parakeet-tdt_ctc-1.1b / tokenizer.vocab
senstella's picture
Upload folder using huggingface_hub
94c2a8a verified
<unk> 0
▁t -0
▁th -1
▁a -2
in -3
re -4
▁the -5
▁w -6
▁s -7
▁o -8
er -9
ou -10
at -11
nd -12
it -13
▁h -14
▁c -15
▁b -16
is -17
en -18
on -19
ing -20
▁f -21
▁to -22
▁m -23
es -24
▁p -25
or -26
an -27
▁d -28
ll -29
▁I -30
ed -31
▁and -32
▁l -33
▁of -34
▁in -35
▁y -36
ar -37
▁g -38
▁you -39
as -40
om -41
▁n -42
ve -43
▁that -44
le -45
ic -46
us -47
ow -48
et -49
al -50
▁e -51
ut -52
▁it -53
ot -54
▁be -55
▁T -56
ion -57
▁is -58
▁wh -59
▁re -60
▁on -61
▁we -62
ent -63
▁A -64
ay -65
▁ha -66
▁Th -67
id -68
▁S -69
ac -70
gh -71
ver -72
ke -73
▁for -74
im -75
ly -76
ur -77
ld -78
▁he -79
▁st -80
all -81
ro -82
st -83
se -84
ct -85
ith -86
ir -87
am -88
▁this -89
if -90
▁W -91
oo -92
ri -93
▁was -94
ght -95
▁u -96
▁with -97
ad -98
ch -99
▁se -100
▁k -101
▁an -102
▁The -103
▁li -104
▁do -105
▁B -106
▁have -107
▁as -108
th -109
▁are -110
▁sh -111
ust -112
ce -113
ally -114
ill -115
▁H -116
▁j -117
ter -118
▁go -119
▁And -120
ation -121
▁C -122
▁so -123
ome -124
▁not -125
op -126
il -127
ore -128
▁ne -129
▁can -130
▁me -131
▁at -132
ould -133
ant -134
▁M -135
▁like -136
ere -137
▁they -138
ra -139
ers -140
▁ab -141
▁de -142
▁kn -143
ge -144
▁Y -145
▁ch -146
ul -147
pp -148
▁or -149
▁al -150
▁con -151
▁com -152
ess -153
▁su -154
out -155
▁your -156
▁So -157
ate -158
▁one -159
▁all -160
▁ex -161
est -162
▁fr -163
▁just -164
▁pro -165
▁know -166
▁O -167
ain -168
▁but -169
ol -170
ive -171
▁v -172
use -173
very -174
art -175
qu -176
▁my -177
el -178
▁N -179
nt -180
▁It -181
▁what -182
ab -183
▁P -184
▁wor -185
▁out -186
▁there -187
▁up -188
um -189
▁from -190
pe -191
▁tw -192
▁r -193
and -194
ight -195
ort -196
un -197
▁L -198
ist -199
▁about -200
ide -201
ig -202
ake -203
▁D -204
em -205
os -206
king -207
rou -208
ind -209
our -210
res -211
▁We -212
▁get -213
▁E -214
▁G -215
ack -216
▁le -217
ity -218
od -219
▁F -220
ard -221
▁pl -222
▁our -223
▁int -224
ment -225
▁will -226
ies -227
▁by -228
ink -229
ca -230
▁if -231
red -232
her -233
ie -234
▁us -235
▁some -236
▁don -237
ven -238
ood -239
ast -240
▁R -241
▁his -242
▁tim -243
▁tr -244
▁more -245
ich -246
ous -247
ame -248
▁going -249
▁had -250
▁them -251
ook -252
▁pe -253
▁Wh -254
▁You -255
▁But -256
ine -257
▁here -258
▁would -259
cause -260
right -261
so -262
ost -263
ure -264
▁has -265
ect -266
▁think -267
▁fe -268
ong -269
▁see -270
▁when -271
▁who -272
▁were -273
▁really -274
▁their -275
▁want -276
one -277
ople -278
▁then -279
▁time -280
▁sa -281
ap -282
▁te -283
▁He -284
▁ye -285
ck -286
▁her -287
▁thing -288
▁right -289
▁which -290
itt -291
ice -292
act -293
▁people -294
ty -295
▁two -296
▁J -297
▁im -298
ther -299
ci -300
ose -301
▁cl -302
▁qu -303
▁man -304
▁also -305
ree -306
▁en -307
ud -308
▁how -309
reat -310
ak -311
hing -312
ag -313
▁any -314
ff -315
ace -316
per -317
▁because -318
▁very -319
own -320
▁ad -321
▁act -322
▁been -323
▁now -324
▁ag -325
▁into -326
▁comp -327
ars -328
ions -329
are -330
ite -331
iv -332
▁these -333
ays -334
ep -335
▁This -336
▁she -337
ans -338
ah -339
een -340
▁over -341
ry -342
▁lo -343
age -344
▁pr -345
▁sp -346
ue -347
▁co -348
ick -349
ber -350
▁did -351
ip -352
ach -353
▁back -354
▁no -355
▁cont -356
▁other -357
▁every -358
pt -359
▁need -360
▁him -361
▁U -362
▁In -363
▁work -364
irst -365
▁part -366
▁look -367
ittle -368
ble -369
iz -370
▁un -371
▁make -372
omet -373
nder -374
ish -375
na -376
▁little -377
▁off -378
▁than -379
▁got -380
ually -381
▁per -382
▁good -383
▁way -384
▁could -385
▁ac -386
▁imp -387
able -388
▁where -389
iff -390
▁That -391
▁res -392
ount -393
pl -394
ance -395
▁first -396
▁ro -397
▁pre -398
ass -399
▁say -400
int -401
ated -402
ire -403
uch -404
ase -405
▁somet -406
ound -407
▁down -408
▁diff -409
sel -410
▁gu -411
▁am -412
ress -413
▁lot -414
ence -415
▁dis -416
orm -417
ix -418
▁po -419
ving -420
enty -421
▁K -422
▁spe -423
und -424
he -425
▁much -426
▁ar -427
round -428
▁app -429
co -430
ark -431
▁new -432
ater -433
ult -434
end -435
▁even -436
▁start -437
ations -438
rough -439
ile -440
fter -441
▁well -442
be -443
▁They -444
▁three -445
ign -446
ild -447
▁said -448
ough -449
ang -450
▁too -451
ade -452
▁bl -453
ens -454
▁inc -455
ia -456
▁those -457
▁mo -458
▁take -459
▁through -460
▁fl -461
▁kind -462
▁things -463
▁bet -464
▁only -465
▁St -466
▁let -467
cess -468
▁Ch -469
ary -470
vel -471
▁If -472
xt -473
other -474
av -475
ical -476
ord -477
▁again -478
▁something -479
onna -480
fore -481
▁may -482
ting -483
▁bu -484
▁differe -485
urn -486
▁gonna -487
▁does -488
uct -489
og -490
▁twenty -491
▁gr -492
▁Ye -493
wn -494
▁should -495
▁comm -496
ition -497
▁under -498
▁hel -499
ory -500
▁fo -501
▁use -502
igh -503
ife -504
▁actually -505
▁tal -506
▁call -507
ents -508
ious -509
ull -510
▁There -511
▁Yeah -512
▁most -513
▁ke -514
ors -515
ved -516
ys -517
▁sc -518
▁happ -519
ope -520
▁help -521
atch -522
▁What -523
▁rem -524
ple -525
▁Now -526
▁br -527
ool -528
oth -529
▁four -530
self -531
▁str -532
ne -533
thing -534
▁put -535
ial -536
▁great -537
ail -538
ub -539
ning -540
▁sm -541
▁feel -542
▁five -543
ody -544
undred -545
iss -546
ank -547
get -548
aking -549
▁many -550
▁hundred -551
▁years -552
▁being -553
▁come -554
▁mean -555
ily -556
▁different -557
▁after -558
▁ser -559
▁show -560
form -561
ful -562
oy -563
▁six -564
▁vide -565
▁V -566
▁its -567
▁point -568
▁day -569
▁des -570
ons -571
▁bit -572
▁bel -573
▁before -574
▁aw -575
▁end -576
▁Oh -577
▁still -578
ath -579
▁long -580
▁' -581
ise -582
ob -583
day -584
▁add -585
ft -586
ves -587
ces -588
ady -589
▁cr -590
▁around -591
▁try -592
les -593
vers -594
kay -595
ian -596
ates -597
▁find -598
ward -599
▁As -600
▁eight -601
lic -602
▁same -603
▁pos -604
▁em -605
▁made -606
▁supp -607
▁life -608
▁Be -609
pect -610
▁dec -611
▁play -612
ange -613
▁att -614
▁pers -615
ways -616
▁high -617
▁hand -618
▁next -619
▁cons -620
▁own -621
▁inv -622
ower -623
▁ind -624
ert -625
ng -626
ave -627
▁year -628
▁big -629
ating -630
▁world -631
▁rel -632
▁sure -633
▁tra -634
ew -635
ered -636
▁fin -637
▁Well -638
▁sl -639
▁doing -640
bs -641
▁set -642
▁rec -643
ual -644
cial -645
▁ph -646
erm -647
▁love -648
ph -649
▁real -650
▁last -651
ict -652
▁bo -653
▁ra -654
ible -655
▁wr -656
mer -657
▁count -658
ities -659
▁always -660
inet -661
ments -662
uc -663
▁might -664
▁inter -665
▁video -666
gin -667
▁tell -668
▁never -669
vent -670
▁import -671
ied -672
▁sy -673
▁How -674
ically -675
ought -676
▁thir -677
▁rep -678
ks -679
ib -680
▁fam -681
ject -682
▁bas -683
▁She -684
▁give -685
akes -686
▁ninet -687
▁reg -688
▁min -689
▁op -690
▁def -691
▁didn -692
te -693
▁cour -694
▁why -695
▁ent -696
▁place -697
▁ins -698
▁car -699
ather -700
▁person -701
ular -702
▁inst -703
▁prod -704
lect -705
▁Al -706
▁today -707
▁bec -708
▁sur -709
▁All -710
▁another -711
▁bus -712
▁keep -713
ell -714
ese -715
riend -716
▁quest -717
▁talk -718
als -719
ings -720
▁mon -721
cond -722
old -723
▁acc -724
▁la -725
▁num -726
ident -727
▁che -728
iness -729
▁turn -730
▁ear -731
▁No -732
ousand -733
▁better -734
ific -735
▁loo -736
▁gl -737
oc -738
▁important -739
ited -740
▁An -741
▁thousand -742
ility -743
llow -744
▁used -745
▁gen -746
▁sim -747
li -748
▁happen -749
▁Un -750
▁Let -751
air -752
ock -753
ably -754
gg -755
▁watch -756
▁For -757
▁sw -758
ren -759
ute -760
ever -761
▁pol -762
▁sch -763
▁When -764
▁such -765
▁fif -766
▁home -767
▁cle -768
▁contin -769
ouse -770
▁friend -771
uring -772
▁Okay -773
gr -774
▁able -775
▁stud -776
▁eff -777
hip -778
body -779
▁top -780
ness -781
▁exper -782
▁pret -783
▁both -784
▁done -785
cri -786
▁mark -787
▁while -788
▁old -789
ros -790
ont -791
▁second -792
ative -793
▁thought -794
▁best -795
▁found -796
iew -797
▁belie -798
▁each -799
erest -800
▁tri -801
▁eas -802
▁ca -803
▁fact -804
▁care -805
▁fun -806
atter -807
ures -808
▁head -809
▁lear -810
▁water -811
▁hard -812
▁few -813
▁side -814
ween -815
▁exp -816
▁away -817
its -818
▁ext -819
lud -820
▁run -821
▁trans -822
ince -823
▁sk -824
▁open -825
cus -826
▁between -827
▁called -828
▁wee -829
▁pretty -830
ason -831
▁far -832
ember -833
omm -834
▁interest -835
any -836
ner -837
uff -838
▁pres -839
▁cur -840
▁child -841
ee -842
▁toget -843
▁together -844
olog -845
▁God -846
ond -847
▁char -848
▁looking -849
stem -850
az -851
cent -852
▁ob -853
▁ass -854
land -855
▁doesn -856
▁business -857
▁course -858
▁ten -859
ps -860
arch -861
ced -862
ms -863
ize -864
nce -865
▁ref -866
▁name -867
ross -868
▁grow -869
oney -870
▁went -871
ics -872
teen -873
▁cou -874
▁prob -875
▁ret -876
▁guys -877
▁came -878
ash -879
led -880
▁Eur -881
ues -882
▁ide -883
gan -884
▁everything -885
▁getting -886
▁ask -887
▁cor -888
▁build -889
▁sign -890
▁small -891
uck -892
▁el -893
▁col -894
▁Is -895
ational -896
stand -897
cy -898
▁conf -899
der -900
▁bre -901
▁cap -902
▁mod -903
ets -904
ike -905
▁number -906
▁comple -907
ertain -908
▁ever -909
▁coll -910
▁hum -911
▁Europe -912
▁cre -913
▁met -914
▁exam -915
▁move -916
▁pass -917
▁left -918
▁system -919
▁includ -920
▁Thank -921
cept -922
▁wom -923
▁product -924
ten -925
▁rest -926
▁probably -927
▁dri -928
▁Do -929
▁gener -930
▁anything -931
▁lar -932
▁My -933
▁school -934
▁lead -935
▁sub -936
▁ty -937
▁plan -938
▁seem -939
▁whole -940
irect -941
▁light -942
▁must -943
▁mom -944
▁opp -945
▁support -946
▁family -947
ices -948
amp -949
▁proble -950
▁dr -951
ready -952
▁using -953
ense -954
▁prov -955
ush -956
ax -957
▁power -958
▁Re -959
alth -960
▁ev -961
▁stand -962
▁war -963
ts -964
-965
e -966
t -967
o -968
a -969
n -970
i -971
s -972
r -973
h -974
l -975
d -976
u -977
c -978
m -979
y -980
g -981
w -982
f -983
p -984
. -985
b -986
, -987
v -988
k -989
' -990
I -991
T -992
A -993
S -994
x -995
W -996
j -997
B -998
C -999
H -1000
? -1001
M -1002
O -1003
Y -1004
N -1005
P -1006
E -1007
q -1008
L -1009
D -1010
z -1011
G -1012
F -1013
R -1014
! -1015
J -1016
U -1017
K -1018
V -1019
Q -1020
Z -1021
X -1022