -66
id -67
▁for -68
▁st -69
ver -70
ly -71
ro -72
ig -73
▁so -74
ld -75
▁this -76
ke -77
▁u -78
se -79
all -80
st -81
ur -82
ce -83
ch -84
im -85
ith -86
▁as -87
▁k -88
▁an -89
▁was -90
▁j -91
▁with -92
ir -93
▁go -94
ra -95
▁do -96
▁have -97
▁li -98
▁sh -99
▁se -100
▁they -101
▁are -102
am -103
ht -104
▁but -105
ation -106
▁not -107
th -108
▁r -109
ally -110
ad -111
ust -112
▁or -113
▁com -114
ould -115
▁can -116
ill -117
▁ne -118
ight -119
▁ch -120
▁de -121
▁con -122
▁at -123
▁mo -124
ant -125
oo -126
il -127
▁me -128
▁what -129
▁there -130
ter -131
pe -132
▁ab -133
▁su -134
ere -135
ck -136
▁pro -137
▁al -138
▁fr -139
▁kn -140
▁all -141
ers -142
▁like -143
ge -144
▁ex -145
▁som -146
ul -147
▁your -148
▁v -149
pp -150
use -151
▁if -152
ess -153
ate -154
est -155
▁know -156
out -157
if -158
▁just -159
ment -160
qu -161
op -162
ain -163
▁one -164
ol -165
ri -166
art -167
very -168
▁wor -169
ive -170
ist -171
▁my -172
nt -173
ab -174
▁from -175
ort -176
▁ma -177
▁about -178
res -179
ity -180
▁out -181
▁bec -182
▁le -183
our -184
od -185
and -186
ink -187
ie -188
▁up -189
ind -190
os -191
un -192
ause -193
oug -194
um -195
▁some -196
▁int -197
▁by -198
▁pl -199
▁get -200
el -201
ard -202
▁when -203
▁don -204
her -205
▁will -206
▁us -207
▁would -208
ook -209
ies -210
ich -211
▁because -212
▁think -213
em -214
▁pe -215
▁his -216
ack -217
▁then -218
▁our -219
ide -220
▁tim -221
▁how -222
ven -223
▁tr -224
▁who -225
▁them -226
ure -227
▁ar -228
▁ye -229
▁more -230
▁going -231
ect -232
▁sa -233
▁cl -234
▁had -235
▁now -236
▁which -237
▁here -238
ous -239
▁their -240
▁tw -241
so -242
▁has -243
ud -244
▁co -245
▁ta -246
ound -247
▁were -248
ast -249
▁peop -250
ough -251
▁no -252
▁really -253
▁any -254
▁people -255
▁want -256
▁she -257
▁en -258
▁fa -259
▁te -260
ame -261
ine -262
▁qu -263
red -264
▁im -265
▁right -266
ther -267
▁act -268
▁thing -269
king -270
ose -271
▁ad -272
▁see -273
▁time -274
▁these -275
ci -276
one -277
▁say -278
▁also -279
▁fe -280
per -281
▁ag -282
▁man -283
ore -284
▁un -285
pt -286
▁her -287
▁look -288
ong -289
ice -290
▁very -291
ff -292
ions -293
▁comp -294
▁did -295
itt -296
▁well -297
▁other -298
iv -299
ase -300
ree -301
hing -302
▁lo -303
reat -304
▁cont -305
▁part -306
▁into -307
nder -308
▁been -309
are -310
▁am -311
ans -312
▁sp -313
▁two -314
ue -315
▁way -316
age -317
▁where -318
ite -319
▁dis -320
▁than -321
▁every -322
▁pr -323
▁po -324
ag -325
▁need -326
ach -327
iff -328
ence -329
pl -330
own -331
▁ac -332
ble -333
▁over -334
iz -335
▁work -336
▁res -337
▁make -338
▁could -339
▁off -340
ually -341
▁ro -342
▁back -343
able -344
ip -345
ry -346
▁him -347
▁cour -348
ber -349
▁pre -350
▁fir -351
▁spe -352
ap -353
ars -354
▁diff -355
ire -356
▁somet -357
▁imp -358
▁those -359
▁comm -360
ance -361
ick -362
▁even -363
ated -364
way -365
sel -366
▁let -367
▁br -368
ty -369
▁per -370
int -371
▁first -372
▁thr -373
▁under -374
ah -375
▁may -376
▁cou -377
▁new -378
ress -379
act -380
▁gr -381
ep -382
▁said -383
ations -384
▁good -385
ace -386
ass -387
▁does -388
orm -389
ish -390
▁af -391
ving -392
co -393
▁app -394
▁lot -395
▁things -396
▁tra -397
ittle -398
▁bl -399
▁little -400
▁mu -401
cess -402
fe -403
ome -404
▁inc -405
▁differe -406
ary -407
ical -408
▁only -409
ult -410
▁again -411
▁got -412
ens -413
▁gu -414
▁kind -415
▁much -416
ord -417
▁through -418
ition -419
ild -420
▁down -421
▁actually -422
▁something -423
ang -424
ru -425
ces -426
▁fl -427
ile -428
ater -429
▁ra -430
▁take -431
ict -432
ign -433
▁sc -434
vel -435
▁bet -436
▁tal -437
▁yeah -438
▁use -439
fore -440
▁bu -441
▁start -442
ory -443
be -444
▁day -445
wn -446
xt -447
ia -448
ak -449
▁after -450
▁should -451
▁fo -452
▁ho -453
▁hel -454
▁ind -455
▁uh -456
na -457
ial -458
other -459
▁ke -460
▁call -461
▁most -462
▁ok -463
▁different -464
▁em -465
ting -466
ple -467
▁being -468
▁bo -469
ning -470
▁too -471
ors -472
▁happ -473
ark -474
og -475
▁help -476
▁rem -477
du -478
ction -479
ood -480
▁ser -481
ether -482
ious -483
▁mean -484
▁many -485
▁court -486
▁bel -487
ade -488
▁la -489
ved -490
▁des -491
▁rec -492
▁jo -493
▁dec -494
ves -495
▁before -496
▁put -497
self -498
▁point -499
te -500
▁ev -501
form -502
ents -503
▁add -504
ody -505
thing -506
▁case -507
▁pers -508
▁cons -509
iss -510
▁three -511
oth -512
▁ph -513
▁come -514
▁find -515
▁why -516
ull -517
▁show -518
▁bas -519
▁great -520
ily -521
▁rel -522
▁sm -523
▁its -524
▁fact -525
▁pos -526
ool -527
ments -528
ise -529
nds -530
ys -531
▁try -532
ual -533
ful -534
erm -535
▁inter -536
ons -537
▁quest -538
▁sub -539
we -540
vers -541
▁supp -542
▁feel -543
▁same -544
ub -545
ates -546
urn -547
ert -548
▁inv -549
day -550
▁rep -551
igh -552
▁sy -553
▁inst -554
▁long -555
▁still -556
▁okay -557
ft -558
ific -559
atch -560
ought -561
ath -562
▁own -563
▁made -564
ix -565
ced -566
ks -567
lic -568
▁wr -569
de -570
▁cr -571
▁att -572
▁ob -573
▁world -574
▁sure -575
ward -576
▁bit -577
▁life -578
▁person -579
▁pres -580
ph -581
▁vide -582
▁reg -583
▁end -584
ject -585
ange -586
▁fin -587
ied -588
pect -589
▁didn -590
▁around -591
ian -592
▁car -593
ible -594
▁sim -595
ever -596
▁sch -597
ating -598
▁pol -599
▁set -600
▁oh -601
cy -602
▁real -603
▁import -604
▁count -605
▁um -606
▁next -607
cial -608
les -609
▁hu -610
▁acc -611
▁might -612
▁ent -613
▁doing -614
▁ins -615
▁gen -616
▁play -617
▁cle -618
▁another -619
ady -620
ular -621
ib -622
ways -623
ered -624
ility -625
ities -626
▁op -627
▁def -628
▁years -629
▁never -630
ower -631
ram -632
▁tell -633
▁sl -634
onna -635
ail -636
ren -637
ute -638
▁gonna -639
▁big -640
▁give -641
der -642
ount -643
▁ap -644
kes -645
▁state -646
▁cor -647
▁min -648
ically -649
▁mon -650
▁fam -651
▁important -652
▁always -653
▁high -654
▁four -655
▁gra -656
▁ca -657
▁stud -658
▁dist -659
▁talk -660
▁num -661
▁str -662
▁today -663
ract -664
▁while -665
ason -666
▁iss -667
▁sur -668
▁char -669
▁last -670
oy -671
ited -672
▁exper -673
▁place -674
▁tri -675
▁ear -676
▁belie -677
▁able -678
▁underst -679
▁che -680
▁both -681
ug -682
▁doesn -683
▁keep -684
▁happen -685
ings -686
iew -687
ather -688
▁ass -689
▁love -690
ative -691
av -692
▁yes -693
▁ele -694
▁year -695
▁such -696
▁video -697
ness -698
▁el -699
▁trans -700
▁five -701
▁produ -702
ave -703
erest -704
als -705
body -706
cus -707
▁found -708
atter -709
▁eff -710
▁god -711
▁used -712
llow -713
▁interest -714
▁question -715
hip -716
▁bus -717
▁ask -718
▁exam -719
▁prov -720
lud -721
▁form -722
▁law -723
ense -724
▁child -725
▁gl -726
ne -727
▁each -728
▁understand -729
▁care -730
stem -731
▁med -732
▁maybe -733
ably -734
▁det -735
▁coll -736
its -737
▁commun -738
▁hand -739
▁' -740
▁ref -741
▁lear -742
▁done -743
▁gener -744
vern -745
▁mr -746
ween -747
▁better -748
▁between -749
li -750
blem -751
▁system -752
ertain -753
▁school -754
▁eas -755
▁exp -756
▁war -757
ention -758
▁ty -759
▁govern -760
ues -761
▁problem -762
▁plan -763
ac -764
▁conf -765
▁course -766
ouse -767
▁mar -768
▁stand -769
▁sk -770
▁seco -771
uring -772
▁ed -773
▁mem -774
ros -775
cri -776
▁thought -777
cept -778
▁partic -779
▁test -780
olog -781
iness -782
▁far -783
led -784
▁col -785
▁looking -786
▁read -787
▁whether -788
▁word -789
me -790
▁once -791
ize -792
▁home -793
▁requ -794
gg -795
▁ide -796
▁thank -797
ures -798
▁called -799
▁cur -800
▁water -801
▁frie -802
▁side -803
▁best -804
▁number -805
oney -806
▁turn -807
ock -808
▁eng -809
▁top -810
▁open -811
ead -812
▁everything -813
▁term -814
▁prob -815
▁hard -816
▁fun -817
▁spec -818
▁dire -819
▁second -820
▁pa -821
▁build -822
▁run -823
▁sign -824
▁reason -825
▁inform -826
▁watch -827
ution -828
▁few -829
mo -830
▁hum -831
ision -832
▁ext -833
▁tog -834
▁conc -835
▁thous -836
▁thousand -837
▁support -838
▁together -839
▁six -840
ps -841
▁mark -842
ics -843
▁includ -844
ef -845
▁opp -846
ident -847
▁anything -848
▁met -849
▁bre -850
▁jud -851
▁away -852
▁old -853
▁prog -854
ten -855
▁book -856
▁says -857
▁seem -858
▁contin -859
▁process -860
▁sing -861
▁money -862
▁having -863
▁beg -864
▁comple -865
▁thir -866
▁using -867
▁ret -868
ger -869
▁head -870
▁cre -871
▁poss -872
enty -873
▁certain -874
▁clear -875
ines -876
▁wee -877
arch -878
▁inf -879
ont -880
▁sit -881
▁lead -882
alth -883
▁art -884
ross -885
▁pub -886
▁without -887
▁pret -888
▁getting -889
ient -890
▁z -891
▁wom -892
▁power -893
ational -894
ner -895
▁rest -896
▁believe -897
▁wa -898
▁aut -899
▁move -900
aim -901
▁sort -902
idence -903
▁creat -904
▁expl -905
▁name -906
▁went -907
▁eu -908
▁change -909
▁came -910
▁pay -911
ices -912
▁sin -913
▁pur -914
▁pass -915
▁whole -916
▁house -917
▁hund -918
▁hundred -919
▁pretty -920
▁trying -921
▁ple -922
▁allow -923
▁compan -924
▁government -925
▁small -926
▁light -927
▁bra -928
▁stu -929
aint -930
▁ah -931
▁prot -932
ets -933
▁cent -934
velop -935
▁family -936
▁business -937
ety -938
▁making -939
▁list -940
▁experi -941
eric -942
▁follow -943
ately -944
▁probably -945
▁appe -946
▁serv -947
▁val -948
▁leg -949
▁resp -950
▁develop -951
ready -952
▁already -953
▁sec -954
ell -955
▁saying -956
ash -957
▁hear -958
▁loc -959
▁adv -960
▁pri -961
ret -962
▁lar -963
▁beh -964
▁must -965
▁hon -966
▁means -967
ew -968
▁par -969
▁order -970
▁mom -971
gn -972
▁though -973
▁record -974
▁miss -975
▁dr -976
▁es -977
▁eight -978
▁ever -979
▁left -980
▁example -981
▁enough -982
osed -983
▁claim -984
ank -985
con -986
▁americ -987
▁information -988
▁arg -989
▁full -990
nce -991
▁consid -992
▁working -993
ature -994
-995
e -996
t -997
a -998
o -999
i -1000
n -1001
s -1002
r -1003
h -1004
l -1005
d -1006
u -1007
c -1008
m -1009
y -1010
w -1011
g -1012
f -1013
p -1014
b -1015
v -1016
k -1017
' -1018
j -1019
x -1020
q -1021
z -1022