zuhri025 commited on
Commit
ccce676
·
verified ·
1 Parent(s): ca0b7b3

feat: GPT-style 50k tokenizer + 80 sound/paralinguistic tags

Browse files
Files changed (2) hide show
  1. tokenizer.json +160 -160
  2. tokenizer_config.json +82 -2
tokenizer.json CHANGED
@@ -113,7 +113,7 @@
113
  },
114
  {
115
  "id": 12,
116
- "content": "[LAUGHS]",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
@@ -122,7 +122,7 @@
122
  },
123
  {
124
  "id": 13,
125
- "content": "[SIGHS]",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
@@ -131,7 +131,7 @@
131
  },
132
  {
133
  "id": 14,
134
- "content": "[GASPS]",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
@@ -140,7 +140,7 @@
140
  },
141
  {
142
  "id": 15,
143
- "content": "[CLEARS_THROAT]",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
@@ -149,7 +149,7 @@
149
  },
150
  {
151
  "id": 16,
152
- "content": "[MUSIC]",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
@@ -158,7 +158,7 @@
158
  },
159
  {
160
  "id": 17,
161
- "content": "[BEEP]",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
@@ -167,7 +167,7 @@
167
  },
168
  {
169
  "id": 18,
170
- "content": "[APPLAUSE]",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
@@ -176,7 +176,7 @@
176
  },
177
  {
178
  "id": 19,
179
- "content": "[COUGHS]",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  },
186
  {
187
  "id": 20,
188
- "content": "[MUMBLES]",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
@@ -194,7 +194,7 @@
194
  },
195
  {
196
  "id": 21,
197
- "content": "[WHISTLES]",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
@@ -203,7 +203,7 @@
203
  },
204
  {
205
  "id": 22,
206
- "content": "[SNIFFS]",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
@@ -212,7 +212,7 @@
212
  },
213
  {
214
  "id": 23,
215
- "content": "[SINGS]",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
@@ -221,7 +221,7 @@
221
  },
222
  {
223
  "id": 24,
224
- "content": "[GROANS]",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
@@ -230,7 +230,7 @@
230
  },
231
  {
232
  "id": 25,
233
- "content": "[SCREAMS]",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
@@ -239,7 +239,7 @@
239
  },
240
  {
241
  "id": 26,
242
- "content": "[SNEEZES]",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
@@ -248,7 +248,7 @@
248
  },
249
  {
250
  "id": 27,
251
- "content": "[EXHALES]",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  },
258
  {
259
  "id": 28,
260
- "content": "[INHALES]",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
@@ -266,7 +266,7 @@
266
  },
267
  {
268
  "id": 29,
269
- "content": "[BREATH]",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
@@ -275,7 +275,7 @@
275
  },
276
  {
277
  "id": 30,
278
- "content": "[DEEP_BREATH]",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
@@ -284,7 +284,7 @@
284
  },
285
  {
286
  "id": 31,
287
- "content": "[SHARP_INHALE]",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
@@ -293,7 +293,7 @@
293
  },
294
  {
295
  "id": 32,
296
- "content": "[SHARP_BREATH]",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
@@ -302,7 +302,7 @@
302
  },
303
  {
304
  "id": 33,
305
- "content": "[SHAKY_BREATH]",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
@@ -311,7 +311,7 @@
311
  },
312
  {
313
  "id": 34,
314
- "content": "[BREATHY_EXHALE]",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
@@ -320,7 +320,7 @@
320
  },
321
  {
322
  "id": 35,
323
- "content": "[STRAINED_BREATH]",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  },
330
  {
331
  "id": 36,
332
- "content": "[QUICK_BREATH]",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
@@ -338,7 +338,7 @@
338
  },
339
  {
340
  "id": 37,
341
- "content": "[PANTING]",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
@@ -347,7 +347,7 @@
347
  },
348
  {
349
  "id": 38,
350
- "content": "[BREATHING]",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
@@ -356,7 +356,7 @@
356
  },
357
  {
358
  "id": 39,
359
- "content": "[HEAVY_BREATHING]",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
@@ -365,7 +365,7 @@
365
  },
366
  {
367
  "id": 40,
368
- "content": "[NERVOUS_EXHALE]",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
@@ -374,7 +374,7 @@
374
  },
375
  {
376
  "id": 41,
377
- "content": "[PAINED_BREATH]",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
@@ -383,7 +383,7 @@
383
  },
384
  {
385
  "id": 42,
386
- "content": "[GIGGLES]",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
@@ -392,7 +392,7 @@
392
  },
393
  {
394
  "id": 43,
395
- "content": "[CHUCKLES]",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  },
402
  {
403
  "id": 44,
404
- "content": "[SOFT_CHUCKLE]",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
@@ -410,7 +410,7 @@
410
  },
411
  {
412
  "id": 45,
413
- "content": "[SOFT_LAUGH]",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
@@ -419,7 +419,7 @@
419
  },
420
  {
421
  "id": 46,
422
- "content": "[NERVOUS_LAUGH]",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
@@ -428,7 +428,7 @@
428
  },
429
  {
430
  "id": 47,
431
- "content": "[SOBS]",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
@@ -437,7 +437,7 @@
437
  },
438
  {
439
  "id": 48,
440
- "content": "[SOBBING]",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
@@ -446,7 +446,7 @@
446
  },
447
  {
448
  "id": 49,
449
- "content": "[CHOKED_SOB]",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
@@ -455,7 +455,7 @@
455
  },
456
  {
457
  "id": 50,
458
- "content": "[CRYING]",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
@@ -464,7 +464,7 @@
464
  },
465
  {
466
  "id": 51,
467
- "content": "[WHIMPERS]",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
@@ -473,7 +473,7 @@
473
  },
474
  {
475
  "id": 52,
476
- "content": "[SOFT_WHIMPER]",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
@@ -482,7 +482,7 @@
482
  },
483
  {
484
  "id": 53,
485
- "content": "[PAINED_CRY]",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
@@ -491,7 +491,7 @@
491
  },
492
  {
493
  "id": 54,
494
- "content": "[PAINED_GRUNT]",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
@@ -500,7 +500,7 @@
500
  },
501
  {
502
  "id": 55,
503
- "content": "[PAINED_SOUND]",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
@@ -509,7 +509,7 @@
509
  },
510
  {
511
  "id": 56,
512
- "content": "[CHOKES]",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
@@ -518,7 +518,7 @@
518
  },
519
  {
520
  "id": 57,
521
- "content": "[HUMS]",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
@@ -527,7 +527,7 @@
527
  },
528
  {
529
  "id": 58,
530
- "content": "[HUMMING]",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
@@ -536,7 +536,7 @@
536
  },
537
  {
538
  "id": 59,
539
- "content": "[SOFT_HUM]",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
@@ -545,7 +545,7 @@
545
  },
546
  {
547
  "id": 60,
548
- "content": "[PLEASED_HUM]",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
@@ -554,7 +554,7 @@
554
  },
555
  {
556
  "id": 61,
557
- "content": "[CONTENTED_HUM]",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
@@ -563,7 +563,7 @@
563
  },
564
  {
565
  "id": 62,
566
- "content": "[MURMURS]",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
@@ -572,7 +572,7 @@
572
  },
573
  {
574
  "id": 63,
575
- "content": "[MMM]",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
@@ -581,7 +581,7 @@
581
  },
582
  {
583
  "id": 64,
584
- "content": "[MHM]",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
@@ -590,7 +590,7 @@
590
  },
591
  {
592
  "id": 65,
593
- "content": "[HMM]",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
@@ -599,7 +599,7 @@
599
  },
600
  {
601
  "id": 66,
602
- "content": "[AH]",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
@@ -608,7 +608,7 @@
608
  },
609
  {
610
  "id": 67,
611
- "content": "[MOUTH_SOUND]",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
@@ -617,7 +617,7 @@
617
  },
618
  {
619
  "id": 68,
620
- "content": "[MOUTH_CLICK]",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
@@ -626,7 +626,7 @@
626
  },
627
  {
628
  "id": 69,
629
- "content": "[TONGUE_CLICK]",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
@@ -635,7 +635,7 @@
635
  },
636
  {
637
  "id": 70,
638
- "content": "[LIP_SMACK]",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
@@ -644,7 +644,7 @@
644
  },
645
  {
646
  "id": 71,
647
- "content": "[SMACKS]",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
@@ -653,7 +653,7 @@
653
  },
654
  {
655
  "id": 72,
656
- "content": "[TSK]",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
@@ -662,7 +662,7 @@
662
  },
663
  {
664
  "id": 73,
665
- "content": "[CLICKS]",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
@@ -671,7 +671,7 @@
671
  },
672
  {
673
  "id": 74,
674
- "content": "[SLURPS]",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
@@ -680,7 +680,7 @@
680
  },
681
  {
682
  "id": 75,
683
- "content": "[GULPS]",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
@@ -689,7 +689,7 @@
689
  },
690
  {
691
  "id": 76,
692
- "content": "[SWALLOWS]",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
@@ -698,7 +698,7 @@
698
  },
699
  {
700
  "id": 77,
701
- "content": "[YAWNS]",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
@@ -707,7 +707,7 @@
707
  },
708
  {
709
  "id": 78,
710
- "content": "[MOANS]",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
@@ -716,7 +716,7 @@
716
  },
717
  {
718
  "id": 79,
719
- "content": "[GRUNTS]",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
@@ -725,7 +725,7 @@
725
  },
726
  {
727
  "id": 80,
728
- "content": "[GROWLS]",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
@@ -734,7 +734,7 @@
734
  },
735
  {
736
  "id": 81,
737
- "content": "[HISSES]",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
@@ -743,7 +743,7 @@
743
  },
744
  {
745
  "id": 82,
746
- "content": "[SCOFFS]",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
@@ -752,7 +752,7 @@
752
  },
753
  {
754
  "id": 83,
755
- "content": "[HMPH]",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
@@ -761,7 +761,7 @@
761
  },
762
  {
763
  "id": 84,
764
- "content": "[HUFFS]",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
@@ -770,7 +770,7 @@
770
  },
771
  {
772
  "id": 85,
773
- "content": "[WHISPERS]",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
@@ -779,7 +779,7 @@
779
  },
780
  {
781
  "id": 86,
782
- "content": "[PURRS]",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
@@ -788,7 +788,7 @@
788
  },
789
  {
790
  "id": 87,
791
- "content": "[STUTTERS]",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
@@ -797,7 +797,7 @@
797
  },
798
  {
799
  "id": 88,
800
- "content": "[HICCUPS]",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
@@ -806,7 +806,7 @@
806
  },
807
  {
808
  "id": 89,
809
- "content": "[SHIVERS]",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
@@ -815,7 +815,7 @@
815
  },
816
  {
817
  "id": 90,
818
- "content": "[YELPS]",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
@@ -895,86 +895,6 @@
895
  "<|speech|>": 9,
896
  "<|frame_start|>": 10,
897
  "<|frame_end|>": 11,
898
- "[LAUGHS]": 12,
899
- "[SIGHS]": 13,
900
- "[GASPS]": 14,
901
- "[CLEARS_THROAT]": 15,
902
- "[MUSIC]": 16,
903
- "[BEEP]": 17,
904
- "[APPLAUSE]": 18,
905
- "[COUGHS]": 19,
906
- "[MUMBLES]": 20,
907
- "[WHISTLES]": 21,
908
- "[SNIFFS]": 22,
909
- "[SINGS]": 23,
910
- "[GROANS]": 24,
911
- "[SCREAMS]": 25,
912
- "[SNEEZES]": 26,
913
- "[EXHALES]": 27,
914
- "[INHALES]": 28,
915
- "[BREATH]": 29,
916
- "[DEEP_BREATH]": 30,
917
- "[SHARP_INHALE]": 31,
918
- "[SHARP_BREATH]": 32,
919
- "[SHAKY_BREATH]": 33,
920
- "[BREATHY_EXHALE]": 34,
921
- "[STRAINED_BREATH]": 35,
922
- "[QUICK_BREATH]": 36,
923
- "[PANTING]": 37,
924
- "[BREATHING]": 38,
925
- "[HEAVY_BREATHING]": 39,
926
- "[NERVOUS_EXHALE]": 40,
927
- "[PAINED_BREATH]": 41,
928
- "[GIGGLES]": 42,
929
- "[CHUCKLES]": 43,
930
- "[SOFT_CHUCKLE]": 44,
931
- "[SOFT_LAUGH]": 45,
932
- "[NERVOUS_LAUGH]": 46,
933
- "[SOBS]": 47,
934
- "[SOBBING]": 48,
935
- "[CHOKED_SOB]": 49,
936
- "[CRYING]": 50,
937
- "[WHIMPERS]": 51,
938
- "[SOFT_WHIMPER]": 52,
939
- "[PAINED_CRY]": 53,
940
- "[PAINED_GRUNT]": 54,
941
- "[PAINED_SOUND]": 55,
942
- "[CHOKES]": 56,
943
- "[HUMS]": 57,
944
- "[HUMMING]": 58,
945
- "[SOFT_HUM]": 59,
946
- "[PLEASED_HUM]": 60,
947
- "[CONTENTED_HUM]": 61,
948
- "[MURMURS]": 62,
949
- "[MMM]": 63,
950
- "[MHM]": 64,
951
- "[HMM]": 65,
952
- "[AH]": 66,
953
- "[MOUTH_SOUND]": 67,
954
- "[MOUTH_CLICK]": 68,
955
- "[TONGUE_CLICK]": 69,
956
- "[LIP_SMACK]": 70,
957
- "[SMACKS]": 71,
958
- "[TSK]": 72,
959
- "[CLICKS]": 73,
960
- "[SLURPS]": 74,
961
- "[GULPS]": 75,
962
- "[SWALLOWS]": 76,
963
- "[YAWNS]": 77,
964
- "[MOANS]": 78,
965
- "[GRUNTS]": 79,
966
- "[GROWLS]": 80,
967
- "[HISSES]": 81,
968
- "[SCOFFS]": 82,
969
- "[HMPH]": 83,
970
- "[HUFFS]": 84,
971
- "[WHISPERS]": 85,
972
- "[PURRS]": 86,
973
- "[STUTTERS]": 87,
974
- "[HICCUPS]": 88,
975
- "[SHIVERS]": 89,
976
- "[YELPS]": 90,
977
- "[ROARS]": 91,
978
  "!": 92,
979
  "\"": 93,
980
  "#": 94,
@@ -50882,7 +50802,87 @@
50882
  "ĠBened": 49996,
50883
  "ĠÙĤصÛĮدÛĴ": 49997,
50884
  "Complete": 49998,
50885
- "اÙĦÙ쨶ÙĦ": 49999
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50886
  },
50887
  "merges": [
50888
  [
 
113
  },
114
  {
115
  "id": 12,
116
+ "content": "[S1]",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
 
122
  },
123
  {
124
  "id": 13,
125
+ "content": "[S2]",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
 
131
  },
132
  {
133
  "id": 14,
134
+ "content": "[LAUGHS]",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
 
140
  },
141
  {
142
  "id": 15,
143
+ "content": "[SIGHS]",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
 
149
  },
150
  {
151
  "id": 16,
152
+ "content": "[GASPS]",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
 
158
  },
159
  {
160
  "id": 17,
161
+ "content": "[CLEARS_THROAT]",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
 
167
  },
168
  {
169
  "id": 18,
170
+ "content": "[MUSIC]",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
 
176
  },
177
  {
178
  "id": 19,
179
+ "content": "[BEEP]",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
 
185
  },
186
  {
187
  "id": 20,
188
+ "content": "[APPLAUSE]",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
 
194
  },
195
  {
196
  "id": 21,
197
+ "content": "[COUGHS]",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
 
203
  },
204
  {
205
  "id": 22,
206
+ "content": "[MUMBLES]",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
 
212
  },
213
  {
214
  "id": 23,
215
+ "content": "[WHISTLES]",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
 
221
  },
222
  {
223
  "id": 24,
224
+ "content": "[SNIFFS]",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
 
230
  },
231
  {
232
  "id": 25,
233
+ "content": "[SINGS]",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
 
239
  },
240
  {
241
  "id": 26,
242
+ "content": "[GROANS]",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
 
248
  },
249
  {
250
  "id": 27,
251
+ "content": "[SCREAMS]",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
 
257
  },
258
  {
259
  "id": 28,
260
+ "content": "[SNEEZES]",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
 
266
  },
267
  {
268
  "id": 29,
269
+ "content": "[EXHALES]",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
 
275
  },
276
  {
277
  "id": 30,
278
+ "content": "[INHALES]",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
 
284
  },
285
  {
286
  "id": 31,
287
+ "content": "[BREATH]",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
 
293
  },
294
  {
295
  "id": 32,
296
+ "content": "[DEEP_BREATH]",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
 
302
  },
303
  {
304
  "id": 33,
305
+ "content": "[SHARP_INHALE]",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
 
311
  },
312
  {
313
  "id": 34,
314
+ "content": "[SHARP_BREATH]",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
 
320
  },
321
  {
322
  "id": 35,
323
+ "content": "[SHAKY_BREATH]",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
 
329
  },
330
  {
331
  "id": 36,
332
+ "content": "[BREATHY_EXHALE]",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
 
338
  },
339
  {
340
  "id": 37,
341
+ "content": "[STRAINED_BREATH]",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
 
347
  },
348
  {
349
  "id": 38,
350
+ "content": "[QUICK_BREATH]",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
 
356
  },
357
  {
358
  "id": 39,
359
+ "content": "[PANTING]",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
 
365
  },
366
  {
367
  "id": 40,
368
+ "content": "[BREATHING]",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
 
374
  },
375
  {
376
  "id": 41,
377
+ "content": "[HEAVY_BREATHING]",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
 
383
  },
384
  {
385
  "id": 42,
386
+ "content": "[NERVOUS_EXHALE]",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
 
392
  },
393
  {
394
  "id": 43,
395
+ "content": "[PAINED_BREATH]",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
 
401
  },
402
  {
403
  "id": 44,
404
+ "content": "[GIGGLES]",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
 
410
  },
411
  {
412
  "id": 45,
413
+ "content": "[CHUCKLES]",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
 
419
  },
420
  {
421
  "id": 46,
422
+ "content": "[SOFT_CHUCKLE]",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
 
428
  },
429
  {
430
  "id": 47,
431
+ "content": "[SOFT_LAUGH]",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
 
437
  },
438
  {
439
  "id": 48,
440
+ "content": "[NERVOUS_LAUGH]",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
 
446
  },
447
  {
448
  "id": 49,
449
+ "content": "[SOBS]",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
 
455
  },
456
  {
457
  "id": 50,
458
+ "content": "[SOBBING]",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
 
464
  },
465
  {
466
  "id": 51,
467
+ "content": "[CHOKED_SOB]",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
 
473
  },
474
  {
475
  "id": 52,
476
+ "content": "[CRYING]",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
 
482
  },
483
  {
484
  "id": 53,
485
+ "content": "[WHIMPERS]",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
 
491
  },
492
  {
493
  "id": 54,
494
+ "content": "[SOFT_WHIMPER]",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
 
500
  },
501
  {
502
  "id": 55,
503
+ "content": "[PAINED_CRY]",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
 
509
  },
510
  {
511
  "id": 56,
512
+ "content": "[PAINED_GRUNT]",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
 
518
  },
519
  {
520
  "id": 57,
521
+ "content": "[PAINED_SOUND]",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
 
527
  },
528
  {
529
  "id": 58,
530
+ "content": "[CHOKES]",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
 
536
  },
537
  {
538
  "id": 59,
539
+ "content": "[HUMS]",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
 
545
  },
546
  {
547
  "id": 60,
548
+ "content": "[HUMMING]",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
 
554
  },
555
  {
556
  "id": 61,
557
+ "content": "[SOFT_HUM]",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
 
563
  },
564
  {
565
  "id": 62,
566
+ "content": "[PLEASED_HUM]",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
 
572
  },
573
  {
574
  "id": 63,
575
+ "content": "[CONTENTED_HUM]",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
 
581
  },
582
  {
583
  "id": 64,
584
+ "content": "[MURMURS]",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
 
590
  },
591
  {
592
  "id": 65,
593
+ "content": "[MMM]",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
 
599
  },
600
  {
601
  "id": 66,
602
+ "content": "[MHM]",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
 
608
  },
609
  {
610
  "id": 67,
611
+ "content": "[HMM]",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
 
617
  },
618
  {
619
  "id": 68,
620
+ "content": "[AH]",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
 
626
  },
627
  {
628
  "id": 69,
629
+ "content": "[MOUTH_SOUND]",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
 
635
  },
636
  {
637
  "id": 70,
638
+ "content": "[MOUTH_CLICK]",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
 
644
  },
645
  {
646
  "id": 71,
647
+ "content": "[TONGUE_CLICK]",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
 
653
  },
654
  {
655
  "id": 72,
656
+ "content": "[LIP_SMACK]",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
 
662
  },
663
  {
664
  "id": 73,
665
+ "content": "[SMACKS]",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
 
671
  },
672
  {
673
  "id": 74,
674
+ "content": "[TSK]",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
 
680
  },
681
  {
682
  "id": 75,
683
+ "content": "[CLICKS]",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
 
689
  },
690
  {
691
  "id": 76,
692
+ "content": "[SLURPS]",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
 
698
  },
699
  {
700
  "id": 77,
701
+ "content": "[GULPS]",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
 
707
  },
708
  {
709
  "id": 78,
710
+ "content": "[SWALLOWS]",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
 
716
  },
717
  {
718
  "id": 79,
719
+ "content": "[YAWNS]",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
 
725
  },
726
  {
727
  "id": 80,
728
+ "content": "[MOANS]",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
 
734
  },
735
  {
736
  "id": 81,
737
+ "content": "[GRUNTS]",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
 
743
  },
744
  {
745
  "id": 82,
746
+ "content": "[GROWLS]",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
 
752
  },
753
  {
754
  "id": 83,
755
+ "content": "[HISSES]",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
 
761
  },
762
  {
763
  "id": 84,
764
+ "content": "[SCOFFS]",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
 
770
  },
771
  {
772
  "id": 85,
773
+ "content": "[HMPH]",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
 
779
  },
780
  {
781
  "id": 86,
782
+ "content": "[HUFFS]",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
 
788
  },
789
  {
790
  "id": 87,
791
+ "content": "[WHISPERS]",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
 
797
  },
798
  {
799
  "id": 88,
800
+ "content": "[PURRS]",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
 
806
  },
807
  {
808
  "id": 89,
809
+ "content": "[STUTTERS]",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
 
815
  },
816
  {
817
  "id": 90,
818
+ "content": "[HICCUPS]",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
 
895
  "<|speech|>": 9,
896
  "<|frame_start|>": 10,
897
  "<|frame_end|>": 11,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
898
  "!": 92,
899
  "\"": 93,
900
  "#": 94,
 
50802
  "ĠBened": 49996,
50803
  "ĠÙĤصÛĮدÛĴ": 49997,
50804
  "Complete": 49998,
50805
+ "اÙĦÙ쨶ÙĦ": 49999,
50806
+ "[S1]": 12,
50807
+ "[S2]": 13,
50808
+ "[LAUGHS]": 14,
50809
+ "[SIGHS]": 15,
50810
+ "[GASPS]": 16,
50811
+ "[CLEARS_THROAT]": 17,
50812
+ "[MUSIC]": 18,
50813
+ "[BEEP]": 19,
50814
+ "[APPLAUSE]": 20,
50815
+ "[COUGHS]": 21,
50816
+ "[MUMBLES]": 22,
50817
+ "[WHISTLES]": 23,
50818
+ "[SNIFFS]": 24,
50819
+ "[SINGS]": 25,
50820
+ "[GROANS]": 26,
50821
+ "[SCREAMS]": 27,
50822
+ "[SNEEZES]": 28,
50823
+ "[EXHALES]": 29,
50824
+ "[INHALES]": 30,
50825
+ "[BREATH]": 31,
50826
+ "[DEEP_BREATH]": 32,
50827
+ "[SHARP_INHALE]": 33,
50828
+ "[SHARP_BREATH]": 34,
50829
+ "[SHAKY_BREATH]": 35,
50830
+ "[BREATHY_EXHALE]": 36,
50831
+ "[STRAINED_BREATH]": 37,
50832
+ "[QUICK_BREATH]": 38,
50833
+ "[PANTING]": 39,
50834
+ "[BREATHING]": 40,
50835
+ "[HEAVY_BREATHING]": 41,
50836
+ "[NERVOUS_EXHALE]": 42,
50837
+ "[PAINED_BREATH]": 43,
50838
+ "[GIGGLES]": 44,
50839
+ "[CHUCKLES]": 45,
50840
+ "[SOFT_CHUCKLE]": 46,
50841
+ "[SOFT_LAUGH]": 47,
50842
+ "[NERVOUS_LAUGH]": 48,
50843
+ "[SOBS]": 49,
50844
+ "[SOBBING]": 50,
50845
+ "[CHOKED_SOB]": 51,
50846
+ "[CRYING]": 52,
50847
+ "[WHIMPERS]": 53,
50848
+ "[SOFT_WHIMPER]": 54,
50849
+ "[PAINED_CRY]": 55,
50850
+ "[PAINED_GRUNT]": 56,
50851
+ "[PAINED_SOUND]": 57,
50852
+ "[CHOKES]": 58,
50853
+ "[HUMS]": 59,
50854
+ "[HUMMING]": 60,
50855
+ "[SOFT_HUM]": 61,
50856
+ "[PLEASED_HUM]": 62,
50857
+ "[CONTENTED_HUM]": 63,
50858
+ "[MURMURS]": 64,
50859
+ "[MMM]": 65,
50860
+ "[MHM]": 66,
50861
+ "[HMM]": 67,
50862
+ "[AH]": 68,
50863
+ "[MOUTH_SOUND]": 69,
50864
+ "[MOUTH_CLICK]": 70,
50865
+ "[TONGUE_CLICK]": 71,
50866
+ "[LIP_SMACK]": 72,
50867
+ "[SMACKS]": 73,
50868
+ "[TSK]": 74,
50869
+ "[CLICKS]": 75,
50870
+ "[SLURPS]": 76,
50871
+ "[GULPS]": 77,
50872
+ "[SWALLOWS]": 78,
50873
+ "[YAWNS]": 79,
50874
+ "[MOANS]": 80,
50875
+ "[GRUNTS]": 81,
50876
+ "[GROWLS]": 82,
50877
+ "[HISSES]": 83,
50878
+ "[SCOFFS]": 84,
50879
+ "[HMPH]": 85,
50880
+ "[HUFFS]": 86,
50881
+ "[WHISPERS]": 87,
50882
+ "[PURRS]": 88,
50883
+ "[STUTTERS]": 89,
50884
+ "[HICCUPS]": 90,
50885
+ "[ROARS]": 91
50886
  },
50887
  "merges": [
50888
  [
tokenizer_config.json CHANGED
@@ -11,6 +11,88 @@
11
  "<|speech|>",
12
  "<|frame_start|>",
13
  "<|frame_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "[LAUGHS]",
15
  "[SIGHS]",
16
  "[GASPS]",
@@ -88,8 +170,6 @@
88
  "[PURRS]",
89
  "[STUTTERS]",
90
  "[HICCUPS]",
91
- "[SHIVERS]",
92
- "[YELPS]",
93
  "[ROARS]"
94
  ],
95
  "model_max_length": 1000000000000000019884624838656,
 
11
  "<|speech|>",
12
  "<|frame_start|>",
13
  "<|frame_end|>",
14
+ "<|reserved_1|>",
15
+ "<|reserved_2|>",
16
+ "<|reserved_3|>",
17
+ "<|reserved_4|>",
18
+ "<|reserved_5|>",
19
+ "<|reserved_6|>",
20
+ "<|reserved_7|>",
21
+ "<|reserved_8|>",
22
+ "<|reserved_9|>",
23
+ "<|reserved_10|>",
24
+ "<|reserved_11|>",
25
+ "<|reserved_12|>",
26
+ "<|reserved_13|>",
27
+ "<|reserved_14|>",
28
+ "<|reserved_15|>",
29
+ "<|reserved_16|>",
30
+ "<|reserved_17|>",
31
+ "<|reserved_18|>",
32
+ "<|reserved_19|>",
33
+ "<|reserved_20|>",
34
+ "<|reserved_21|>",
35
+ "<|reserved_22|>",
36
+ "<|reserved_23|>",
37
+ "<|reserved_24|>",
38
+ "<|reserved_25|>",
39
+ "<|reserved_26|>",
40
+ "<|reserved_27|>",
41
+ "<|reserved_28|>",
42
+ "<|reserved_29|>",
43
+ "<|reserved_30|>",
44
+ "<|reserved_31|>",
45
+ "<|reserved_32|>",
46
+ "<|reserved_33|>",
47
+ "<|reserved_34|>",
48
+ "<|reserved_35|>",
49
+ "<|reserved_36|>",
50
+ "<|reserved_37|>",
51
+ "<|reserved_38|>",
52
+ "<|reserved_39|>",
53
+ "<|reserved_40|>",
54
+ "<|reserved_41|>",
55
+ "<|reserved_42|>",
56
+ "<|reserved_43|>",
57
+ "<|reserved_44|>",
58
+ "<|reserved_45|>",
59
+ "<|reserved_46|>",
60
+ "<|reserved_47|>",
61
+ "<|reserved_48|>",
62
+ "<|reserved_49|>",
63
+ "<|reserved_50|>",
64
+ "<|reserved_51|>",
65
+ "<|reserved_52|>",
66
+ "<|reserved_53|>",
67
+ "<|reserved_54|>",
68
+ "<|reserved_55|>",
69
+ "<|reserved_56|>",
70
+ "<|reserved_57|>",
71
+ "<|reserved_58|>",
72
+ "<|reserved_59|>",
73
+ "<|reserved_60|>",
74
+ "<|reserved_61|>",
75
+ "<|reserved_62|>",
76
+ "<|reserved_63|>",
77
+ "<|reserved_64|>",
78
+ "<|reserved_65|>",
79
+ "<|reserved_66|>",
80
+ "<|reserved_67|>",
81
+ "<|reserved_68|>",
82
+ "<|reserved_69|>",
83
+ "<|reserved_70|>",
84
+ "<|reserved_71|>",
85
+ "<|reserved_72|>",
86
+ "<|reserved_73|>",
87
+ "<|reserved_74|>",
88
+ "<|reserved_75|>",
89
+ "<|reserved_76|>",
90
+ "<|reserved_77|>",
91
+ "<|reserved_78|>",
92
+ "<|reserved_79|>",
93
+ "<|reserved_80|>",
94
+ "[S1]",
95
+ "[S2]",
96
  "[LAUGHS]",
97
  "[SIGHS]",
98
  "[GASPS]",
 
170
  "[PURRS]",
171
  "[STUTTERS]",
172
  "[HICCUPS]",
 
 
173
  "[ROARS]"
174
  ],
175
  "model_max_length": 1000000000000000019884624838656,