tuanio commited on
Commit
a2834ba
1 Parent(s): b239681

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +963 -0
  2. special_tokens_map.json +3 -5
  3. tokenizer.json +1988 -1044
  4. tokenizer_config.json +5 -9
  5. vocab.json +1 -0
merges.txt ADDED
@@ -0,0 +1,963 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #version: 0.2
2
+ Ġ t
3
+ e r
4
+ r e
5
+ o n
6
+ Ġ f
7
+ i n
8
+ Ġ s
9
+ v e
10
+ on e
11
+ Ġt h
12
+ Ġ one
13
+ re e
14
+ w o
15
+ Ġ z
16
+ Ġt wo
17
+ er o
18
+ Ġz ero
19
+ Ġth ree
20
+ a r
21
+ i g
22
+ ig h
23
+ o u
24
+ l e
25
+ igh t
26
+ Ġ c
27
+ n d
28
+ Ġ e
29
+ Ġ n
30
+ Ġ d
31
+ Ġ a
32
+ Ġs e
33
+ Ġf i
34
+ Ġs i
35
+ Ġfi ve
36
+ Ġe ight
37
+ ve n
38
+ a y
39
+ Ġsi x
40
+ ou r
41
+ Ġse ven
42
+ Ġn in
43
+ in g
44
+ Ġ r
45
+ a l
46
+ Ġf our
47
+ Ġd e
48
+ m b
49
+ o r
50
+ k y
51
+ Ġ le
52
+ ar k
53
+ l ark
54
+ re d
55
+ ky lark
56
+ a c
57
+ n w
58
+ Ġnin er
59
+ Ġt o
60
+ Ġ g
61
+ ve l
62
+ Ġ l
63
+ Ġ h
64
+ u r
65
+ Ġle vel
66
+ Ġ w
67
+ a nd
68
+ r o
69
+ a d
70
+ u nw
71
+ unw ay
72
+ s c
73
+ in d
74
+ l i
75
+ a p
76
+ Ġr unway
77
+ Ġ m
78
+ s kylark
79
+ Ġg o
80
+ a n
81
+ i r
82
+ mb er
83
+ Ġ er
84
+ u e
85
+ i s
86
+ e t
87
+ Ġf l
88
+ t ar
89
+ Ġ p
90
+ Ġ b
91
+ le a
92
+ lea red
93
+ c t
94
+ n o
95
+ m al
96
+ Ġfl ight
97
+ k e
98
+ Ġa nd
99
+ Ġ o
100
+ Ġc on
101
+ Ġ v
102
+ q ue
103
+ Ġf or
104
+ c h
105
+ Ġ re
106
+ li mb
107
+ e nd
108
+ ou s
109
+ ous and
110
+ Ġth ousand
111
+ u m
112
+ sc end
113
+ Ġ k
114
+ a t
115
+ a in
116
+ le tar
117
+ p ur
118
+ e d
119
+ um pur
120
+ o d
121
+ o w
122
+ s i
123
+ r a
124
+ Ġcon t
125
+ Ġc leared
126
+ Ġgo od
127
+ c i
128
+ s t
129
+ ci mal
130
+ Ġde cimal
131
+ Ġc limb
132
+ p ro
133
+ Ġde scend
134
+ Ġa p
135
+ ve mber
136
+ Ġap pro
137
+ Ġse letar
138
+ Ġf e
139
+ Ġfe et
140
+ Ġs kylark
141
+ i re
142
+ ac t
143
+ e ad
144
+ Ġr ad
145
+ Ġ y
146
+ u mber
147
+ Ġc ap
148
+ f f
149
+ Ġrad ar
150
+ b e
151
+ l y
152
+ Ġto w
153
+ Ġl umpur
154
+ Ġtow er
155
+ Ġcont act
156
+ ac e
157
+ ur f
158
+ urf ace
159
+ Ġs urface
160
+ no t
161
+ Ġw ind
162
+ i t
163
+ Ġk not
164
+ Ġknot s
165
+ g ree
166
+ x t
167
+ d e
168
+ o p
169
+ Ġ j
170
+ n in
171
+ sc ar
172
+ Ġnin e
173
+ f t
174
+ Ġde gree
175
+ Ġdegree s
176
+ ch o
177
+ i ed
178
+ que be
179
+ quebe c
180
+ ro t
181
+ o xt
182
+ oxt rot
183
+ Ġ quebec
184
+ Ġv i
185
+ Ġd ow
186
+ Ġo scar
187
+ ct or
188
+ nw ind
189
+ Ġl and
190
+ Ġe cho
191
+ Ġdow nwind
192
+ i l
193
+ o re
194
+ Ġf oxtrot
195
+ f ly
196
+ ead ing
197
+ nin er
198
+ v o
199
+ ing ap
200
+ ingap ore
201
+ ra vo
202
+ que st
203
+ s s
204
+ ire ct
205
+ ir m
206
+ Ġre quest
207
+ Ġb ravo
208
+ u nd
209
+ Ġn o
210
+ und red
211
+ Ġh undred
212
+ Ġh eading
213
+ no vember
214
+ o t
215
+ ac h
216
+ Ġw h
217
+ ou ch
218
+ ap a
219
+ g o
220
+ at e
221
+ ay si
222
+ t ain
223
+ ain tain
224
+ Ġy ou
225
+ Ġd ay
226
+ Ġm al
227
+ Ġappro ach
228
+ in al
229
+ a ir
230
+ ve d
231
+ Ġf inal
232
+ t a
233
+ Ġp apa
234
+ Ġ red
235
+ Ġn umber
236
+ Ġt ouch
237
+ Ġd irect
238
+ aysi an
239
+ Ġappro ved
240
+ Ġvi ctor
241
+ Ġ u
242
+ s e
243
+ c leared
244
+ Ġs t
245
+ Ġt a
246
+ a m
247
+ t i
248
+ Ġm aintain
249
+ Ġth e
250
+ l umpur
251
+ ou nd
252
+ Ġno vember
253
+ l k
254
+ Ġ i
255
+ Ġm i
256
+ Ġ q
257
+ lk air
258
+ op ied
259
+ Ġc h
260
+ Ġs ingapore
261
+ Ġa ir
262
+ Ġw e
263
+ Ġ on
264
+ o in
265
+ ke y
266
+ is key
267
+ il o
268
+ Ġta ke
269
+ Ġle ft
270
+ Ġa l
271
+ Ġk ilo
272
+ t h
273
+ o ff
274
+ u al
275
+ Ġwh iskey
276
+ Ġb y
277
+ Ġ ar
278
+ Ġtake off
279
+ l d
280
+ Ġv is
281
+ Ġ in
282
+ Ġp a
283
+ Ġu p
284
+ n umber
285
+ ven ing
286
+ ind o
287
+ Ġe vening
288
+ Ġ is
289
+ ac ate
290
+ e n
291
+ Ġa t
292
+ Ġvis ual
293
+ i c
294
+ f irm
295
+ q u
296
+ l ta
297
+ e l
298
+ Ġmi ke
299
+ ar li
300
+ arli e
301
+ o ld
302
+ Ġre ad
303
+ Ġpa ss
304
+ i a
305
+ Ġ x
306
+ ac k
307
+ Ġde lta
308
+ o ot
309
+ g er
310
+ oot er
311
+ c limb
312
+ Ġc opied
313
+ Ġch arlie
314
+ a w
315
+ or t
316
+ Ġread y
317
+ Ġt ur
318
+ Ġfi re
319
+ Ġfire fly
320
+ an go
321
+ r ound
322
+ aw k
323
+ qu awk
324
+ Ġcon firm
325
+ Ġv acate
326
+ ind ia
327
+ de n
328
+ Ġs quawk
329
+ a g
330
+ ft er
331
+ an k
332
+ r ay
333
+ Ġi den
334
+ in e
335
+ Ġpass ing
336
+ ti f
337
+ tif ied
338
+ Ġg round
339
+ Ġ india
340
+ Ġtur n
341
+ Ġiden tified
342
+ Ġh old
343
+ se letar
344
+ h a
345
+ ke e
346
+ p ha
347
+ f ire
348
+ fire fly
349
+ ff irm
350
+ er ra
351
+ i m
352
+ Ġj u
353
+ Ġa fter
354
+ p ort
355
+ v er
356
+ le ar
357
+ Ġal pha
358
+ i on
359
+ Ġmal aysian
360
+ de scend
361
+ ag on
362
+ Ġt ango
363
+ Ġo f
364
+ Ġre port
365
+ in ue
366
+ v i
367
+ Ġo ver
368
+ l f
369
+ Ġr o
370
+ Ġsi r
371
+ Ġsi erra
372
+ r i
373
+ et t
374
+ Ġgo lf
375
+ it h
376
+ li ett
377
+ or n
378
+ u l
379
+ Ġsi lkair
380
+ Ġw ith
381
+ Ġju liett
382
+ mal aysian
383
+ Ġvi a
384
+ c u
385
+ r ack
386
+ h ead
387
+ Ġa re
388
+ Ġclimb ing
389
+ vi ctor
390
+ x p
391
+ s ingapore
392
+ v is
393
+ Ġr ight
394
+ ir cu
395
+ ircu it
396
+ Ġn ow
397
+ ar t
398
+ Ġc ircuit
399
+ si a
400
+ si lkair
401
+ ot el
402
+ orn ing
403
+ p art
404
+ im a
405
+ Ġj et
406
+ Ġl ine
407
+ Ġde part
408
+ a v
409
+ Ġm orning
410
+ oin t
411
+ Ġp oint
412
+ s tar
413
+ Ġst op
414
+ Ġl ima
415
+ Ġc lear
416
+ Ġby e
417
+ Ġa d
418
+ Ġl ow
419
+ an kee
420
+ v al
421
+ Ġy ankee
422
+ Ġth ank
423
+ a ve
424
+ Ġar ri
425
+ Ġarri val
426
+ i ve
427
+ a ffirm
428
+ o b
429
+ Ġh otel
430
+ Ġcont inue
431
+ Ġmal indo
432
+ Ġb e
433
+ at h
434
+ Ġs c
435
+ Ġover head
436
+ Ġa sia
437
+ a tar
438
+ no on
439
+ Ġsc ooter
440
+ ff ic
441
+ Ġad vis
442
+ ra ffic
443
+ Ġafter noon
444
+ Ġj oin
445
+ Ġt raffic
446
+ Ġe xp
447
+ go od
448
+ c on
449
+ an g
450
+ ro ger
451
+ Ġwh en
452
+ li de
453
+ Ġs u
454
+ il l
455
+ Ġm a
456
+ ro l
457
+ Ġb ob
458
+ Ġhold ing
459
+ t wo
460
+ Ġh igh
461
+ Ġcont rol
462
+ c e
463
+ sc ooter
464
+ mal indo
465
+ Ġn or
466
+ Ġd ue
467
+ th ree
468
+ u re
469
+ e ight
470
+ Ġy our
471
+ Ġa g
472
+ Ġag ain
473
+ Ġw agon
474
+ ed ic
475
+ m e
476
+ Ġh ave
477
+ Ġfl y
478
+ Ġt rack
479
+ av ing
480
+ Ġle aving
481
+ atar i
482
+ ath er
483
+ Ġwe ather
484
+ Ġst and
485
+ l am
486
+ lam at
487
+ Ġbob is
488
+ ct ion
489
+ Ġse lamat
490
+ le s
491
+ Ġf ul
492
+ Ġg lide
493
+ Ġro ger
494
+ Ġth is
495
+ c opied
496
+ Ġw ill
497
+ Ġful l
498
+ con t
499
+ nin e
500
+ a k
501
+ ay a
502
+ d irect
503
+ e m
504
+ o h
505
+ me o
506
+ ate s
507
+ Ġn e
508
+ p e
509
+ re ss
510
+ oh or
511
+ ir ates
512
+ or re
513
+ w agon
514
+ at ive
515
+ ti on
516
+ at ion
517
+ Ġro meo
518
+ u n
519
+ orre ction
520
+ b ar
521
+ pe ed
522
+ Ġjet star
523
+ j et
524
+ am a
525
+ Ġdepart ure
526
+ Ġle bar
527
+ Ġadvis ed
528
+ Ġp aya
529
+ Ġz one
530
+ Ġc orrection
531
+ a x
532
+ Ġar ama
533
+ b le
534
+ s ky
535
+ g ative
536
+ Ġmi les
537
+ al l
538
+ o k
539
+ be k
540
+ Ġa ffirm
541
+ ul u
542
+ z ero
543
+ al ax
544
+ Ġwith in
545
+ kee p
546
+ m aintain
547
+ Ġar ound
548
+ Ġj ohor
549
+ Ġz ulu
550
+ si tion
551
+ Ġs alax
552
+ Ġsu k
553
+ r unway
554
+ Ġ keep
555
+ t rack
556
+ Ġno bek
557
+ jet star
558
+ r an
559
+ Ġc o
560
+ i al
561
+ y e
562
+ Ġne gative
563
+ ro ss
564
+ an ad
565
+ anad u
566
+ Ġc an
567
+ t e
568
+ h eading
569
+ f or
570
+ c ap
571
+ se ven
572
+ Ġnor th
573
+ m edic
574
+ Ġs peed
575
+ si x
576
+ Ġdescend ing
577
+ Ġb ack
578
+ l ine
579
+ cont inue
580
+ Ġs ay
581
+ q atari
582
+ u p
583
+ n ight
584
+ a st
585
+ b ye
586
+ c lear
587
+ e ct
588
+ Ġexp ress
589
+ Ġc ross
590
+ w ay
591
+ Ġc all
592
+ Ġare a
593
+ it ial
594
+ Ġal l
595
+ Ġapproach ing
596
+ Ġnor mal
597
+ for m
598
+ ' re
599
+ Ġo b
600
+ Ġmaintain ing
601
+ Ġadvis e
602
+ t er
603
+ Ġp o
604
+ Ġexp ect
605
+ Ġo p
606
+ st op
607
+ Ġm edic
608
+ ow er
609
+ l o
610
+ l ight
611
+ Ġin itial
612
+ t ower
613
+ f oxtrot
614
+ Ġq atari
615
+ it ch
616
+ Ġturn s
617
+ Ġsquawk ing
618
+ c k
619
+ c o
620
+ f light
621
+ que n
622
+ ro m
623
+ Ġs h
624
+ em irates
625
+ an stop
626
+ aysi a
627
+ f our
628
+ Ġf rom
629
+ Ġth at
630
+ Ġt ran
631
+ t o
632
+ r il
633
+ Ġs w
634
+ op y
635
+ Ġf anstop
636
+ m en
637
+ ir d
638
+ th ank
639
+ ank an
640
+ Ġe m
641
+ t ouch
642
+ up ta
643
+ Ġa way
644
+ a s
645
+ Ġem irates
646
+ le vel
647
+ f ive
648
+ b ird
649
+ Ġdepart ing
650
+ Ġto p
651
+ Ġinitial ly
652
+ Ġback track
653
+ Ġpo sition
654
+ Ġg upta
655
+ Ġop s
656
+ Ġmal am
657
+ Ġw et
658
+ Ġco m
659
+ b ound
660
+ i an
661
+ st and
662
+ er s
663
+ e xp
664
+ v acate
665
+ e ck
666
+ w h
667
+ Ġu n
668
+ quen c
669
+ Ġgood night
670
+ Ġwe st
671
+ is h
672
+ ril ankan
673
+ Ġsw itch
674
+ t ango
675
+ Ġturn ing
676
+ x i
677
+ Ġch eck
678
+ ar ta
679
+ ak arta
680
+ Ġrequest ing
681
+ r u
682
+ ar ly
683
+ s h
684
+ b ang
685
+ j oin
686
+ re quenc
687
+ requenc y
688
+ c al
689
+ Ġf requency
690
+ l l
691
+ Ġl ate
692
+ Ġgo ing
693
+ h old
694
+ Ġm et
695
+ Ġa head
696
+ p apa
697
+ er n
698
+ o scar
699
+ Ġta xi
700
+ i d
701
+ Ġsuk ri
702
+ ar go
703
+ a b
704
+ et ang
705
+ Ġu h
706
+ Ġc a
707
+ Ġx anadu
708
+ Ġ or
709
+ Ġob st
710
+ Ġp etang
711
+ Ġe arly
712
+ on g
713
+ Ġw a
714
+ i ke
715
+ an ce
716
+ le d
717
+ Ġh and
718
+ Ġj akarta
719
+ Ġe st
720
+ Ġe xt
721
+ Ġsu bang
722
+ cont act
723
+ h ad
724
+ Ġtop or
725
+ Ġobst ac
726
+ ak o
727
+ g ako
728
+ Ġmet ers
729
+ Ġext end
730
+ e cho
731
+ exp ress
732
+ Ġp ro
733
+ Ġh eight
734
+ a u
735
+ o s
736
+ er e
737
+ Ġsuk at
738
+ Ġa n
739
+ Ġsh ort
740
+ g i
741
+ Ġo gako
742
+ Ġwa it
743
+ k ish
744
+ u s
745
+ on ian
746
+ led onian
747
+ ou t
748
+ Ġland ing
749
+ Ġhigh er
750
+ n t
751
+ Ġa ble
752
+ Ġca ledonian
753
+ Ġh e
754
+ t y
755
+ a h
756
+ t ur
757
+ Ġswitch ing
758
+ il co
759
+ con firm
760
+ Ġs ight
761
+ x anadu
762
+ ' s
763
+ Ġch ang
764
+ Ġma ke
765
+ Ġd o
766
+ Ġju st
767
+ it e
768
+ Ġcom men
769
+ Ġair f
770
+ Ġair b
771
+ Ġre qu
772
+ i e
773
+ ed ite
774
+ th er
775
+ a ble
776
+ f a
777
+ Ġpa gi
778
+ Ġb atar
779
+ Ġin form
780
+ Ġth ere
781
+ Ġchang e
782
+ ap pro
783
+ gree n
784
+ im e
785
+ Ġinform ation
786
+ b ravo
787
+ em as
788
+ p t
789
+ ru ct
790
+ b o
791
+ er green
792
+ Ġc opy
793
+ Ġst ruct
794
+ ce ed
795
+ Ġstruct ure
796
+ l u
797
+ Ġm in
798
+ Ġa h
799
+ Ġre join
800
+ ur ther
801
+ Ġg emas
802
+ si erra
803
+ e el
804
+ g lide
805
+ Ġtran sition
806
+ i form
807
+ w e
808
+ Ġre cleared
809
+ a se
810
+ Ġst eel
811
+ r ad
812
+ Ġobstac les
813
+ Ġsi lo
814
+ Ġnorth ern
815
+ Ġf urther
816
+ mal aysia
817
+ Ġtrack ing
818
+ w ind
819
+ Ġan y
820
+ n e
821
+ Ġal fa
822
+ ar d
823
+ v a
824
+ Ġun iform
825
+ s peed
826
+ Ġb ase
827
+ orn e
828
+ Ġpro ceed
829
+ Ġt ime
830
+ Ġn au
831
+ Ġe ast
832
+ ti cal
833
+ Ġjoin ing
834
+ Ġairb orne
835
+ Ġnau tical
836
+ r y
837
+ a i
838
+ rad ar
839
+ Ġs rilankan
840
+ is e
841
+ Ġp ath
842
+ ap le
843
+ n av
844
+ li te
845
+ Ġexp edite
846
+ Ġlow er
847
+ e x
848
+ id ot
849
+ ' ll
850
+ li sh
851
+ h otel
852
+ ab lish
853
+ Ġl o
854
+ Ġr nav
855
+ Ġmal aysia
856
+ un e
857
+ l ow
858
+ Ġ it
859
+ Ġest ablish
860
+ Ġextend ed
861
+ m ain
862
+ aple ss
863
+ Ġfl apless
864
+ speed bird
865
+ i p
866
+ u te
867
+ a fter
868
+ lea se
869
+ Ġspeed bird
870
+ i red
871
+ Ġg ra
872
+ Ġcommen ce
873
+ Ġrequ ired
874
+ Ġk idot
875
+ wh en
876
+ Ġmin ute
877
+ Ġs ky
878
+ r act
879
+ s ay
880
+ Ġgra ss
881
+ appro ved
882
+ ie ld
883
+ u t
884
+ c el
885
+ vis ta
886
+ m ike
887
+ ra ft
888
+ Ġin bound
889
+ Ġshort ly
890
+ Ġtran s
891
+ Ġairf ield
892
+ Ġp ract
893
+ c raft
894
+ Ġre main
895
+ Ġin ter
896
+ lu x
897
+ Ġc argo
898
+ j ohor
899
+ Ġeight y
900
+ Ġdow n
901
+ Ġthe n
902
+ Ġc re
903
+ et i
904
+ Ġp re
905
+ ran s
906
+ eti had
907
+ Ġair craft
908
+ Ġp lease
909
+ Ġthank s
910
+ Ġsu p
911
+ Ġstructure s
912
+ c opy
913
+ wh iskey
914
+ or ry
915
+ Ġcre w
916
+ Ġi f
917
+ Ġa s
918
+ pt une
919
+ Ġs tar
920
+ Ġvis ta
921
+ il able
922
+ Ġpract ise
923
+ s rilankan
924
+ Ġo ff
925
+ on d
926
+ Ġa va
927
+ v ing
928
+ Ġava ilable
929
+ t it
930
+ u de
931
+ Ġw ilco
932
+ Ġcall ing
933
+ Ġa c
934
+ Ġal tit
935
+ Ġaltit ude
936
+ Ġle ave
937
+ it os
938
+ b ack
939
+ Ġh ow
940
+ c argo
941
+ Ġm itos
942
+ tur kish
943
+ Ġi fly
944
+ Ġb el
945
+ al am
946
+ t en
947
+ Ġr ou
948
+ Ġt e
949
+ Ġup wind
950
+ ad em
951
+ Ġk ong
952
+ Ġrou te
953
+ Ġwest bound
954
+ Ġclear ance
955
+ adem y
956
+ Ġbob ag
957
+ r ight
958
+ Ġre ach
959
+ se nt
960
+ en ger
961
+ ave x
962
+ p a
963
+ t ing
special_tokens_map.json CHANGED
@@ -1,7 +1,5 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
 
 
5
  }
tokenizer.json CHANGED
@@ -5,48 +5,12 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "content": "[UNK]",
9
- "single_word": false,
10
- "lstrip": false,
11
- "rstrip": false,
12
- "normalized": false,
13
- "special": true
14
- },
15
- {
16
- "id": 1,
17
  "content": "[PAD]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
  "normalized": false,
22
  "special": true
23
- },
24
- {
25
- "id": 2,
26
- "content": "[CLS]",
27
- "single_word": false,
28
- "lstrip": false,
29
- "rstrip": false,
30
- "normalized": false,
31
- "special": true
32
- },
33
- {
34
- "id": 3,
35
- "content": "[SEP]",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": false,
40
- "special": true
41
- },
42
- {
43
- "id": 4,
44
- "content": "[MASK]",
45
- "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
- "normalized": false,
49
- "special": true
50
  }
51
  ],
52
  "normalizer": {
@@ -57,1016 +21,1996 @@
57
  "lowercase": true
58
  },
59
  "pre_tokenizer": {
60
- "type": "BertPreTokenizer"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  },
62
- "post_processor": null,
63
- "decoder": null,
64
  "model": {
65
- "type": "WordPiece",
66
- "unk_token": "[UNK]",
67
- "continuing_subword_prefix": "##",
68
- "max_input_chars_per_word": 100,
 
 
 
69
  "vocab": {
70
- "[UNK]": 0,
71
- "[PAD]": 1,
72
- "[CLS]": 2,
73
- "[SEP]": 3,
74
- "[MASK]": 4,
75
- "'": 5,
76
- "(": 6,
77
- ")": 7,
78
- "-": 8,
79
- ".": 9,
80
- "8": 10,
81
- "<": 11,
82
- ">": 12,
83
- "@": 13,
84
- "`": 14,
85
- "a": 15,
86
- "b": 16,
87
- "c": 17,
88
- "d": 18,
89
- "e": 19,
90
- "f": 20,
91
- "g": 21,
92
- "h": 22,
93
- "i": 23,
94
- "j": 24,
95
- "k": 25,
96
- "l": 26,
97
- "m": 27,
98
- "n": 28,
99
- "o": 29,
100
- "p": 30,
101
- "q": 31,
102
- "r": 32,
103
- "s": 33,
104
- "t": 34,
105
- "u": 35,
106
- "v": 36,
107
- "w": 37,
108
- "x": 38,
109
- "y": 39,
110
- "z": 40,
111
- "##o": 41,
112
- "##r": 42,
113
- "##t": 43,
114
- "##h": 44,
115
- "##e": 45,
116
- "##l": 46,
117
- "##y": 47,
118
- "##u": 48,
119
- "##f": 49,
120
- "##a": 50,
121
- "##c": 51,
122
- "##i": 52,
123
- "##n": 53,
124
- "##g": 54,
125
- "##s": 55,
126
- "##k": 56,
127
- "##d": 57,
128
- "##b": 58,
129
- "##m": 59,
130
- "##p": 60,
131
- "##w": 61,
132
- "##v": 62,
133
- "##j": 63,
134
- "##x": 64,
135
- "##q": 65,
136
- "##z": 66,
137
- "##8": 67,
138
- "##er": 68,
139
- "##re": 69,
140
- "##ve": 70,
141
- "##in": 71,
142
- "on": 72,
143
- "one": 73,
144
- "th": 74,
145
- "##ree": 75,
146
- "##wo": 76,
147
- "two": 77,
148
- "##ero": 78,
149
- "zero": 79,
150
- "three": 80,
151
- "##ar": 81,
152
- "##ig": 82,
153
- "##igh": 83,
154
- "##ou": 84,
155
- "##ight": 85,
156
- "##nd": 86,
157
- "##eve": 87,
158
- "fi": 88,
159
- "si": 89,
160
- "eight": 90,
161
- "five": 91,
162
- "nin": 92,
163
- "##ay": 93,
164
- "six": 94,
165
- "##even": 95,
166
- "seven": 96,
167
- "##our": 97,
168
- "de": 98,
169
- "##ing": 99,
170
- "four": 100,
171
- "niner": 101,
172
- "##al": 102,
173
- "##le": 103,
174
- "##mb": 104,
175
- "##or": 105,
176
- "##ky": 106,
177
- "sky": 107,
178
- "##ark": 108,
179
- "skyl": 109,
180
- "skylark": 110,
181
- "##ac": 111,
182
- "##nw": 112,
183
- "to": 113,
184
- "##on": 114,
185
- "leve": 115,
186
- "level": 116,
187
- "##ur": 117,
188
- "re": 118,
189
- "##ad": 119,
190
- "er": 120,
191
- "go": 121,
192
- "##and": 122,
193
- "ru": 123,
194
- "##nway": 124,
195
- "runway": 125,
196
- "##li": 126,
197
- "##red": 127,
198
- "##ap": 128,
199
- "##ro": 129,
200
- "##sc": 130,
201
- "##an": 131,
202
- "##ir": 132,
203
- "##ind": 133,
204
- "##mber": 134,
205
- "##ue": 135,
206
- "fl": 136,
207
- "cle": 137,
208
- "##et": 138,
209
- "##tar": 139,
210
- "con": 140,
211
- "flight": 141,
212
- "and": 142,
213
- "##ared": 143,
214
- "##ct": 144,
215
- "cleared": 145,
216
- "se": 146,
217
- "##ke": 147,
218
- "for": 148,
219
- "##is": 149,
220
- "##ch": 150,
221
- "##ot": 151,
222
- "cli": 152,
223
- "climb": 153,
224
- "no": 154,
225
- "##end": 155,
226
- "##im": 156,
227
- "thou": 157,
228
- "thous": 158,
229
- "thousand": 159,
230
- "##um": 160,
231
- "##ed": 161,
232
- "##scend": 162,
233
- "descend": 163,
234
- "##ain": 164,
235
- "sele": 165,
236
- "##at": 166,
237
- "seletar": 167,
238
- "##ump": 168,
239
- "lump": 169,
240
- "lumpur": 170,
241
- "cont": 171,
242
- "##od": 172,
243
- "good": 173,
244
- "##ra": 174,
245
- "dec": 175,
246
- "##imal": 176,
247
- "decimal": 177,
248
- "##pp": 178,
249
- "app": 179,
250
- "appro": 180,
251
- "nove": 181,
252
- "november": 182,
253
- "##st": 183,
254
- "##ow": 184,
255
- "fe": 185,
256
- "feet": 186,
257
- "vi": 187,
258
- "mal": 188,
259
- "cap": 189,
260
- "rad": 190,
261
- "tow": 191,
262
- "##act": 192,
263
- "tower": 193,
264
- "##ead": 194,
265
- "radar": 195,
266
- "##si": 196,
267
- "nine": 197,
268
- "nu": 198,
269
- "number": 199,
270
- "contact": 200,
271
- "red": 201,
272
- "##ff": 202,
273
- "##be": 203,
274
- "##ace": 204,
275
- "sur": 205,
276
- "surf": 206,
277
- "surface": 207,
278
- "wind": 208,
279
- "##not": 209,
280
- "##ly": 210,
281
- "knot": 211,
282
- "knots": 212,
283
- "##gree": 213,
284
- "##xt": 214,
285
- "##op": 215,
286
- "##scar": 216,
287
- "oscar": 217,
288
- "##it": 218,
289
- "##ft": 219,
290
- "degree": 220,
291
- "degrees": 221,
292
- "fo": 222,
293
- "ech": 223,
294
- "echo": 224,
295
- "##ied": 225,
296
- "que": 226,
297
- "##bec": 227,
298
- "quebec": 228,
299
- "dow": 229,
300
- "##rot": 230,
301
- "##rect": 231,
302
- "foxt": 232,
303
- "foxtrot": 233,
304
- "land": 234,
305
- "##ctor": 235,
306
- "le": 236,
307
- "##nwind": 237,
308
- "downwind": 238,
309
- "victor": 239,
310
- "##il": 240,
311
- "##ore": 241,
312
- "##en": 242,
313
- "##que": 243,
314
- "head": 244,
315
- "heading": 245,
316
- "sing": 246,
317
- "##vo": 247,
318
- "singap": 248,
319
- "singapore": 249,
320
- "di": 250,
321
- "bra": 251,
322
- "bravo": 252,
323
- "##fly": 253,
324
- "##ss": 254,
325
- "reque": 255,
326
- "request": 256,
327
- "direct": 257,
328
- "##ning": 258,
329
- "wh": 259,
330
- "##irm": 260,
331
- "##und": 261,
332
- "hund": 262,
333
- "hundred": 263,
334
- "fire": 264,
335
- "firefly": 265,
336
- "##ach": 266,
337
- "tou": 267,
338
- "touch": 268,
339
- "pap": 269,
340
- "papa": 270,
341
- "##ate": 271,
342
- "malay": 272,
343
- "malaysi": 273,
344
- "main": 274,
345
- "##tain": 275,
346
- "maintain": 276,
347
- "you": 277,
348
- "st": 278,
349
- "day": 279,
350
- "approach": 280,
351
- "fin": 281,
352
- "final": 282,
353
- "##ved": 283,
354
- "approved": 284,
355
- "air": 285,
356
- "cop": 286,
357
- "##ta": 287,
358
- "malaysian": 288,
359
- "sil": 289,
360
- "ta": 290,
361
- "##ti": 291,
362
- "mi": 292,
363
- "##ang": 293,
364
- "we": 294,
365
- "ch": 295,
366
- "##ka": 296,
367
- "##ound": 297,
368
- "by": 298,
369
- "silka": 299,
370
- "silkair": 300,
371
- "copied": 301,
372
- "al": 302,
373
- "the": 303,
374
- "vis": 304,
375
- "##oin": 305,
376
- "left": 306,
377
- "ro": 307,
378
- "whis": 308,
379
- "take": 309,
380
- "##key": 310,
381
- "whiskey": 311,
382
- "kil": 312,
383
- "kilo": 313,
384
- "##round": 314,
385
- "##off": 315,
386
- "takeoff": 316,
387
- "##ort": 317,
388
- "##ual": 318,
389
- "##ld": 319,
390
- "pa": 320,
391
- "in": 321,
392
- "##co": 322,
393
- "vac": 323,
394
- "up": 324,
395
- "visual": 325,
396
- "mike": 326,
397
- "eve": 327,
398
- "evening": 328,
399
- "at": 329,
400
- "is": 330,
401
- "##indo": 331,
402
- "vacate": 332,
403
- "del": 333,
404
- "ho": 334,
405
- "##ic": 335,
406
- "tur": 336,
407
- "pass": 337,
408
- "##firm": 338,
409
- "confirm": 339,
410
- "##qu": 340,
411
- "hold": 341,
412
- "read": 342,
413
- "delta": 343,
414
- "##arli": 344,
415
- "##arlie": 345,
416
- "charlie": 346,
417
- "##el": 347,
418
- "malindo": 348,
419
- "##ia": 349,
420
- "##ack": 350,
421
- "sco": 351,
422
- "scoot": 352,
423
- "scooter": 353,
424
- "ind": 354,
425
- "ready": 355,
426
- "##aw": 356,
427
- "##ger": 357,
428
- "wa": 358,
429
- "ray": 359,
430
- "##enti": 360,
431
- "passing": 361,
432
- "tang": 362,
433
- "tango": 363,
434
- "ground": 364,
435
- "##awk": 365,
436
- "##quawk": 366,
437
- "squawk": 367,
438
- "india": 368,
439
- "id": 369,
440
- "jet": 370,
441
- "##fter": 371,
442
- "##ank": 372,
443
- "##ine": 373,
444
- "##fied": 374,
445
- "identi": 375,
446
- "identified": 376,
447
- "roger": 377,
448
- "after": 378,
449
- "ju": 379,
450
- "##ph": 380,
451
- "alph": 381,
452
- "alpha": 382,
453
- "line": 383,
454
- "##ffirm": 384,
455
- "affirm": 385,
456
- "##erra": 386,
457
- "sierra": 387,
458
- "##ion": 388,
459
- "##port": 389,
460
- "##ver": 390,
461
- "report": 391,
462
- "##am": 392,
463
- "clear": 393,
464
- "##gon": 394,
465
- "wagon": 395,
466
- "of": 396,
467
- "contin": 397,
468
- "over": 398,
469
- "continue": 399,
470
- "sir": 400,
471
- "turn": 401,
472
- "##lf": 402,
473
- "ex": 403,
474
- "golf": 404,
475
- "##ett": 405,
476
- "##ri": 406,
477
- "bye": 407,
478
- "juli": 408,
479
- "thank": 409,
480
- "##ith": 410,
481
- "juliett": 411,
482
- "with": 412,
483
- "climbing": 413,
484
- "##ul": 414,
485
- "via": 415,
486
- "tr": 416,
487
- "right": 417,
488
- "##cu": 418,
489
- "are": 419,
490
- "##head": 420,
491
- "##av": 421,
492
- "##her": 422,
493
- "exp": 423,
494
- "now": 424,
495
- "cir": 425,
496
- "##cuit": 426,
497
- "circuit": 427,
498
- "##art": 428,
499
- "low": 429,
500
- "##ima": 430,
501
- "hot": 431,
502
- "mor": 432,
503
- "dep": 433,
504
- "hotel": 434,
505
- "morning": 435,
506
- "depart": 436,
507
- "stop": 437,
508
- "##sia": 438,
509
- "##oint": 439,
510
- "point": 440,
511
- "lima": 441,
512
- "##de": 442,
513
- "jets": 443,
514
- "jetstar": 444,
515
- "ad": 445,
516
- "ar": 446,
517
- "bo": 447,
518
- "##ave": 448,
519
- "##kee": 449,
520
- "yan": 450,
521
- "yankee": 451,
522
- "asia": 452,
523
- "when": 453,
524
- "stand": 454,
525
- "##no": 455,
526
- "##val": 456,
527
- "join": 457,
528
- "arri": 458,
529
- "arrival": 459,
530
- "be": 460,
531
- "wil": 461,
532
- "adv": 462,
533
- "overhead": 463,
534
- "su": 464,
535
- "fly": 465,
536
- "##atar": 466,
537
- "bob": 467,
538
- "afterno": 468,
539
- "afternoon": 469,
540
- "advis": 470,
541
- "##ffic": 471,
542
- "tra": 472,
543
- "traffic": 473,
544
- "ma": 474,
545
- "holding": 475,
546
- "gli": 476,
547
- "glide": 477,
548
- "##aving": 478,
549
- "high": 479,
550
- "leaving": 480,
551
- "##rol": 481,
552
- "control": 482,
553
- "bobis": 483,
554
- "##ce": 484,
555
- "track": 485,
556
- "due": 486,
557
- "ag": 487,
558
- "your": 488,
559
- "med": 489,
560
- "again": 490,
561
- "##ure": 491,
562
- "medic": 492,
563
- "have": 493,
564
- "ne": 494,
565
- "##me": 495,
566
- "##orm": 496,
567
- "qatar": 497,
568
- "will": 498,
569
- "qatari": 499,
570
- "##ma": 500,
571
- "##ather": 501,
572
- "weather": 502,
573
- "sel": 503,
574
- "##amat": 504,
575
- "selamat": 505,
576
- "ful": 506,
577
- "cal": 507,
578
- "##les": 508,
579
- "##ive": 509,
580
- "this": 510,
581
- "full": 511,
582
- "##ak": 512,
583
- "##one": 513,
584
- "rome": 514,
585
- "romeo": 515,
586
- "##oh": 516,
587
- "##ates": 517,
588
- "sp": 518,
589
- "##ress": 519,
590
- "em": 520,
591
- "joh": 521,
592
- "emir": 522,
593
- "johor": 523,
594
- "cor": 524,
595
- "emirates": 525,
596
- "correct": 526,
597
- "express": 527,
598
- "##ative": 528,
599
- "##ation": 529,
600
- "##aya": 530,
601
- "spe": 531,
602
- "correction": 532,
603
- "##bar": 533,
604
- "speed": 534,
605
- "departure": 535,
606
- "paya": 536,
607
- "lebar": 537,
608
- "advised": 538,
609
- "ara": 539,
610
- "##ep": 540,
611
- "arama": 541,
612
- "zone": 542,
613
- "say": 543,
614
- "##ax": 544,
615
- "##ble": 545,
616
- "neg": 546,
617
- "negative": 547,
618
- "back": 548,
619
- "miles": 549,
620
- "sal": 550,
621
- "##bek": 551,
622
- "##tion": 552,
623
- "nobek": 553,
624
- "am": 554,
625
- "within": 555,
626
- "##ulu": 556,
627
- "co": 557,
628
- "salax": 558,
629
- "ke": 559,
630
- "zulu": 560,
631
- "around": 561,
632
- "keep": 562,
633
- "##sition": 563,
634
- "suk": 564,
635
- "can": 565,
636
- "##ect": 566,
637
- "descending": 567,
638
- "##ial": 568,
639
- "##ross": 569,
640
- "xan": 570,
641
- "##adu": 571,
642
- "xanadu": 572,
643
- "cross": 573,
644
- "##se": 574,
645
- "he": 575,
646
- "all": 576,
647
- "nort": 577,
648
- "##te": 578,
649
- "##un": 579,
650
- "call": 580,
651
- "##tr": 581,
652
- "##track": 582,
653
- "backtrack": 583,
654
- "un": 584,
655
- "maintaining": 585,
656
- "##ast": 586,
657
- "approaching": 587,
658
- "ok": 588,
659
- "po": 589,
660
- "area": 590,
661
- "norm": 591,
662
- "##way": 592,
663
- "normal": 593,
664
- "init": 594,
665
- "initial": 595,
666
- "##night": 596,
667
- "##form": 597,
668
- "advise": 598,
669
- "expect": 599,
670
- "ob": 600,
671
- "goodnight": 601,
672
- "op": 602,
673
- "sh": 603,
674
- "sw": 604,
675
- "that": 605,
676
- "##ter": 606,
677
- "squawking": 607,
678
- "##itch": 608,
679
- "turns": 609,
680
- "##go": 610,
681
- "##ck": 611,
682
- "##quen": 612,
683
- "malam": 613,
684
- "##ent": 614,
685
- "##ase": 615,
686
- "fro": 616,
687
- "fan": 617,
688
- "tran": 618,
689
- "from": 619,
690
- "##stop": 620,
691
- "fanstop": 621,
692
- "malaysia": 622,
693
- "##up": 623,
694
- "initially": 624,
695
- "position": 625,
696
- "top": 626,
697
- "copy": 627,
698
- "##ird": 628,
699
- "##ankan": 629,
700
- "gup": 630,
701
- "uh": 631,
702
- "away": 632,
703
- "gupta": 633,
704
- "departing": 634,
705
- "ah": 635,
706
- "ops": 636,
707
- "com": 637,
708
- "going": 638,
709
- "turning": 639,
710
- "switch": 640,
711
- "wet": 641,
712
- "##bird": 642,
713
- "speedbird": 643,
714
- "##ian": 644,
715
- "##bound": 645,
716
- "che": 646,
717
- "##ers": 647,
718
- "west": 648,
719
- "##quenc": 649,
720
- "check": 650,
721
- "requesting": 651,
722
- "##ril": 652,
723
- "sril": 653,
724
- "##ish": 654,
725
- "srilankan": 655,
726
- "jak": 656,
727
- "##th": 657,
728
- "##arta": 658,
729
- "jakarta": 659,
730
- "tax": 660,
731
- "ear": 661,
732
- "##ru": 662,
733
- "early": 663,
734
- "fre": 664,
735
- "taxi": 665,
736
- "late": 666,
737
- "##cal": 667,
738
- "##quency": 668,
739
- "frequency": 669,
740
- "north": 670,
741
- "airf": 671,
742
- "vista": 672,
743
- "rec": 673,
744
- "an": 674,
745
- "car": 675,
746
- "met": 676,
747
- "sukri": 677,
748
- "ahead": 678,
749
- "##ut": 679,
750
- "sub": 680,
751
- "##gi": 681,
752
- "est": 682,
753
- "cargo": 683,
754
- "or": 684,
755
- "obst": 685,
756
- "##ab": 686,
757
- "##etang": 687,
758
- "pro": 688,
759
- "petang": 689,
760
- "##ance": 690,
761
- "ext": 691,
762
- "subang": 692,
763
- "##id": 693,
764
- "##ong": 694,
765
- "do": 695,
766
- "hand": 696,
767
- "topor": 697,
768
- "obstac": 698,
769
- "##au": 699,
770
- "extend": 700,
771
- "eti": 701,
772
- "##had": 702,
773
- "etihad": 703,
774
- "##us": 704,
775
- "##ako": 705,
776
- "og": 706,
777
- "ogako": 707,
778
- "meters": 708,
779
- "sukat": 709,
780
- "east": 710,
781
- "##bo": 711,
782
- "height": 712,
783
- "short": 713,
784
- "wait": 714,
785
- "##ere": 715,
786
- "switching": 716,
787
- "able": 717,
788
- "landing": 718,
789
- "##per": 719,
790
- "higher": 720,
791
- "##ruct": 721,
792
- "##onian": 722,
793
- "##edonian": 723,
794
- "caledonian": 724,
795
- "ifly": 725,
796
- "##sh": 726,
797
- "##ther": 727,
798
- "make": 728,
799
- "just": 729,
800
- "wilco": 730,
801
- "##men": 731,
802
- "chang": 732,
803
- "sight": 733,
804
- "##ath": 734,
805
- "recle": 735,
806
- "turk": 736,
807
- "airb": 737,
808
- "turkish": 738,
809
- "recleared": 739,
810
- "super": 740,
811
- "pagi": 741,
812
- "commen": 742,
813
- "##ite": 743,
814
- "exped": 744,
815
- "inform": 745,
816
- "requ": 746,
817
- "requi": 747,
818
- "##ie": 748,
819
- "expedite": 749,
820
- "batar": 750,
821
- "##fa": 751,
822
- "alfa": 752,
823
- "there": 753,
824
- "change": 754,
825
- "information": 755,
826
- "rej": 756,
827
- "rejoin": 757,
828
- "##able": 758,
829
- "##ime": 759,
830
- "##mas": 760,
831
- "ge": 761,
832
- "##os": 762,
833
- "gemas": 763,
834
- "##pt": 764,
835
- "##ne": 765,
836
- "##green": 766,
837
- "supergreen": 767,
838
- "min": 768,
839
- "struct": 769,
840
- "##ceed": 770,
841
- "structure": 771,
842
- "##em": 772,
843
- "ac": 773,
844
- "##ans": 774,
845
- "fur": 775,
846
- "ste": 776,
847
- "any": 777,
848
- "proceed": 778,
849
- "further": 779,
850
- "tracking": 780,
851
- "transition": 781,
852
- "uni": 782,
853
- "uniform": 783,
854
- "steel": 784,
855
- "##ag": 785,
856
- "obstacles": 786,
857
- "norther": 787,
858
- "northern": 788,
859
- "##lo": 789,
860
- "it": 790,
861
- "##ard": 791,
862
- "joining": 792,
863
- "##va": 793,
864
- "lo": 794,
865
- "base": 795,
866
- "time": 796,
867
- "##orne": 797,
868
- "airborne": 798,
869
- "##ise": 799,
870
- "##ren": 800,
871
- "##auti": 801,
872
- "nauti": 802,
873
- "nautical": 803,
874
- "star": 804,
875
- "##ty": 805,
876
- "raya": 806,
877
- "path": 807,
878
- "##aple": 808,
879
- "eli": 809,
880
- "##wind": 810,
881
- "lower": 811,
882
- "elite": 812,
883
- "rn": 813,
884
- "##ai": 814,
885
- "kid": 815,
886
- "rnav": 816,
887
- "kidot": 817,
888
- "lark": 818,
889
- "ll": 819,
890
- "##lish": 820,
891
- "estab": 821,
892
- "establish": 822,
893
- "inter": 823,
894
- "extended": 824,
895
- "##une": 825,
896
- "flaple": 826,
897
- "flapless": 827,
898
- "eastindo": 828,
899
- "rem": 829,
900
- "gra": 830,
901
- "remain": 831,
902
- "##ute": 832,
903
- "commence": 833,
904
- "##lease": 834,
905
- "required": 835,
906
- "grass": 836,
907
- "minute": 837,
908
- "thanks": 838,
909
- "trans": 839,
910
- "##ract": 840,
911
- "pre": 841,
912
- "##ry": 842,
913
- "down": 843,
914
- "##ield": 844,
915
- "shortly": 845,
916
- "pract": 846,
917
- "##ux": 847,
918
- "inbound": 848,
919
- "airfield": 849,
920
- "please": 850,
921
- "##raft": 851,
922
- "then": 852,
923
- "bel": 853,
924
- "cre": 854,
925
- "##craft": 855,
926
- "as": 856,
927
- "eighty": 857,
928
- "silo": 858,
929
- "##ip": 859,
930
- "station": 860,
931
- "calling": 861,
932
- "aircraft": 862,
933
- "if": 863,
934
- "##cel": 864,
935
- "leave": 865,
936
- "structures": 866,
937
- "##orry": 867,
938
- "crew": 868,
939
- "li": 869,
940
- "sorry": 870,
941
- "rou": 871,
942
- "int": 872,
943
- "##rans": 873,
944
- "off": 874,
945
- "nept": 875,
946
- "neptune": 876,
947
- "practise": 877,
948
- "airfrans": 878,
949
- "lion": 879,
950
- "##es": 880,
951
- "##lux": 881,
952
- "cargolux": 882,
953
- "##ok": 883,
954
- "##vail": 884,
955
- "##by": 885,
956
- "avail": 886,
957
- "alt": 887,
958
- "available": 888,
959
- "bat": 889,
960
- "##ond": 890,
961
- "how": 891,
962
- "##ude": 892,
963
- "##itude": 893,
964
- "altitude": 894,
965
- "mit": 895,
966
- "mitos": 896,
967
- "##ting": 897,
968
- "kong": 898,
969
- "hel": 899,
970
- "upwind": 900,
971
- "clearance": 901,
972
- "westbound": 902,
973
- "route": 903,
974
- "reach": 904,
975
- "##adem": 905,
976
- "academ": 906,
977
- "bobag": 907,
978
- "academy": 908,
979
- "##ill": 909,
980
- "##vi": 910,
981
- "set": 911,
982
- "pres": 912,
983
- "present": 913,
984
- "nave": 914,
985
- "##enger": 915,
986
- "navex": 916,
987
- "ab": 917,
988
- "passenger": 918,
989
- "##avy": 919,
990
- "minutes": 920,
991
- "excel": 921,
992
- "heavy": 922,
993
- "bay": 923,
994
- "##io": 924,
995
- "##so": 925,
996
- "out": 926,
997
- "ver": 927,
998
- "##urren": 928,
999
- "##urrent": 929,
1000
- "current": 930,
1001
- "devi": 931,
1002
- "like": 932,
1003
- "##ould": 933,
1004
- "##alam": 934,
1005
- "radio": 935,
1006
- "sou": 936,
1007
- "##kum": 937,
1008
- "##reak": 938,
1009
- "break": 939,
1010
- "mu": 940,
1011
- "##out": 941,
1012
- "heli": 942,
1013
- "unk": 943,
1014
- "##ment": 944,
1015
- "below": 945,
1016
- "##ex": 946,
1017
- "res": 947,
1018
- "fed": 948,
1019
- "ten": 949,
1020
- "about": 950,
1021
- "very": 951,
1022
- "gun": 952,
1023
- "still": 953,
1024
- "estim": 954,
1025
- "##bye": 955,
1026
- "fedex": 956,
1027
- "goodbye": 957,
1028
- "ass": 958,
1029
- "transm": 959,
1030
- "##ating": 960,
1031
- "stra": 961,
1032
- "##ik": 962,
1033
- "straight": 963,
1034
- "##ll": 964,
1035
- "standing": 965,
1036
- "hello": 966,
1037
- "local": 967,
1038
- "##ah": 968,
1039
- "so": 969,
1040
- "diam": 970,
1041
- "##ention": 971,
1042
- "diamond": 972,
1043
- "##erm": 973,
1044
- "mas": 974,
1045
- "##ung": 975,
1046
- "intention": 976,
1047
- "reaching": 977,
1048
- "see": 978,
1049
- "bang": 979,
1050
- "##ume": 980,
1051
- "##ice": 981,
1052
- "currently": 982,
1053
- "nav": 983,
1054
- "##after": 984,
1055
- "thereafter": 985,
1056
- "resume": 986,
1057
- "masbo": 987,
1058
- "light": 988,
1059
- "navig": 989,
1060
- "sab": 990,
1061
- "deviation": 991,
1062
- "not": 992,
1063
- "navigation": 993,
1064
- "fir": 994,
1065
- "batik": 995,
1066
- "estimate": 996,
1067
- "aro": 997,
1068
- "##aining": 998,
1069
- "pl": 999
1070
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1071
  }
1072
  }
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
 
 
 
 
 
 
 
 
8
  "content": "[PAD]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
  "normalized": false,
13
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
  ],
16
  "normalizer": {
 
21
  "lowercase": true
22
  },
23
  "pre_tokenizer": {
24
+ "type": "ByteLevel",
25
+ "add_prefix_space": false,
26
+ "trim_offsets": true,
27
+ "use_regex": true
28
+ },
29
+ "post_processor": {
30
+ "type": "ByteLevel",
31
+ "add_prefix_space": true,
32
+ "trim_offsets": false,
33
+ "use_regex": true
34
+ },
35
+ "decoder": {
36
+ "type": "ByteLevel",
37
+ "add_prefix_space": true,
38
+ "trim_offsets": true,
39
+ "use_regex": true
40
  },
 
 
41
  "model": {
42
+ "type": "BPE",
43
+ "dropout": null,
44
+ "unk_token": null,
45
+ "continuing_subword_prefix": null,
46
+ "end_of_word_suffix": null,
47
+ "fuse_unk": false,
48
+ "byte_fallback": false,
49
  "vocab": {
50
+ "[PAD]": 0,
51
+ "'": 1,
52
+ "(": 2,
53
+ ")": 3,
54
+ "-": 4,
55
+ ".": 5,
56
+ "8": 6,
57
+ "<": 7,
58
+ ">": 8,
59
+ "@": 9,
60
+ "`": 10,
61
+ "a": 11,
62
+ "b": 12,
63
+ "c": 13,
64
+ "d": 14,
65
+ "e": 15,
66
+ "f": 16,
67
+ "g": 17,
68
+ "h": 18,
69
+ "i": 19,
70
+ "j": 20,
71
+ "k": 21,
72
+ "l": 22,
73
+ "m": 23,
74
+ "n": 24,
75
+ "o": 25,
76
+ "p": 26,
77
+ "q": 27,
78
+ "r": 28,
79
+ "s": 29,
80
+ "t": 30,
81
+ "u": 31,
82
+ "v": 32,
83
+ "w": 33,
84
+ "x": 34,
85
+ "y": 35,
86
+ "z": 36,
87
+ "Ġ": 37,
88
+ "Ġt": 38,
89
+ "er": 39,
90
+ "re": 40,
91
+ "on": 41,
92
+ "Ġf": 42,
93
+ "in": 43,
94
+ "Ġs": 44,
95
+ "ve": 45,
96
+ "one": 46,
97
+ "Ġth": 47,
98
+ "Ġone": 48,
99
+ "ree": 49,
100
+ "wo": 50,
101
+ "Ġz": 51,
102
+ "Ġtwo": 52,
103
+ "ero": 53,
104
+ "Ġzero": 54,
105
+ "Ġthree": 55,
106
+ "ar": 56,
107
+ "ig": 57,
108
+ "igh": 58,
109
+ "ou": 59,
110
+ "le": 60,
111
+ "ight": 61,
112
+ "Ġc": 62,
113
+ "nd": 63,
114
+ "Ġe": 64,
115
+ "Ġn": 65,
116
+ "Ġd": 66,
117
+ "Ġa": 67,
118
+ "Ġse": 68,
119
+ "Ġfi": 69,
120
+ "Ġsi": 70,
121
+ "Ġfive": 71,
122
+ "Ġeight": 72,
123
+ "ven": 73,
124
+ "ay": 74,
125
+ "Ġsix": 75,
126
+ "our": 76,
127
+ "Ġseven": 77,
128
+ "Ġnin": 78,
129
+ "ing": 79,
130
+ "Ġr": 80,
131
+ "al": 81,
132
+ "Ġfour": 82,
133
+ "Ġde": 83,
134
+ "mb": 84,
135
+ "or": 85,
136
+ "ky": 86,
137
+ "Ġle": 87,
138
+ "ark": 88,
139
+ "lark": 89,
140
+ "red": 90,
141
+ "kylark": 91,
142
+ "ac": 92,
143
+ "nw": 93,
144
+ "Ġniner": 94,
145
+ "Ġto": 95,
146
+ "Ġg": 96,
147
+ "vel": 97,
148
+ "Ġl": 98,
149
+ "Ġh": 99,
150
+ "ur": 100,
151
+ "Ġlevel": 101,
152
+ "Ġw": 102,
153
+ "and": 103,
154
+ "ro": 104,
155
+ "ad": 105,
156
+ "unw": 106,
157
+ "unway": 107,
158
+ "sc": 108,
159
+ "ind": 109,
160
+ "li": 110,
161
+ "ap": 111,
162
+ "Ġrunway": 112,
163
+ "Ġm": 113,
164
+ "skylark": 114,
165
+ "Ġgo": 115,
166
+ "an": 116,
167
+ "ir": 117,
168
+ "mber": 118,
169
+ "Ġer": 119,
170
+ "ue": 120,
171
+ "is": 121,
172
+ "et": 122,
173
+ "Ġfl": 123,
174
+ "tar": 124,
175
+ "Ġp": 125,
176
+ "Ġb": 126,
177
+ "lea": 127,
178
+ "leared": 128,
179
+ "ct": 129,
180
+ "no": 130,
181
+ "mal": 131,
182
+ "Ġflight": 132,
183
+ "ke": 133,
184
+ "Ġand": 134,
185
+ "Ġo": 135,
186
+ "Ġcon": 136,
187
+ "Ġv": 137,
188
+ "que": 138,
189
+ "Ġfor": 139,
190
+ "ch": 140,
191
+ "Ġre": 141,
192
+ "limb": 142,
193
+ "end": 143,
194
+ "ous": 144,
195
+ "ousand": 145,
196
+ "Ġthousand": 146,
197
+ "um": 147,
198
+ "scend": 148,
199
+ "Ġk": 149,
200
+ "at": 150,
201
+ "ain": 151,
202
+ "letar": 152,
203
+ "pur": 153,
204
+ "ed": 154,
205
+ "umpur": 155,
206
+ "od": 156,
207
+ "ow": 157,
208
+ "si": 158,
209
+ "ra": 159,
210
+ "Ġcont": 160,
211
+ "Ġcleared": 161,
212
+ "Ġgood": 162,
213
+ "ci": 163,
214
+ "st": 164,
215
+ "cimal": 165,
216
+ "Ġdecimal": 166,
217
+ "Ġclimb": 167,
218
+ "pro": 168,
219
+ "Ġdescend": 169,
220
+ "Ġap": 170,
221
+ "vember": 171,
222
+ "Ġappro": 172,
223
+ "Ġseletar": 173,
224
+ "Ġfe": 174,
225
+ "Ġfeet": 175,
226
+ "Ġskylark": 176,
227
+ "ire": 177,
228
+ "act": 178,
229
+ "ead": 179,
230
+ "Ġrad": 180,
231
+ "Ġy": 181,
232
+ "umber": 182,
233
+ "Ġcap": 183,
234
+ "ff": 184,
235
+ "Ġradar": 185,
236
+ "be": 186,
237
+ "ly": 187,
238
+ "Ġtow": 188,
239
+ "Ġlumpur": 189,
240
+ "Ġtower": 190,
241
+ "Ġcontact": 191,
242
+ "ace": 192,
243
+ "urf": 193,
244
+ "urface": 194,
245
+ "Ġsurface": 195,
246
+ "not": 196,
247
+ "Ġwind": 197,
248
+ "it": 198,
249
+ "Ġknot": 199,
250
+ "Ġknots": 200,
251
+ "gree": 201,
252
+ "xt": 202,
253
+ "de": 203,
254
+ "op": 204,
255
+ "Ġj": 205,
256
+ "nin": 206,
257
+ "scar": 207,
258
+ "Ġnine": 208,
259
+ "ft": 209,
260
+ "Ġdegree": 210,
261
+ "Ġdegrees": 211,
262
+ "cho": 212,
263
+ "ied": 213,
264
+ "quebe": 214,
265
+ "quebec": 215,
266
+ "rot": 216,
267
+ "oxt": 217,
268
+ "oxtrot": 218,
269
+ "Ġquebec": 219,
270
+ "Ġvi": 220,
271
+ "Ġdow": 221,
272
+ "Ġoscar": 222,
273
+ "ctor": 223,
274
+ "nwind": 224,
275
+ "Ġland": 225,
276
+ "Ġecho": 226,
277
+ "Ġdownwind": 227,
278
+ "il": 228,
279
+ "ore": 229,
280
+ "Ġfoxtrot": 230,
281
+ "fly": 231,
282
+ "eading": 232,
283
+ "niner": 233,
284
+ "vo": 234,
285
+ "ingap": 235,
286
+ "ingapore": 236,
287
+ "ravo": 237,
288
+ "quest": 238,
289
+ "ss": 239,
290
+ "irect": 240,
291
+ "irm": 241,
292
+ "Ġrequest": 242,
293
+ "Ġbravo": 243,
294
+ "und": 244,
295
+ "Ġno": 245,
296
+ "undred": 246,
297
+ "Ġhundred": 247,
298
+ "Ġheading": 248,
299
+ "november": 249,
300
+ "ot": 250,
301
+ "ach": 251,
302
+ "Ġwh": 252,
303
+ "ouch": 253,
304
+ "apa": 254,
305
+ "go": 255,
306
+ "ate": 256,
307
+ "aysi": 257,
308
+ "tain": 258,
309
+ "aintain": 259,
310
+ "Ġyou": 260,
311
+ "Ġday": 261,
312
+ "Ġmal": 262,
313
+ "Ġapproach": 263,
314
+ "inal": 264,
315
+ "air": 265,
316
+ "ved": 266,
317
+ "Ġfinal": 267,
318
+ "ta": 268,
319
+ "Ġpapa": 269,
320
+ "Ġred": 270,
321
+ "Ġnumber": 271,
322
+ "Ġtouch": 272,
323
+ "Ġdirect": 273,
324
+ "aysian": 274,
325
+ "Ġapproved": 275,
326
+ "Ġvictor": 276,
327
+ "Ġu": 277,
328
+ "se": 278,
329
+ "cleared": 279,
330
+ "Ġst": 280,
331
+ "Ġta": 281,
332
+ "am": 282,
333
+ "ti": 283,
334
+ "Ġmaintain": 284,
335
+ "Ġthe": 285,
336
+ "lumpur": 286,
337
+ "ound": 287,
338
+ "Ġnovember": 288,
339
+ "lk": 289,
340
+ "Ġi": 290,
341
+ "Ġmi": 291,
342
+ "Ġq": 292,
343
+ "lkair": 293,
344
+ "opied": 294,
345
+ "Ġch": 295,
346
+ "Ġsingapore": 296,
347
+ "Ġair": 297,
348
+ "Ġwe": 298,
349
+ "Ġon": 299,
350
+ "oin": 300,
351
+ "key": 301,
352
+ "iskey": 302,
353
+ "ilo": 303,
354
+ "Ġtake": 304,
355
+ "Ġleft": 305,
356
+ "Ġal": 306,
357
+ "Ġkilo": 307,
358
+ "th": 308,
359
+ "off": 309,
360
+ "ual": 310,
361
+ "Ġwhiskey": 311,
362
+ "Ġby": 312,
363
+ "Ġar": 313,
364
+ "Ġtakeoff": 314,
365
+ "ld": 315,
366
+ "Ġvis": 316,
367
+ "Ġin": 317,
368
+ "Ġpa": 318,
369
+ "Ġup": 319,
370
+ "number": 320,
371
+ "vening": 321,
372
+ "indo": 322,
373
+ "Ġevening": 323,
374
+ "Ġis": 324,
375
+ "acate": 325,
376
+ "en": 326,
377
+ "Ġat": 327,
378
+ "Ġvisual": 328,
379
+ "ic": 329,
380
+ "firm": 330,
381
+ "qu": 331,
382
+ "lta": 332,
383
+ "el": 333,
384
+ "Ġmike": 334,
385
+ "arli": 335,
386
+ "arlie": 336,
387
+ "old": 337,
388
+ "Ġread": 338,
389
+ "Ġpass": 339,
390
+ "ia": 340,
391
+ "Ġx": 341,
392
+ "ack": 342,
393
+ "Ġdelta": 343,
394
+ "oot": 344,
395
+ "ger": 345,
396
+ "ooter": 346,
397
+ "climb": 347,
398
+ "Ġcopied": 348,
399
+ "Ġcharlie": 349,
400
+ "aw": 350,
401
+ "ort": 351,
402
+ "Ġready": 352,
403
+ "Ġtur": 353,
404
+ "Ġfire": 354,
405
+ "Ġfirefly": 355,
406
+ "ango": 356,
407
+ "round": 357,
408
+ "awk": 358,
409
+ "quawk": 359,
410
+ "Ġconfirm": 360,
411
+ "Ġvacate": 361,
412
+ "india": 362,
413
+ "den": 363,
414
+ "Ġsquawk": 364,
415
+ "ag": 365,
416
+ "fter": 366,
417
+ "ank": 367,
418
+ "ray": 368,
419
+ "Ġiden": 369,
420
+ "ine": 370,
421
+ "Ġpassing": 371,
422
+ "tif": 372,
423
+ "tified": 373,
424
+ "Ġground": 374,
425
+ "Ġindia": 375,
426
+ "Ġturn": 376,
427
+ "Ġidentified": 377,
428
+ "Ġhold": 378,
429
+ "seletar": 379,
430
+ "ha": 380,
431
+ "kee": 381,
432
+ "pha": 382,
433
+ "fire": 383,
434
+ "firefly": 384,
435
+ "ffirm": 385,
436
+ "erra": 386,
437
+ "im": 387,
438
+ "Ġju": 388,
439
+ "Ġafter": 389,
440
+ "port": 390,
441
+ "ver": 391,
442
+ "lear": 392,
443
+ "Ġalpha": 393,
444
+ "ion": 394,
445
+ "Ġmalaysian": 395,
446
+ "descend": 396,
447
+ "agon": 397,
448
+ "Ġtango": 398,
449
+ "Ġof": 399,
450
+ "Ġreport": 400,
451
+ "inue": 401,
452
+ "vi": 402,
453
+ "Ġover": 403,
454
+ "lf": 404,
455
+ "Ġro": 405,
456
+ "Ġsir": 406,
457
+ "Ġsierra": 407,
458
+ "ri": 408,
459
+ "ett": 409,
460
+ "Ġgolf": 410,
461
+ "ith": 411,
462
+ "liett": 412,
463
+ "orn": 413,
464
+ "ul": 414,
465
+ "Ġsilkair": 415,
466
+ "Ġwith": 416,
467
+ "Ġjuliett": 417,
468
+ "malaysian": 418,
469
+ "Ġvia": 419,
470
+ "cu": 420,
471
+ "rack": 421,
472
+ "head": 422,
473
+ "Ġare": 423,
474
+ "Ġclimbing": 424,
475
+ "victor": 425,
476
+ "xp": 426,
477
+ "singapore": 427,
478
+ "vis": 428,
479
+ "Ġright": 429,
480
+ "ircu": 430,
481
+ "ircuit": 431,
482
+ "Ġnow": 432,
483
+ "art": 433,
484
+ "Ġcircuit": 434,
485
+ "sia": 435,
486
+ "silkair": 436,
487
+ "otel": 437,
488
+ "orning": 438,
489
+ "part": 439,
490
+ "ima": 440,
491
+ "Ġjet": 441,
492
+ "Ġline": 442,
493
+ "Ġdepart": 443,
494
+ "av": 444,
495
+ "Ġmorning": 445,
496
+ "oint": 446,
497
+ "Ġpoint": 447,
498
+ "star": 448,
499
+ "Ġstop": 449,
500
+ "Ġlima": 450,
501
+ "Ġclear": 451,
502
+ "Ġbye": 452,
503
+ "Ġad": 453,
504
+ "Ġlow": 454,
505
+ "ankee": 455,
506
+ "val": 456,
507
+ "Ġyankee": 457,
508
+ "Ġthank": 458,
509
+ "ave": 459,
510
+ "Ġarri": 460,
511
+ "Ġarrival": 461,
512
+ "ive": 462,
513
+ "affirm": 463,
514
+ "ob": 464,
515
+ "Ġhotel": 465,
516
+ "Ġcontinue": 466,
517
+ "Ġmalindo": 467,
518
+ "Ġbe": 468,
519
+ "ath": 469,
520
+ "Ġsc": 470,
521
+ "Ġoverhead": 471,
522
+ "Ġasia": 472,
523
+ "atar": 473,
524
+ "noon": 474,
525
+ "Ġscooter": 475,
526
+ "ffic": 476,
527
+ "Ġadvis": 477,
528
+ "raffic": 478,
529
+ "Ġafternoon": 479,
530
+ "Ġjoin": 480,
531
+ "Ġtraffic": 481,
532
+ "Ġexp": 482,
533
+ "good": 483,
534
+ "con": 484,
535
+ "ang": 485,
536
+ "roger": 486,
537
+ "Ġwhen": 487,
538
+ "lide": 488,
539
+ "Ġsu": 489,
540
+ "ill": 490,
541
+ "Ġma": 491,
542
+ "rol": 492,
543
+ "Ġbob": 493,
544
+ "Ġholding": 494,
545
+ "two": 495,
546
+ "Ġhigh": 496,
547
+ "Ġcontrol": 497,
548
+ "ce": 498,
549
+ "scooter": 499,
550
+ "malindo": 500,
551
+ "Ġnor": 501,
552
+ "Ġdue": 502,
553
+ "three": 503,
554
+ "ure": 504,
555
+ "eight": 505,
556
+ "Ġyour": 506,
557
+ "Ġag": 507,
558
+ "Ġagain": 508,
559
+ "Ġwagon": 509,
560
+ "edic": 510,
561
+ "me": 511,
562
+ "Ġhave": 512,
563
+ "Ġfly": 513,
564
+ "Ġtrack": 514,
565
+ "aving": 515,
566
+ "Ġleaving": 516,
567
+ "atari": 517,
568
+ "ather": 518,
569
+ "Ġweather": 519,
570
+ "Ġstand": 520,
571
+ "lam": 521,
572
+ "lamat": 522,
573
+ "Ġbobis": 523,
574
+ "ction": 524,
575
+ "Ġselamat": 525,
576
+ "les": 526,
577
+ "Ġful": 527,
578
+ "Ġglide": 528,
579
+ "Ġroger": 529,
580
+ "Ġthis": 530,
581
+ "copied": 531,
582
+ "Ġwill": 532,
583
+ "Ġfull": 533,
584
+ "cont": 534,
585
+ "nine": 535,
586
+ "ak": 536,
587
+ "aya": 537,
588
+ "direct": 538,
589
+ "em": 539,
590
+ "oh": 540,
591
+ "meo": 541,
592
+ "ates": 542,
593
+ "Ġne": 543,
594
+ "pe": 544,
595
+ "ress": 545,
596
+ "ohor": 546,
597
+ "irates": 547,
598
+ "orre": 548,
599
+ "wagon": 549,
600
+ "ative": 550,
601
+ "tion": 551,
602
+ "ation": 552,
603
+ "Ġromeo": 553,
604
+ "un": 554,
605
+ "orrection": 555,
606
+ "bar": 556,
607
+ "peed": 557,
608
+ "Ġjetstar": 558,
609
+ "jet": 559,
610
+ "ama": 560,
611
+ "Ġdeparture": 561,
612
+ "Ġlebar": 562,
613
+ "Ġadvised": 563,
614
+ "Ġpaya": 564,
615
+ "Ġzone": 565,
616
+ "Ġcorrection": 566,
617
+ "ax": 567,
618
+ "Ġarama": 568,
619
+ "ble": 569,
620
+ "sky": 570,
621
+ "gative": 571,
622
+ "Ġmiles": 572,
623
+ "all": 573,
624
+ "ok": 574,
625
+ "bek": 575,
626
+ "Ġaffirm": 576,
627
+ "ulu": 577,
628
+ "zero": 578,
629
+ "alax": 579,
630
+ "Ġwithin": 580,
631
+ "keep": 581,
632
+ "maintain": 582,
633
+ "Ġaround": 583,
634
+ "Ġjohor": 584,
635
+ "Ġzulu": 585,
636
+ "sition": 586,
637
+ "Ġsalax": 587,
638
+ "Ġsuk": 588,
639
+ "runway": 589,
640
+ "Ġkeep": 590,
641
+ "track": 591,
642
+ "Ġnobek": 592,
643
+ "jetstar": 593,
644
+ "ran": 594,
645
+ "Ġco": 595,
646
+ "ial": 596,
647
+ "ye": 597,
648
+ "Ġnegative": 598,
649
+ "ross": 599,
650
+ "anad": 600,
651
+ "anadu": 601,
652
+ "Ġcan": 602,
653
+ "te": 603,
654
+ "heading": 604,
655
+ "for": 605,
656
+ "cap": 606,
657
+ "seven": 607,
658
+ "Ġnorth": 608,
659
+ "medic": 609,
660
+ "Ġspeed": 610,
661
+ "six": 611,
662
+ "Ġdescending": 612,
663
+ "Ġback": 613,
664
+ "line": 614,
665
+ "continue": 615,
666
+ "Ġsay": 616,
667
+ "qatari": 617,
668
+ "up": 618,
669
+ "night": 619,
670
+ "ast": 620,
671
+ "bye": 621,
672
+ "clear": 622,
673
+ "ect": 623,
674
+ "Ġexpress": 624,
675
+ "Ġcross": 625,
676
+ "way": 626,
677
+ "Ġcall": 627,
678
+ "Ġarea": 628,
679
+ "itial": 629,
680
+ "Ġall": 630,
681
+ "Ġapproaching": 631,
682
+ "Ġnormal": 632,
683
+ "form": 633,
684
+ "'re": 634,
685
+ "Ġob": 635,
686
+ "Ġmaintaining": 636,
687
+ "Ġadvise": 637,
688
+ "ter": 638,
689
+ "Ġpo": 639,
690
+ "Ġexpect": 640,
691
+ "Ġop": 641,
692
+ "stop": 642,
693
+ "Ġmedic": 643,
694
+ "ower": 644,
695
+ "lo": 645,
696
+ "light": 646,
697
+ "Ġinitial": 647,
698
+ "tower": 648,
699
+ "foxtrot": 649,
700
+ "Ġqatari": 650,
701
+ "itch": 651,
702
+ "Ġturns": 652,
703
+ "Ġsquawking": 653,
704
+ "ck": 654,
705
+ "co": 655,
706
+ "flight": 656,
707
+ "quen": 657,
708
+ "rom": 658,
709
+ "Ġsh": 659,
710
+ "emirates": 660,
711
+ "anstop": 661,
712
+ "aysia": 662,
713
+ "four": 663,
714
+ "Ġfrom": 664,
715
+ "Ġthat": 665,
716
+ "Ġtran": 666,
717
+ "to": 667,
718
+ "ril": 668,
719
+ "Ġsw": 669,
720
+ "opy": 670,
721
+ "Ġfanstop": 671,
722
+ "men": 672,
723
+ "ird": 673,
724
+ "thank": 674,
725
+ "ankan": 675,
726
+ "Ġem": 676,
727
+ "touch": 677,
728
+ "upta": 678,
729
+ "Ġaway": 679,
730
+ "as": 680,
731
+ "Ġemirates": 681,
732
+ "level": 682,
733
+ "five": 683,
734
+ "bird": 684,
735
+ "Ġdeparting": 685,
736
+ "Ġtop": 686,
737
+ "Ġinitially": 687,
738
+ "Ġbacktrack": 688,
739
+ "Ġposition": 689,
740
+ "Ġgupta": 690,
741
+ "Ġops": 691,
742
+ "Ġmalam": 692,
743
+ "Ġwet": 693,
744
+ "Ġcom": 694,
745
+ "bound": 695,
746
+ "ian": 696,
747
+ "stand": 697,
748
+ "ers": 698,
749
+ "exp": 699,
750
+ "vacate": 700,
751
+ "eck": 701,
752
+ "wh": 702,
753
+ "Ġun": 703,
754
+ "quenc": 704,
755
+ "Ġgoodnight": 705,
756
+ "Ġwest": 706,
757
+ "ish": 707,
758
+ "rilankan": 708,
759
+ "Ġswitch": 709,
760
+ "tango": 710,
761
+ "Ġturning": 711,
762
+ "xi": 712,
763
+ "Ġcheck": 713,
764
+ "arta": 714,
765
+ "akarta": 715,
766
+ "Ġrequesting": 716,
767
+ "ru": 717,
768
+ "arly": 718,
769
+ "sh": 719,
770
+ "bang": 720,
771
+ "join": 721,
772
+ "requenc": 722,
773
+ "requency": 723,
774
+ "cal": 724,
775
+ "Ġfrequency": 725,
776
+ "ll": 726,
777
+ "Ġlate": 727,
778
+ "Ġgoing": 728,
779
+ "hold": 729,
780
+ "Ġmet": 730,
781
+ "Ġahead": 731,
782
+ "papa": 732,
783
+ "ern": 733,
784
+ "oscar": 734,
785
+ "Ġtaxi": 735,
786
+ "id": 736,
787
+ "Ġsukri": 737,
788
+ "argo": 738,
789
+ "ab": 739,
790
+ "etang": 740,
791
+ "Ġuh": 741,
792
+ "Ġca": 742,
793
+ "Ġxanadu": 743,
794
+ "Ġor": 744,
795
+ "Ġobst": 745,
796
+ "Ġpetang": 746,
797
+ "Ġearly": 747,
798
+ "ong": 748,
799
+ "Ġwa": 749,
800
+ "ike": 750,
801
+ "ance": 751,
802
+ "led": 752,
803
+ "Ġhand": 753,
804
+ "Ġjakarta": 754,
805
+ "Ġest": 755,
806
+ "Ġext": 756,
807
+ "Ġsubang": 757,
808
+ "contact": 758,
809
+ "had": 759,
810
+ "Ġtopor": 760,
811
+ "Ġobstac": 761,
812
+ "ako": 762,
813
+ "gako": 763,
814
+ "Ġmeters": 764,
815
+ "Ġextend": 765,
816
+ "echo": 766,
817
+ "express": 767,
818
+ "Ġpro": 768,
819
+ "Ġheight": 769,
820
+ "au": 770,
821
+ "os": 771,
822
+ "ere": 772,
823
+ "Ġsukat": 773,
824
+ "Ġan": 774,
825
+ "Ġshort": 775,
826
+ "gi": 776,
827
+ "Ġogako": 777,
828
+ "Ġwait": 778,
829
+ "kish": 779,
830
+ "us": 780,
831
+ "onian": 781,
832
+ "ledonian": 782,
833
+ "out": 783,
834
+ "Ġlanding": 784,
835
+ "Ġhigher": 785,
836
+ "nt": 786,
837
+ "Ġable": 787,
838
+ "Ġcaledonian": 788,
839
+ "Ġhe": 789,
840
+ "ty": 790,
841
+ "ah": 791,
842
+ "tur": 792,
843
+ "Ġswitching": 793,
844
+ "ilco": 794,
845
+ "confirm": 795,
846
+ "Ġsight": 796,
847
+ "xanadu": 797,
848
+ "'s": 798,
849
+ "Ġchang": 799,
850
+ "Ġmake": 800,
851
+ "Ġdo": 801,
852
+ "Ġjust": 802,
853
+ "ite": 803,
854
+ "Ġcommen": 804,
855
+ "Ġairf": 805,
856
+ "Ġairb": 806,
857
+ "Ġrequ": 807,
858
+ "ie": 808,
859
+ "edite": 809,
860
+ "ther": 810,
861
+ "able": 811,
862
+ "fa": 812,
863
+ "Ġpagi": 813,
864
+ "Ġbatar": 814,
865
+ "Ġinform": 815,
866
+ "Ġthere": 816,
867
+ "Ġchange": 817,
868
+ "appro": 818,
869
+ "green": 819,
870
+ "ime": 820,
871
+ "Ġinformation": 821,
872
+ "bravo": 822,
873
+ "emas": 823,
874
+ "pt": 824,
875
+ "ruct": 825,
876
+ "bo": 826,
877
+ "ergreen": 827,
878
+ "Ġcopy": 828,
879
+ "Ġstruct": 829,
880
+ "ceed": 830,
881
+ "Ġstructure": 831,
882
+ "lu": 832,
883
+ "Ġmin": 833,
884
+ "Ġah": 834,
885
+ "Ġrejoin": 835,
886
+ "urther": 836,
887
+ "Ġgemas": 837,
888
+ "sierra": 838,
889
+ "eel": 839,
890
+ "glide": 840,
891
+ "Ġtransition": 841,
892
+ "iform": 842,
893
+ "we": 843,
894
+ "Ġrecleared": 844,
895
+ "ase": 845,
896
+ "Ġsteel": 846,
897
+ "rad": 847,
898
+ "Ġobstacles": 848,
899
+ "Ġsilo": 849,
900
+ "Ġnorthern": 850,
901
+ "Ġfurther": 851,
902
+ "malaysia": 852,
903
+ "Ġtracking": 853,
904
+ "wind": 854,
905
+ "Ġany": 855,
906
+ "ne": 856,
907
+ "Ġalfa": 857,
908
+ "ard": 858,
909
+ "va": 859,
910
+ "Ġuniform": 860,
911
+ "speed": 861,
912
+ "Ġbase": 862,
913
+ "orne": 863,
914
+ "Ġproceed": 864,
915
+ "Ġtime": 865,
916
+ "Ġnau": 866,
917
+ "Ġeast": 867,
918
+ "tical": 868,
919
+ "Ġjoining": 869,
920
+ "Ġairborne": 870,
921
+ "Ġnautical": 871,
922
+ "ry": 872,
923
+ "ai": 873,
924
+ "radar": 874,
925
+ "Ġsrilankan": 875,
926
+ "ise": 876,
927
+ "Ġpath": 877,
928
+ "aple": 878,
929
+ "nav": 879,
930
+ "lite": 880,
931
+ "Ġexpedite": 881,
932
+ "Ġlower": 882,
933
+ "ex": 883,
934
+ "idot": 884,
935
+ "'ll": 885,
936
+ "lish": 886,
937
+ "hotel": 887,
938
+ "ablish": 888,
939
+ "Ġlo": 889,
940
+ "Ġrnav": 890,
941
+ "Ġmalaysia": 891,
942
+ "une": 892,
943
+ "low": 893,
944
+ "Ġit": 894,
945
+ "Ġestablish": 895,
946
+ "Ġextended": 896,
947
+ "main": 897,
948
+ "apless": 898,
949
+ "Ġflapless": 899,
950
+ "speedbird": 900,
951
+ "ip": 901,
952
+ "ute": 902,
953
+ "after": 903,
954
+ "lease": 904,
955
+ "Ġspeedbird": 905,
956
+ "ired": 906,
957
+ "Ġgra": 907,
958
+ "Ġcommence": 908,
959
+ "Ġrequired": 909,
960
+ "Ġkidot": 910,
961
+ "when": 911,
962
+ "Ġminute": 912,
963
+ "Ġsky": 913,
964
+ "ract": 914,
965
+ "say": 915,
966
+ "Ġgrass": 916,
967
+ "approved": 917,
968
+ "ield": 918,
969
+ "ut": 919,
970
+ "cel": 920,
971
+ "vista": 921,
972
+ "mike": 922,
973
+ "raft": 923,
974
+ "Ġinbound": 924,
975
+ "Ġshortly": 925,
976
+ "Ġtrans": 926,
977
+ "Ġairfield": 927,
978
+ "Ġpract": 928,
979
+ "craft": 929,
980
+ "Ġremain": 930,
981
+ "Ġinter": 931,
982
+ "lux": 932,
983
+ "Ġcargo": 933,
984
+ "johor": 934,
985
+ "Ġeighty": 935,
986
+ "Ġdown": 936,
987
+ "Ġthen": 937,
988
+ "Ġcre": 938,
989
+ "eti": 939,
990
+ "Ġpre": 940,
991
+ "rans": 941,
992
+ "etihad": 942,
993
+ "Ġaircraft": 943,
994
+ "Ġplease": 944,
995
+ "Ġthanks": 945,
996
+ "Ġsup": 946,
997
+ "Ġstructures": 947,
998
+ "copy": 948,
999
+ "whiskey": 949,
1000
+ "orry": 950,
1001
+ "Ġcrew": 951,
1002
+ "Ġif": 952,
1003
+ "Ġas": 953,
1004
+ "ptune": 954,
1005
+ "Ġstar": 955,
1006
+ "Ġvista": 956,
1007
+ "ilable": 957,
1008
+ "Ġpractise": 958,
1009
+ "srilankan": 959,
1010
+ "Ġoff": 960,
1011
+ "ond": 961,
1012
+ "Ġava": 962,
1013
+ "ving": 963,
1014
+ "Ġavailable": 964,
1015
+ "tit": 965,
1016
+ "ude": 966,
1017
+ "Ġwilco": 967,
1018
+ "Ġcalling": 968,
1019
+ "Ġac": 969,
1020
+ "Ġaltit": 970,
1021
+ "Ġaltitude": 971,
1022
+ "Ġleave": 972,
1023
+ "itos": 973,
1024
+ "back": 974,
1025
+ "Ġhow": 975,
1026
+ "cargo": 976,
1027
+ "Ġmitos": 977,
1028
+ "turkish": 978,
1029
+ "Ġifly": 979,
1030
+ "Ġbel": 980,
1031
+ "alam": 981,
1032
+ "ten": 982,
1033
+ "Ġrou": 983,
1034
+ "Ġte": 984,
1035
+ "Ġupwind": 985,
1036
+ "adem": 986,
1037
+ "Ġkong": 987,
1038
+ "Ġroute": 988,
1039
+ "Ġwestbound": 989,
1040
+ "Ġclearance": 990,
1041
+ "ademy": 991,
1042
+ "Ġbobag": 992,
1043
+ "right": 993,
1044
+ "Ġreach": 994,
1045
+ "sent": 995,
1046
+ "enger": 996,
1047
+ "avex": 997,
1048
+ "pa": 998,
1049
+ "ting": 999
1050
+ },
1051
+ "merges": [
1052
+ "Ġ t",
1053
+ "e r",
1054
+ "r e",
1055
+ "o n",
1056
+ "Ġ f",
1057
+ "i n",
1058
+ "Ġ s",
1059
+ "v e",
1060
+ "on e",
1061
+ "Ġt h",
1062
+ "Ġ one",
1063
+ "re e",
1064
+ "w o",
1065
+ "Ġ z",
1066
+ "Ġt wo",
1067
+ "er o",
1068
+ "Ġz ero",
1069
+ "Ġth ree",
1070
+ "a r",
1071
+ "i g",
1072
+ "ig h",
1073
+ "o u",
1074
+ "l e",
1075
+ "igh t",
1076
+ "Ġ c",
1077
+ "n d",
1078
+ "Ġ e",
1079
+ "Ġ n",
1080
+ "Ġ d",
1081
+ "Ġ a",
1082
+ "Ġs e",
1083
+ "Ġf i",
1084
+ "Ġs i",
1085
+ "Ġfi ve",
1086
+ "Ġe ight",
1087
+ "ve n",
1088
+ "a y",
1089
+ "Ġsi x",
1090
+ "ou r",
1091
+ "Ġse ven",
1092
+ "Ġn in",
1093
+ "in g",
1094
+ "Ġ r",
1095
+ "a l",
1096
+ "Ġf our",
1097
+ "Ġd e",
1098
+ "m b",
1099
+ "o r",
1100
+ "k y",
1101
+ "Ġ le",
1102
+ "ar k",
1103
+ "l ark",
1104
+ "re d",
1105
+ "ky lark",
1106
+ "a c",
1107
+ "n w",
1108
+ "Ġnin er",
1109
+ "Ġt o",
1110
+ "Ġ g",
1111
+ "ve l",
1112
+ "Ġ l",
1113
+ "Ġ h",
1114
+ "u r",
1115
+ "Ġle vel",
1116
+ "Ġ w",
1117
+ "a nd",
1118
+ "r o",
1119
+ "a d",
1120
+ "u nw",
1121
+ "unw ay",
1122
+ "s c",
1123
+ "in d",
1124
+ "l i",
1125
+ "a p",
1126
+ "Ġr unway",
1127
+ "Ġ m",
1128
+ "s kylark",
1129
+ "Ġg o",
1130
+ "a n",
1131
+ "i r",
1132
+ "mb er",
1133
+ "Ġ er",
1134
+ "u e",
1135
+ "i s",
1136
+ "e t",
1137
+ "Ġf l",
1138
+ "t ar",
1139
+ "Ġ p",
1140
+ "Ġ b",
1141
+ "le a",
1142
+ "lea red",
1143
+ "c t",
1144
+ "n o",
1145
+ "m al",
1146
+ "Ġfl ight",
1147
+ "k e",
1148
+ "Ġa nd",
1149
+ "Ġ o",
1150
+ "Ġc on",
1151
+ "Ġ v",
1152
+ "q ue",
1153
+ "Ġf or",
1154
+ "c h",
1155
+ "Ġ re",
1156
+ "li mb",
1157
+ "e nd",
1158
+ "ou s",
1159
+ "ous and",
1160
+ "Ġth ousand",
1161
+ "u m",
1162
+ "sc end",
1163
+ "Ġ k",
1164
+ "a t",
1165
+ "a in",
1166
+ "le tar",
1167
+ "p ur",
1168
+ "e d",
1169
+ "um pur",
1170
+ "o d",
1171
+ "o w",
1172
+ "s i",
1173
+ "r a",
1174
+ "Ġcon t",
1175
+ "Ġc leared",
1176
+ "Ġgo od",
1177
+ "c i",
1178
+ "s t",
1179
+ "ci mal",
1180
+ "Ġde cimal",
1181
+ "Ġc limb",
1182
+ "p ro",
1183
+ "Ġde scend",
1184
+ "Ġa p",
1185
+ "ve mber",
1186
+ "Ġap pro",
1187
+ "Ġse letar",
1188
+ "Ġf e",
1189
+ "Ġfe et",
1190
+ "Ġs kylark",
1191
+ "i re",
1192
+ "ac t",
1193
+ "e ad",
1194
+ "Ġr ad",
1195
+ "Ġ y",
1196
+ "u mber",
1197
+ "Ġc ap",
1198
+ "f f",
1199
+ "Ġrad ar",
1200
+ "b e",
1201
+ "l y",
1202
+ "Ġto w",
1203
+ "Ġl umpur",
1204
+ "Ġtow er",
1205
+ "Ġcont act",
1206
+ "ac e",
1207
+ "ur f",
1208
+ "urf ace",
1209
+ "Ġs urface",
1210
+ "no t",
1211
+ "Ġw ind",
1212
+ "i t",
1213
+ "Ġk not",
1214
+ "Ġknot s",
1215
+ "g ree",
1216
+ "x t",
1217
+ "d e",
1218
+ "o p",
1219
+ "Ġ j",
1220
+ "n in",
1221
+ "sc ar",
1222
+ "Ġnin e",
1223
+ "f t",
1224
+ "Ġde gree",
1225
+ "Ġdegree s",
1226
+ "ch o",
1227
+ "i ed",
1228
+ "que be",
1229
+ "quebe c",
1230
+ "ro t",
1231
+ "o xt",
1232
+ "oxt rot",
1233
+ "Ġ quebec",
1234
+ "Ġv i",
1235
+ "Ġd ow",
1236
+ "Ġo scar",
1237
+ "ct or",
1238
+ "nw ind",
1239
+ "Ġl and",
1240
+ "Ġe cho",
1241
+ "Ġdow nwind",
1242
+ "i l",
1243
+ "o re",
1244
+ "Ġf oxtrot",
1245
+ "f ly",
1246
+ "ead ing",
1247
+ "nin er",
1248
+ "v o",
1249
+ "ing ap",
1250
+ "ingap ore",
1251
+ "ra vo",
1252
+ "que st",
1253
+ "s s",
1254
+ "ire ct",
1255
+ "ir m",
1256
+ "Ġre quest",
1257
+ "Ġb ravo",
1258
+ "u nd",
1259
+ "Ġn o",
1260
+ "und red",
1261
+ "Ġh undred",
1262
+ "Ġh eading",
1263
+ "no vember",
1264
+ "o t",
1265
+ "ac h",
1266
+ "Ġw h",
1267
+ "ou ch",
1268
+ "ap a",
1269
+ "g o",
1270
+ "at e",
1271
+ "ay si",
1272
+ "t ain",
1273
+ "ain tain",
1274
+ "Ġy ou",
1275
+ "Ġd ay",
1276
+ "Ġm al",
1277
+ "Ġappro ach",
1278
+ "in al",
1279
+ "a ir",
1280
+ "ve d",
1281
+ "Ġf inal",
1282
+ "t a",
1283
+ "Ġp apa",
1284
+ "Ġ red",
1285
+ "Ġn umber",
1286
+ "Ġt ouch",
1287
+ "Ġd irect",
1288
+ "aysi an",
1289
+ "Ġappro ved",
1290
+ "Ġvi ctor",
1291
+ "Ġ u",
1292
+ "s e",
1293
+ "c leared",
1294
+ "Ġs t",
1295
+ "Ġt a",
1296
+ "a m",
1297
+ "t i",
1298
+ "Ġm aintain",
1299
+ "Ġth e",
1300
+ "l umpur",
1301
+ "ou nd",
1302
+ "Ġno vember",
1303
+ "l k",
1304
+ "Ġ i",
1305
+ "Ġm i",
1306
+ "Ġ q",
1307
+ "lk air",
1308
+ "op ied",
1309
+ "Ġc h",
1310
+ "Ġs ingapore",
1311
+ "Ġa ir",
1312
+ "Ġw e",
1313
+ "Ġ on",
1314
+ "o in",
1315
+ "ke y",
1316
+ "is key",
1317
+ "il o",
1318
+ "Ġta ke",
1319
+ "Ġle ft",
1320
+ "Ġa l",
1321
+ "Ġk ilo",
1322
+ "t h",
1323
+ "o ff",
1324
+ "u al",
1325
+ "Ġwh iskey",
1326
+ "Ġb y",
1327
+ "Ġ ar",
1328
+ "Ġtake off",
1329
+ "l d",
1330
+ "Ġv is",
1331
+ "Ġ in",
1332
+ "Ġp a",
1333
+ "Ġu p",
1334
+ "n umber",
1335
+ "ven ing",
1336
+ "ind o",
1337
+ "Ġe vening",
1338
+ "Ġ is",
1339
+ "ac ate",
1340
+ "e n",
1341
+ "Ġa t",
1342
+ "Ġvis ual",
1343
+ "i c",
1344
+ "f irm",
1345
+ "q u",
1346
+ "l ta",
1347
+ "e l",
1348
+ "Ġmi ke",
1349
+ "ar li",
1350
+ "arli e",
1351
+ "o ld",
1352
+ "Ġre ad",
1353
+ "Ġpa ss",
1354
+ "i a",
1355
+ "Ġ x",
1356
+ "ac k",
1357
+ "Ġde lta",
1358
+ "o ot",
1359
+ "g er",
1360
+ "oot er",
1361
+ "c limb",
1362
+ "Ġc opied",
1363
+ "Ġch arlie",
1364
+ "a w",
1365
+ "or t",
1366
+ "Ġread y",
1367
+ "Ġt ur",
1368
+ "Ġfi re",
1369
+ "Ġfire fly",
1370
+ "an go",
1371
+ "r ound",
1372
+ "aw k",
1373
+ "qu awk",
1374
+ "Ġcon firm",
1375
+ "Ġv acate",
1376
+ "ind ia",
1377
+ "de n",
1378
+ "Ġs quawk",
1379
+ "a g",
1380
+ "ft er",
1381
+ "an k",
1382
+ "r ay",
1383
+ "Ġi den",
1384
+ "in e",
1385
+ "Ġpass ing",
1386
+ "ti f",
1387
+ "tif ied",
1388
+ "Ġg round",
1389
+ "Ġ india",
1390
+ "Ġtur n",
1391
+ "Ġiden tified",
1392
+ "Ġh old",
1393
+ "se letar",
1394
+ "h a",
1395
+ "ke e",
1396
+ "p ha",
1397
+ "f ire",
1398
+ "fire fly",
1399
+ "ff irm",
1400
+ "er ra",
1401
+ "i m",
1402
+ "Ġj u",
1403
+ "Ġa fter",
1404
+ "p ort",
1405
+ "v er",
1406
+ "le ar",
1407
+ "Ġal pha",
1408
+ "i on",
1409
+ "Ġmal aysian",
1410
+ "de scend",
1411
+ "ag on",
1412
+ "Ġt ango",
1413
+ "Ġo f",
1414
+ "Ġre port",
1415
+ "in ue",
1416
+ "v i",
1417
+ "Ġo ver",
1418
+ "l f",
1419
+ "Ġr o",
1420
+ "Ġsi r",
1421
+ "Ġsi erra",
1422
+ "r i",
1423
+ "et t",
1424
+ "Ġgo lf",
1425
+ "it h",
1426
+ "li ett",
1427
+ "or n",
1428
+ "u l",
1429
+ "Ġsi lkair",
1430
+ "Ġw ith",
1431
+ "Ġju liett",
1432
+ "mal aysian",
1433
+ "Ġvi a",
1434
+ "c u",
1435
+ "r ack",
1436
+ "h ead",
1437
+ "Ġa re",
1438
+ "Ġclimb ing",
1439
+ "vi ctor",
1440
+ "x p",
1441
+ "s ingapore",
1442
+ "v is",
1443
+ "Ġr ight",
1444
+ "ir cu",
1445
+ "ircu it",
1446
+ "Ġn ow",
1447
+ "ar t",
1448
+ "Ġc ircuit",
1449
+ "si a",
1450
+ "si lkair",
1451
+ "ot el",
1452
+ "orn ing",
1453
+ "p art",
1454
+ "im a",
1455
+ "Ġj et",
1456
+ "Ġl ine",
1457
+ "Ġde part",
1458
+ "a v",
1459
+ "Ġm orning",
1460
+ "oin t",
1461
+ "Ġp oint",
1462
+ "s tar",
1463
+ "Ġst op",
1464
+ "Ġl ima",
1465
+ "Ġc lear",
1466
+ "Ġby e",
1467
+ "Ġa d",
1468
+ "Ġl ow",
1469
+ "an kee",
1470
+ "v al",
1471
+ "Ġy ankee",
1472
+ "Ġth ank",
1473
+ "a ve",
1474
+ "Ġar ri",
1475
+ "Ġarri val",
1476
+ "i ve",
1477
+ "a ffirm",
1478
+ "o b",
1479
+ "Ġh otel",
1480
+ "Ġcont inue",
1481
+ "Ġmal indo",
1482
+ "Ġb e",
1483
+ "at h",
1484
+ "Ġs c",
1485
+ "Ġover head",
1486
+ "Ġa sia",
1487
+ "a tar",
1488
+ "no on",
1489
+ "Ġsc ooter",
1490
+ "ff ic",
1491
+ "Ġad vis",
1492
+ "ra ffic",
1493
+ "Ġafter noon",
1494
+ "Ġj oin",
1495
+ "Ġt raffic",
1496
+ "Ġe xp",
1497
+ "go od",
1498
+ "c on",
1499
+ "an g",
1500
+ "ro ger",
1501
+ "Ġwh en",
1502
+ "li de",
1503
+ "Ġs u",
1504
+ "il l",
1505
+ "Ġm a",
1506
+ "ro l",
1507
+ "Ġb ob",
1508
+ "Ġhold ing",
1509
+ "t wo",
1510
+ "Ġh igh",
1511
+ "Ġcont rol",
1512
+ "c e",
1513
+ "sc ooter",
1514
+ "mal indo",
1515
+ "Ġn or",
1516
+ "Ġd ue",
1517
+ "th ree",
1518
+ "u re",
1519
+ "e ight",
1520
+ "Ġy our",
1521
+ "Ġa g",
1522
+ "Ġag ain",
1523
+ "Ġw agon",
1524
+ "ed ic",
1525
+ "m e",
1526
+ "Ġh ave",
1527
+ "Ġfl y",
1528
+ "Ġt rack",
1529
+ "av ing",
1530
+ "Ġle aving",
1531
+ "atar i",
1532
+ "ath er",
1533
+ "Ġwe ather",
1534
+ "Ġst and",
1535
+ "l am",
1536
+ "lam at",
1537
+ "Ġbob is",
1538
+ "ct ion",
1539
+ "Ġse lamat",
1540
+ "le s",
1541
+ "Ġf ul",
1542
+ "Ġg lide",
1543
+ "Ġro ger",
1544
+ "Ġth is",
1545
+ "c opied",
1546
+ "Ġw ill",
1547
+ "Ġful l",
1548
+ "con t",
1549
+ "nin e",
1550
+ "a k",
1551
+ "ay a",
1552
+ "d irect",
1553
+ "e m",
1554
+ "o h",
1555
+ "me o",
1556
+ "ate s",
1557
+ "Ġn e",
1558
+ "p e",
1559
+ "re ss",
1560
+ "oh or",
1561
+ "ir ates",
1562
+ "or re",
1563
+ "w agon",
1564
+ "at ive",
1565
+ "ti on",
1566
+ "at ion",
1567
+ "Ġro meo",
1568
+ "u n",
1569
+ "orre ction",
1570
+ "b ar",
1571
+ "pe ed",
1572
+ "Ġjet star",
1573
+ "j et",
1574
+ "am a",
1575
+ "Ġdepart ure",
1576
+ "Ġle bar",
1577
+ "Ġadvis ed",
1578
+ "Ġp aya",
1579
+ "Ġz one",
1580
+ "Ġc orrection",
1581
+ "a x",
1582
+ "Ġar ama",
1583
+ "b le",
1584
+ "s ky",
1585
+ "g ative",
1586
+ "Ġmi les",
1587
+ "al l",
1588
+ "o k",
1589
+ "be k",
1590
+ "Ġa ffirm",
1591
+ "ul u",
1592
+ "z ero",
1593
+ "al ax",
1594
+ "Ġwith in",
1595
+ "kee p",
1596
+ "m aintain",
1597
+ "Ġar ound",
1598
+ "Ġj ohor",
1599
+ "Ġz ulu",
1600
+ "si tion",
1601
+ "Ġs alax",
1602
+ "Ġsu k",
1603
+ "r unway",
1604
+ "Ġ keep",
1605
+ "t rack",
1606
+ "Ġno bek",
1607
+ "jet star",
1608
+ "r an",
1609
+ "Ġc o",
1610
+ "i al",
1611
+ "y e",
1612
+ "Ġne gative",
1613
+ "ro ss",
1614
+ "an ad",
1615
+ "anad u",
1616
+ "Ġc an",
1617
+ "t e",
1618
+ "h eading",
1619
+ "f or",
1620
+ "c ap",
1621
+ "se ven",
1622
+ "Ġnor th",
1623
+ "m edic",
1624
+ "Ġs peed",
1625
+ "si x",
1626
+ "Ġdescend ing",
1627
+ "Ġb ack",
1628
+ "l ine",
1629
+ "cont inue",
1630
+ "Ġs ay",
1631
+ "q atari",
1632
+ "u p",
1633
+ "n ight",
1634
+ "a st",
1635
+ "b ye",
1636
+ "c lear",
1637
+ "e ct",
1638
+ "Ġexp ress",
1639
+ "Ġc ross",
1640
+ "w ay",
1641
+ "Ġc all",
1642
+ "Ġare a",
1643
+ "it ial",
1644
+ "Ġal l",
1645
+ "Ġapproach ing",
1646
+ "Ġnor mal",
1647
+ "for m",
1648
+ "' re",
1649
+ "Ġo b",
1650
+ "Ġmaintain ing",
1651
+ "Ġadvis e",
1652
+ "t er",
1653
+ "Ġp o",
1654
+ "Ġexp ect",
1655
+ "Ġo p",
1656
+ "st op",
1657
+ "Ġm edic",
1658
+ "ow er",
1659
+ "l o",
1660
+ "l ight",
1661
+ "Ġin itial",
1662
+ "t ower",
1663
+ "f oxtrot",
1664
+ "Ġq atari",
1665
+ "it ch",
1666
+ "Ġturn s",
1667
+ "Ġsquawk ing",
1668
+ "c k",
1669
+ "c o",
1670
+ "f light",
1671
+ "que n",
1672
+ "ro m",
1673
+ "Ġs h",
1674
+ "em irates",
1675
+ "an stop",
1676
+ "aysi a",
1677
+ "f our",
1678
+ "Ġf rom",
1679
+ "Ġth at",
1680
+ "Ġt ran",
1681
+ "t o",
1682
+ "r il",
1683
+ "Ġs w",
1684
+ "op y",
1685
+ "Ġf anstop",
1686
+ "m en",
1687
+ "ir d",
1688
+ "th ank",
1689
+ "ank an",
1690
+ "Ġe m",
1691
+ "t ouch",
1692
+ "up ta",
1693
+ "Ġa way",
1694
+ "a s",
1695
+ "Ġem irates",
1696
+ "le vel",
1697
+ "f ive",
1698
+ "b ird",
1699
+ "Ġdepart ing",
1700
+ "Ġto p",
1701
+ "Ġinitial ly",
1702
+ "Ġback track",
1703
+ "Ġpo sition",
1704
+ "Ġg upta",
1705
+ "Ġop s",
1706
+ "Ġmal am",
1707
+ "Ġw et",
1708
+ "Ġco m",
1709
+ "b ound",
1710
+ "i an",
1711
+ "st and",
1712
+ "er s",
1713
+ "e xp",
1714
+ "v acate",
1715
+ "e ck",
1716
+ "w h",
1717
+ "Ġu n",
1718
+ "quen c",
1719
+ "Ġgood night",
1720
+ "Ġwe st",
1721
+ "is h",
1722
+ "ril ankan",
1723
+ "Ġsw itch",
1724
+ "t ango",
1725
+ "Ġturn ing",
1726
+ "x i",
1727
+ "Ġch eck",
1728
+ "ar ta",
1729
+ "ak arta",
1730
+ "Ġrequest ing",
1731
+ "r u",
1732
+ "ar ly",
1733
+ "s h",
1734
+ "b ang",
1735
+ "j oin",
1736
+ "re quenc",
1737
+ "requenc y",
1738
+ "c al",
1739
+ "Ġf requency",
1740
+ "l l",
1741
+ "Ġl ate",
1742
+ "Ġgo ing",
1743
+ "h old",
1744
+ "Ġm et",
1745
+ "Ġa head",
1746
+ "p apa",
1747
+ "er n",
1748
+ "o scar",
1749
+ "Ġta xi",
1750
+ "i d",
1751
+ "Ġsuk ri",
1752
+ "ar go",
1753
+ "a b",
1754
+ "et ang",
1755
+ "Ġu h",
1756
+ "Ġc a",
1757
+ "Ġx anadu",
1758
+ "Ġ or",
1759
+ "Ġob st",
1760
+ "Ġp etang",
1761
+ "Ġe arly",
1762
+ "on g",
1763
+ "Ġw a",
1764
+ "i ke",
1765
+ "an ce",
1766
+ "le d",
1767
+ "Ġh and",
1768
+ "Ġj akarta",
1769
+ "Ġe st",
1770
+ "Ġe xt",
1771
+ "Ġsu bang",
1772
+ "cont act",
1773
+ "h ad",
1774
+ "Ġtop or",
1775
+ "Ġobst ac",
1776
+ "ak o",
1777
+ "g ako",
1778
+ "Ġmet ers",
1779
+ "Ġext end",
1780
+ "e cho",
1781
+ "exp ress",
1782
+ "Ġp ro",
1783
+ "Ġh eight",
1784
+ "a u",
1785
+ "o s",
1786
+ "er e",
1787
+ "Ġsuk at",
1788
+ "Ġa n",
1789
+ "Ġsh ort",
1790
+ "g i",
1791
+ "Ġo gako",
1792
+ "Ġwa it",
1793
+ "k ish",
1794
+ "u s",
1795
+ "on ian",
1796
+ "led onian",
1797
+ "ou t",
1798
+ "Ġland ing",
1799
+ "Ġhigh er",
1800
+ "n t",
1801
+ "Ġa ble",
1802
+ "Ġca ledonian",
1803
+ "Ġh e",
1804
+ "t y",
1805
+ "a h",
1806
+ "t ur",
1807
+ "Ġswitch ing",
1808
+ "il co",
1809
+ "con firm",
1810
+ "Ġs ight",
1811
+ "x anadu",
1812
+ "' s",
1813
+ "Ġch ang",
1814
+ "Ġma ke",
1815
+ "Ġd o",
1816
+ "Ġju st",
1817
+ "it e",
1818
+ "Ġcom men",
1819
+ "Ġair f",
1820
+ "Ġair b",
1821
+ "Ġre qu",
1822
+ "i e",
1823
+ "ed ite",
1824
+ "th er",
1825
+ "a ble",
1826
+ "f a",
1827
+ "Ġpa gi",
1828
+ "Ġb atar",
1829
+ "Ġin form",
1830
+ "Ġth ere",
1831
+ "Ġchang e",
1832
+ "ap pro",
1833
+ "gree n",
1834
+ "im e",
1835
+ "Ġinform ation",
1836
+ "b ravo",
1837
+ "em as",
1838
+ "p t",
1839
+ "ru ct",
1840
+ "b o",
1841
+ "er green",
1842
+ "Ġc opy",
1843
+ "Ġst ruct",
1844
+ "ce ed",
1845
+ "Ġstruct ure",
1846
+ "l u",
1847
+ "Ġm in",
1848
+ "Ġa h",
1849
+ "Ġre join",
1850
+ "ur ther",
1851
+ "Ġg emas",
1852
+ "si erra",
1853
+ "e el",
1854
+ "g lide",
1855
+ "Ġtran sition",
1856
+ "i form",
1857
+ "w e",
1858
+ "Ġre cleared",
1859
+ "a se",
1860
+ "Ġst eel",
1861
+ "r ad",
1862
+ "Ġobstac les",
1863
+ "Ġsi lo",
1864
+ "Ġnorth ern",
1865
+ "Ġf urther",
1866
+ "mal aysia",
1867
+ "Ġtrack ing",
1868
+ "w ind",
1869
+ "Ġan y",
1870
+ "n e",
1871
+ "Ġal fa",
1872
+ "ar d",
1873
+ "v a",
1874
+ "Ġun iform",
1875
+ "s peed",
1876
+ "Ġb ase",
1877
+ "orn e",
1878
+ "Ġpro ceed",
1879
+ "Ġt ime",
1880
+ "Ġn au",
1881
+ "Ġe ast",
1882
+ "ti cal",
1883
+ "Ġjoin ing",
1884
+ "Ġairb orne",
1885
+ "Ġnau tical",
1886
+ "r y",
1887
+ "a i",
1888
+ "rad ar",
1889
+ "Ġs rilankan",
1890
+ "is e",
1891
+ "Ġp ath",
1892
+ "ap le",
1893
+ "n av",
1894
+ "li te",
1895
+ "Ġexp edite",
1896
+ "Ġlow er",
1897
+ "e x",
1898
+ "id ot",
1899
+ "' ll",
1900
+ "li sh",
1901
+ "h otel",
1902
+ "ab lish",
1903
+ "Ġl o",
1904
+ "Ġr nav",
1905
+ "Ġmal aysia",
1906
+ "un e",
1907
+ "l ow",
1908
+ "Ġ it",
1909
+ "Ġest ablish",
1910
+ "Ġextend ed",
1911
+ "m ain",
1912
+ "aple ss",
1913
+ "Ġfl apless",
1914
+ "speed bird",
1915
+ "i p",
1916
+ "u te",
1917
+ "a fter",
1918
+ "lea se",
1919
+ "Ġspeed bird",
1920
+ "i red",
1921
+ "Ġg ra",
1922
+ "Ġcommen ce",
1923
+ "Ġrequ ired",
1924
+ "Ġk idot",
1925
+ "wh en",
1926
+ "Ġmin ute",
1927
+ "Ġs ky",
1928
+ "r act",
1929
+ "s ay",
1930
+ "Ġgra ss",
1931
+ "appro ved",
1932
+ "ie ld",
1933
+ "u t",
1934
+ "c el",
1935
+ "vis ta",
1936
+ "m ike",
1937
+ "ra ft",
1938
+ "Ġin bound",
1939
+ "Ġshort ly",
1940
+ "Ġtran s",
1941
+ "Ġairf ield",
1942
+ "Ġp ract",
1943
+ "c raft",
1944
+ "Ġre main",
1945
+ "Ġin ter",
1946
+ "lu x",
1947
+ "Ġc argo",
1948
+ "j ohor",
1949
+ "Ġeight y",
1950
+ "Ġdow n",
1951
+ "Ġthe n",
1952
+ "Ġc re",
1953
+ "et i",
1954
+ "Ġp re",
1955
+ "ran s",
1956
+ "eti had",
1957
+ "Ġair craft",
1958
+ "Ġp lease",
1959
+ "Ġthank s",
1960
+ "Ġsu p",
1961
+ "Ġstructure s",
1962
+ "c opy",
1963
+ "wh iskey",
1964
+ "or ry",
1965
+ "Ġcre w",
1966
+ "Ġi f",
1967
+ "Ġa s",
1968
+ "pt une",
1969
+ "Ġs tar",
1970
+ "Ġvis ta",
1971
+ "il able",
1972
+ "Ġpract ise",
1973
+ "s rilankan",
1974
+ "Ġo ff",
1975
+ "on d",
1976
+ "Ġa va",
1977
+ "v ing",
1978
+ "Ġava ilable",
1979
+ "t it",
1980
+ "u de",
1981
+ "Ġw ilco",
1982
+ "Ġcall ing",
1983
+ "Ġa c",
1984
+ "Ġal tit",
1985
+ "Ġaltit ude",
1986
+ "Ġle ave",
1987
+ "it os",
1988
+ "b ack",
1989
+ "Ġh ow",
1990
+ "c argo",
1991
+ "Ġm itos",
1992
+ "tur kish",
1993
+ "Ġi fly",
1994
+ "Ġb el",
1995
+ "al am",
1996
+ "t en",
1997
+ "Ġr ou",
1998
+ "Ġt e",
1999
+ "Ġup wind",
2000
+ "ad em",
2001
+ "Ġk ong",
2002
+ "Ġrou te",
2003
+ "Ġwest bound",
2004
+ "Ġclear ance",
2005
+ "adem y",
2006
+ "Ġbob ag",
2007
+ "r ight",
2008
+ "Ġre ach",
2009
+ "se nt",
2010
+ "en ger",
2011
+ "ave x",
2012
+ "p a",
2013
+ "t ing"
2014
+ ]
2015
  }
2016
  }
tokenizer_config.json CHANGED
@@ -1,13 +1,9 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
  "model_max_length": 1000000000000000019884624838656,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "BertTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
  "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
 
 
6
  "model_max_length": 1000000000000000019884624838656,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
 
 
 
 
9
  }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[PAD]":0,"'":1,"(":2,")":3,"-":4,".":5,"8":6,"<":7,">":8,"@":9,"`":10,"a":11,"b":12,"c":13,"d":14,"e":15,"f":16,"g":17,"h":18,"i":19,"j":20,"k":21,"l":22,"m":23,"n":24,"o":25,"p":26,"q":27,"r":28,"s":29,"t":30,"u":31,"v":32,"w":33,"x":34,"y":35,"z":36,"Ġ":37,"Ġt":38,"er":39,"re":40,"on":41,"Ġf":42,"in":43,"Ġs":44,"ve":45,"one":46,"Ġth":47,"Ġone":48,"ree":49,"wo":50,"Ġz":51,"Ġtwo":52,"ero":53,"Ġzero":54,"Ġthree":55,"ar":56,"ig":57,"igh":58,"ou":59,"le":60,"ight":61,"Ġc":62,"nd":63,"Ġe":64,"Ġn":65,"Ġd":66,"Ġa":67,"Ġse":68,"Ġfi":69,"Ġsi":70,"Ġfive":71,"Ġeight":72,"ven":73,"ay":74,"Ġsix":75,"our":76,"Ġseven":77,"Ġnin":78,"ing":79,"Ġr":80,"al":81,"Ġfour":82,"Ġde":83,"mb":84,"or":85,"ky":86,"Ġle":87,"ark":88,"lark":89,"red":90,"kylark":91,"ac":92,"nw":93,"Ġniner":94,"Ġto":95,"Ġg":96,"vel":97,"Ġl":98,"Ġh":99,"ur":100,"Ġlevel":101,"Ġw":102,"and":103,"ro":104,"ad":105,"unw":106,"unway":107,"sc":108,"ind":109,"li":110,"ap":111,"Ġrunway":112,"Ġm":113,"skylark":114,"Ġgo":115,"an":116,"ir":117,"mber":118,"Ġer":119,"ue":120,"is":121,"et":122,"Ġfl":123,"tar":124,"Ġp":125,"Ġb":126,"lea":127,"leared":128,"ct":129,"no":130,"mal":131,"Ġflight":132,"ke":133,"Ġand":134,"Ġo":135,"Ġcon":136,"Ġv":137,"que":138,"Ġfor":139,"ch":140,"Ġre":141,"limb":142,"end":143,"ous":144,"ousand":145,"Ġthousand":146,"um":147,"scend":148,"Ġk":149,"at":150,"ain":151,"letar":152,"pur":153,"ed":154,"umpur":155,"od":156,"ow":157,"si":158,"ra":159,"Ġcont":160,"Ġcleared":161,"Ġgood":162,"ci":163,"st":164,"cimal":165,"Ġdecimal":166,"Ġclimb":167,"pro":168,"Ġdescend":169,"Ġap":170,"vember":171,"Ġappro":172,"Ġseletar":173,"Ġfe":174,"Ġfeet":175,"Ġskylark":176,"ire":177,"act":178,"ead":179,"Ġrad":180,"Ġy":181,"umber":182,"Ġcap":183,"ff":184,"Ġradar":185,"be":186,"ly":187,"Ġtow":188,"Ġlumpur":189,"Ġtower":190,"Ġcontact":191,"ace":192,"urf":193,"urface":194,"Ġsurface":195,"not":196,"Ġwind":197,"it":198,"Ġknot":199,"Ġknots":200,"gree":201,"xt":202,"de":203,"op":204,"Ġj":205,"nin":206,"scar":207,"Ġnine":208,"ft":209,"Ġdegree":210,"Ġdegrees":211,"cho":212,"ied":213,"quebe":214,"quebec":215,"rot":216,"oxt":217,"oxtrot":218,"Ġquebec":219,"Ġvi":220,"Ġdow":221,"Ġoscar":222,"ctor":223,"nwind":224,"Ġland":225,"Ġecho":226,"Ġdownwind":227,"il":228,"ore":229,"Ġfoxtrot":230,"fly":231,"eading":232,"niner":233,"vo":234,"ingap":235,"ingapore":236,"ravo":237,"quest":238,"ss":239,"irect":240,"irm":241,"Ġrequest":242,"Ġbravo":243,"und":244,"Ġno":245,"undred":246,"Ġhundred":247,"Ġheading":248,"november":249,"ot":250,"ach":251,"Ġwh":252,"ouch":253,"apa":254,"go":255,"ate":256,"aysi":257,"tain":258,"aintain":259,"Ġyou":260,"Ġday":261,"Ġmal":262,"Ġapproach":263,"inal":264,"air":265,"ved":266,"Ġfinal":267,"ta":268,"Ġpapa":269,"Ġred":270,"Ġnumber":271,"Ġtouch":272,"Ġdirect":273,"aysian":274,"Ġapproved":275,"Ġvictor":276,"Ġu":277,"se":278,"cleared":279,"Ġst":280,"Ġta":281,"am":282,"ti":283,"Ġmaintain":284,"Ġthe":285,"lumpur":286,"ound":287,"Ġnovember":288,"lk":289,"Ġi":290,"Ġmi":291,"Ġq":292,"lkair":293,"opied":294,"Ġch":295,"Ġsingapore":296,"Ġair":297,"Ġwe":298,"Ġon":299,"oin":300,"key":301,"iskey":302,"ilo":303,"Ġtake":304,"Ġleft":305,"Ġal":306,"Ġkilo":307,"th":308,"off":309,"ual":310,"Ġwhiskey":311,"Ġby":312,"Ġar":313,"Ġtakeoff":314,"ld":315,"Ġvis":316,"Ġin":317,"Ġpa":318,"Ġup":319,"number":320,"vening":321,"indo":322,"Ġevening":323,"Ġis":324,"acate":325,"en":326,"Ġat":327,"Ġvisual":328,"ic":329,"firm":330,"qu":331,"lta":332,"el":333,"Ġmike":334,"arli":335,"arlie":336,"old":337,"Ġread":338,"Ġpass":339,"ia":340,"Ġx":341,"ack":342,"Ġdelta":343,"oot":344,"ger":345,"ooter":346,"climb":347,"Ġcopied":348,"Ġcharlie":349,"aw":350,"ort":351,"Ġready":352,"Ġtur":353,"Ġfire":354,"Ġfirefly":355,"ango":356,"round":357,"awk":358,"quawk":359,"Ġconfirm":360,"Ġvacate":361,"india":362,"den":363,"Ġsquawk":364,"ag":365,"fter":366,"ank":367,"ray":368,"Ġiden":369,"ine":370,"Ġpassing":371,"tif":372,"tified":373,"Ġground":374,"Ġindia":375,"Ġturn":376,"Ġidentified":377,"Ġhold":378,"seletar":379,"ha":380,"kee":381,"pha":382,"fire":383,"firefly":384,"ffirm":385,"erra":386,"im":387,"Ġju":388,"Ġafter":389,"port":390,"ver":391,"lear":392,"Ġalpha":393,"ion":394,"Ġmalaysian":395,"descend":396,"agon":397,"Ġtango":398,"Ġof":399,"Ġreport":400,"inue":401,"vi":402,"Ġover":403,"lf":404,"Ġro":405,"Ġsir":406,"Ġsierra":407,"ri":408,"ett":409,"Ġgolf":410,"ith":411,"liett":412,"orn":413,"ul":414,"Ġsilkair":415,"Ġwith":416,"Ġjuliett":417,"malaysian":418,"Ġvia":419,"cu":420,"rack":421,"head":422,"Ġare":423,"Ġclimbing":424,"victor":425,"xp":426,"singapore":427,"vis":428,"Ġright":429,"ircu":430,"ircuit":431,"Ġnow":432,"art":433,"Ġcircuit":434,"sia":435,"silkair":436,"otel":437,"orning":438,"part":439,"ima":440,"Ġjet":441,"Ġline":442,"Ġdepart":443,"av":444,"Ġmorning":445,"oint":446,"Ġpoint":447,"star":448,"Ġstop":449,"Ġlima":450,"Ġclear":451,"Ġbye":452,"Ġad":453,"Ġlow":454,"ankee":455,"val":456,"Ġyankee":457,"Ġthank":458,"ave":459,"Ġarri":460,"Ġarrival":461,"ive":462,"affirm":463,"ob":464,"Ġhotel":465,"Ġcontinue":466,"Ġmalindo":467,"Ġbe":468,"ath":469,"Ġsc":470,"Ġoverhead":471,"Ġasia":472,"atar":473,"noon":474,"Ġscooter":475,"ffic":476,"Ġadvis":477,"raffic":478,"Ġafternoon":479,"Ġjoin":480,"Ġtraffic":481,"Ġexp":482,"good":483,"con":484,"ang":485,"roger":486,"Ġwhen":487,"lide":488,"Ġsu":489,"ill":490,"Ġma":491,"rol":492,"Ġbob":493,"Ġholding":494,"two":495,"Ġhigh":496,"Ġcontrol":497,"ce":498,"scooter":499,"malindo":500,"Ġnor":501,"Ġdue":502,"three":503,"ure":504,"eight":505,"Ġyour":506,"Ġag":507,"Ġagain":508,"Ġwagon":509,"edic":510,"me":511,"Ġhave":512,"Ġfly":513,"Ġtrack":514,"aving":515,"Ġleaving":516,"atari":517,"ather":518,"Ġweather":519,"Ġstand":520,"lam":521,"lamat":522,"Ġbobis":523,"ction":524,"Ġselamat":525,"les":526,"Ġful":527,"Ġglide":528,"Ġroger":529,"Ġthis":530,"copied":531,"Ġwill":532,"Ġfull":533,"cont":534,"nine":535,"ak":536,"aya":537,"direct":538,"em":539,"oh":540,"meo":541,"ates":542,"Ġne":543,"pe":544,"ress":545,"ohor":546,"irates":547,"orre":548,"wagon":549,"ative":550,"tion":551,"ation":552,"Ġromeo":553,"un":554,"orrection":555,"bar":556,"peed":557,"Ġjetstar":558,"jet":559,"ama":560,"Ġdeparture":561,"Ġlebar":562,"Ġadvised":563,"Ġpaya":564,"Ġzone":565,"Ġcorrection":566,"ax":567,"Ġarama":568,"ble":569,"sky":570,"gative":571,"Ġmiles":572,"all":573,"ok":574,"bek":575,"Ġaffirm":576,"ulu":577,"zero":578,"alax":579,"Ġwithin":580,"keep":581,"maintain":582,"Ġaround":583,"Ġjohor":584,"Ġzulu":585,"sition":586,"Ġsalax":587,"Ġsuk":588,"runway":589,"Ġkeep":590,"track":591,"Ġnobek":592,"jetstar":593,"ran":594,"Ġco":595,"ial":596,"ye":597,"Ġnegative":598,"ross":599,"anad":600,"anadu":601,"Ġcan":602,"te":603,"heading":604,"for":605,"cap":606,"seven":607,"Ġnorth":608,"medic":609,"Ġspeed":610,"six":611,"Ġdescending":612,"Ġback":613,"line":614,"continue":615,"Ġsay":616,"qatari":617,"up":618,"night":619,"ast":620,"bye":621,"clear":622,"ect":623,"Ġexpress":624,"Ġcross":625,"way":626,"Ġcall":627,"Ġarea":628,"itial":629,"Ġall":630,"Ġapproaching":631,"Ġnormal":632,"form":633,"'re":634,"Ġob":635,"Ġmaintaining":636,"Ġadvise":637,"ter":638,"Ġpo":639,"Ġexpect":640,"Ġop":641,"stop":642,"Ġmedic":643,"ower":644,"lo":645,"light":646,"Ġinitial":647,"tower":648,"foxtrot":649,"Ġqatari":650,"itch":651,"Ġturns":652,"Ġsquawking":653,"ck":654,"co":655,"flight":656,"quen":657,"rom":658,"Ġsh":659,"emirates":660,"anstop":661,"aysia":662,"four":663,"Ġfrom":664,"Ġthat":665,"Ġtran":666,"to":667,"ril":668,"Ġsw":669,"opy":670,"Ġfanstop":671,"men":672,"ird":673,"thank":674,"ankan":675,"Ġem":676,"touch":677,"upta":678,"Ġaway":679,"as":680,"Ġemirates":681,"level":682,"five":683,"bird":684,"Ġdeparting":685,"Ġtop":686,"Ġinitially":687,"Ġbacktrack":688,"Ġposition":689,"Ġgupta":690,"Ġops":691,"Ġmalam":692,"Ġwet":693,"Ġcom":694,"bound":695,"ian":696,"stand":697,"ers":698,"exp":699,"vacate":700,"eck":701,"wh":702,"Ġun":703,"quenc":704,"Ġgoodnight":705,"Ġwest":706,"ish":707,"rilankan":708,"Ġswitch":709,"tango":710,"Ġturning":711,"xi":712,"Ġcheck":713,"arta":714,"akarta":715,"Ġrequesting":716,"ru":717,"arly":718,"sh":719,"bang":720,"join":721,"requenc":722,"requency":723,"cal":724,"Ġfrequency":725,"ll":726,"Ġlate":727,"Ġgoing":728,"hold":729,"Ġmet":730,"Ġahead":731,"papa":732,"ern":733,"oscar":734,"Ġtaxi":735,"id":736,"Ġsukri":737,"argo":738,"ab":739,"etang":740,"Ġuh":741,"Ġca":742,"Ġxanadu":743,"Ġor":744,"Ġobst":745,"Ġpetang":746,"Ġearly":747,"ong":748,"Ġwa":749,"ike":750,"ance":751,"led":752,"Ġhand":753,"Ġjakarta":754,"Ġest":755,"Ġext":756,"Ġsubang":757,"contact":758,"had":759,"Ġtopor":760,"Ġobstac":761,"ako":762,"gako":763,"Ġmeters":764,"Ġextend":765,"echo":766,"express":767,"Ġpro":768,"Ġheight":769,"au":770,"os":771,"ere":772,"Ġsukat":773,"Ġan":774,"Ġshort":775,"gi":776,"Ġogako":777,"Ġwait":778,"kish":779,"us":780,"onian":781,"ledonian":782,"out":783,"Ġlanding":784,"Ġhigher":785,"nt":786,"Ġable":787,"Ġcaledonian":788,"Ġhe":789,"ty":790,"ah":791,"tur":792,"Ġswitching":793,"ilco":794,"confirm":795,"Ġsight":796,"xanadu":797,"'s":798,"Ġchang":799,"Ġmake":800,"Ġdo":801,"Ġjust":802,"ite":803,"Ġcommen":804,"Ġairf":805,"Ġairb":806,"Ġrequ":807,"ie":808,"edite":809,"ther":810,"able":811,"fa":812,"Ġpagi":813,"Ġbatar":814,"Ġinform":815,"Ġthere":816,"Ġchange":817,"appro":818,"green":819,"ime":820,"Ġinformation":821,"bravo":822,"emas":823,"pt":824,"ruct":825,"bo":826,"ergreen":827,"Ġcopy":828,"Ġstruct":829,"ceed":830,"Ġstructure":831,"lu":832,"Ġmin":833,"Ġah":834,"Ġrejoin":835,"urther":836,"Ġgemas":837,"sierra":838,"eel":839,"glide":840,"Ġtransition":841,"iform":842,"we":843,"Ġrecleared":844,"ase":845,"Ġsteel":846,"rad":847,"Ġobstacles":848,"Ġsilo":849,"Ġnorthern":850,"Ġfurther":851,"malaysia":852,"Ġtracking":853,"wind":854,"Ġany":855,"ne":856,"Ġalfa":857,"ard":858,"va":859,"Ġuniform":860,"speed":861,"Ġbase":862,"orne":863,"Ġproceed":864,"Ġtime":865,"Ġnau":866,"Ġeast":867,"tical":868,"Ġjoining":869,"Ġairborne":870,"Ġnautical":871,"ry":872,"ai":873,"radar":874,"Ġsrilankan":875,"ise":876,"Ġpath":877,"aple":878,"nav":879,"lite":880,"Ġexpedite":881,"Ġlower":882,"ex":883,"idot":884,"'ll":885,"lish":886,"hotel":887,"ablish":888,"Ġlo":889,"Ġrnav":890,"Ġmalaysia":891,"une":892,"low":893,"Ġit":894,"Ġestablish":895,"Ġextended":896,"main":897,"apless":898,"Ġflapless":899,"speedbird":900,"ip":901,"ute":902,"after":903,"lease":904,"Ġspeedbird":905,"ired":906,"Ġgra":907,"Ġcommence":908,"Ġrequired":909,"Ġkidot":910,"when":911,"Ġminute":912,"Ġsky":913,"ract":914,"say":915,"Ġgrass":916,"approved":917,"ield":918,"ut":919,"cel":920,"vista":921,"mike":922,"raft":923,"Ġinbound":924,"Ġshortly":925,"Ġtrans":926,"Ġairfield":927,"Ġpract":928,"craft":929,"Ġremain":930,"Ġinter":931,"lux":932,"Ġcargo":933,"johor":934,"Ġeighty":935,"Ġdown":936,"Ġthen":937,"Ġcre":938,"eti":939,"Ġpre":940,"rans":941,"etihad":942,"Ġaircraft":943,"Ġplease":944,"Ġthanks":945,"Ġsup":946,"Ġstructures":947,"copy":948,"whiskey":949,"orry":950,"Ġcrew":951,"Ġif":952,"Ġas":953,"ptune":954,"Ġstar":955,"Ġvista":956,"ilable":957,"Ġpractise":958,"srilankan":959,"Ġoff":960,"ond":961,"Ġava":962,"ving":963,"Ġavailable":964,"tit":965,"ude":966,"Ġwilco":967,"Ġcalling":968,"Ġac":969,"Ġaltit":970,"Ġaltitude":971,"Ġleave":972,"itos":973,"back":974,"Ġhow":975,"cargo":976,"Ġmitos":977,"turkish":978,"Ġifly":979,"Ġbel":980,"alam":981,"ten":982,"Ġrou":983,"Ġte":984,"Ġupwind":985,"adem":986,"Ġkong":987,"Ġroute":988,"Ġwestbound":989,"Ġclearance":990,"ademy":991,"Ġbobag":992,"right":993,"Ġreach":994,"sent":995,"enger":996,"avex":997,"pa":998,"ting":999}