linl03 commited on
Commit
c2809ae
1 Parent(s): 4e42f28

Training in progress, step 1000

Browse files
added_tokens.json CHANGED
@@ -1,101 +1,4 @@
1
  {
2
- " ": 177,
3
  "<ctc_blank>": 80,
4
- "<mask>": 79,
5
- "À": 87,
6
- "Á": 86,
7
- "Ã": 90,
8
- "È": 111,
9
- "É": 110,
10
- "Ì": 151,
11
- "Í": 150,
12
- "Ò": 121,
13
- "Ó": 120,
14
- "Õ": 123,
15
- "Ý": 160,
16
- "à": 82,
17
- "á": 81,
18
- "ã": 85,
19
- "è": 106,
20
- "ì": 146,
21
- "í": 145,
22
- "ò": 116,
23
- "ó": 115,
24
- "õ": 118,
25
- "ý": 155,
26
- "Đ": 175,
27
- "đ": 176,
28
- "Ĩ": 153,
29
- "ĩ": 148,
30
- "Ạ": 88,
31
- "ạ": 83,
32
- "Ả": 89,
33
- "ả": 84,
34
- "Ấ": 91,
35
- "ấ": 96,
36
- "Ầ": 92,
37
- "ầ": 97,
38
- "Ẩ": 94,
39
- "ẩ": 99,
40
- "Ẫ": 95,
41
- "ẫ": 100,
42
- "Ậ": 93,
43
- "ậ": 98,
44
- "ắ": 101,
45
- "ằ": 102,
46
- "ẳ": 105,
47
- "ẵ": 103,
48
- "ặ": 104,
49
- "Ẹ": 114,
50
- "ẹ": 109,
51
- "Ẻ": 112,
52
- "ẻ": 107,
53
- "Ẽ": 113,
54
- "ẽ": 108,
55
- "Ế": 170,
56
- "ế": 165,
57
- "Ề": 171,
58
- "ề": 166,
59
- "Ể": 172,
60
- "ể": 167,
61
- "Ễ": 173,
62
- "ễ": 168,
63
- "Ệ": 174,
64
- "ệ": 169,
65
- "Ỉ": 152,
66
- "ỉ": 149,
67
- "Ị": 154,
68
- "ị": 147,
69
- "Ọ": 124,
70
- "ọ": 119,
71
- "Ỏ": 122,
72
- "ỏ": 117,
73
- "Ố": 130,
74
- "ố": 125,
75
- "Ồ": 131,
76
- "ồ": 126,
77
- "Ổ": 133,
78
- "ổ": 128,
79
- "Ỗ": 134,
80
- "ỗ": 127,
81
- "Ộ": 132,
82
- "ộ": 129,
83
- "Ớ": 140,
84
- "ớ": 135,
85
- "Ờ": 141,
86
- "ờ": 136,
87
- "Ở": 143,
88
- "ở": 137,
89
- "Ỡ": 144,
90
- "ỡ": 138,
91
- "Ợ": 142,
92
- "ợ": 139,
93
- "Ỳ": 161,
94
- "ỳ": 156,
95
- "Ỵ": 163,
96
- "ỵ": 159,
97
- "Ỷ": 162,
98
- "ỷ": 157,
99
- "Ỹ": 164,
100
- "ỹ": 158
101
  }
 
1
  {
 
2
  "<ctc_blank>": 80,
3
+ "<mask>": 79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "microsoft/speecht5_tts",
3
  "activation_dropout": 0.1,
4
  "apply_spec_augment": true,
5
  "architectures": [
 
1
  {
2
+ "_name_or_path": "linl03/speecht5_tts_kcn",
3
  "activation_dropout": 0.1,
4
  "apply_spec_augment": true,
5
  "architectures": [
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6259202860264a1e6e21b8b562ee5fa8c72f6519aebda136cec104a4dc5f8516
3
  size 578087304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bd57826f68d17129075d7077294a76cd0a9c7c132b59d08c4065004f31acc2
3
  size 578087304
runs/Sep05_16-31-38_55217d593c2e/events.out.tfevents.1725553904.55217d593c2e.197.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd6f745c33e43807b59fd497e22ffff97623592d5f44f0a73511bca1e7279c
3
+ size 15270
tokenizer_config.json CHANGED
@@ -32,38 +32,6 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "5": {
36
- "content": "e",
37
- "lstrip": false,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": false
42
- },
43
- "7": {
44
- "content": "a",
45
- "lstrip": false,
46
- "normalized": true,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": false
50
- },
51
- "33": {
52
- "content": "A",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "73": {
60
- "content": "é",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
  "79": {
68
  "content": "<mask>",
69
  "lstrip": true,
@@ -79,782 +47,6 @@
79
  "rstrip": false,
80
  "single_word": false,
81
  "special": false
82
- },
83
- "81": {
84
- "content": "á",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "82": {
92
- "content": "à",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "83": {
100
- "content": "ạ",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "84": {
108
- "content": "ả",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "85": {
116
- "content": "ã",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "86": {
124
- "content": "Á",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "87": {
132
- "content": "À",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "88": {
140
- "content": "Ạ",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "89": {
148
- "content": "Ả",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- },
155
- "90": {
156
- "content": "Ã",
157
- "lstrip": false,
158
- "normalized": true,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "91": {
164
- "content": "Ấ",
165
- "lstrip": false,
166
- "normalized": true,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "92": {
172
- "content": "Ầ",
173
- "lstrip": false,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": false
178
- },
179
- "93": {
180
- "content": "Ậ",
181
- "lstrip": false,
182
- "normalized": true,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": false
186
- },
187
- "94": {
188
- "content": "Ẩ",
189
- "lstrip": false,
190
- "normalized": true,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": false
194
- },
195
- "95": {
196
- "content": "Ẫ",
197
- "lstrip": false,
198
- "normalized": true,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": false
202
- },
203
- "96": {
204
- "content": "ấ",
205
- "lstrip": false,
206
- "normalized": true,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": false
210
- },
211
- "97": {
212
- "content": "ầ",
213
- "lstrip": false,
214
- "normalized": true,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": false
218
- },
219
- "98": {
220
- "content": "ậ",
221
- "lstrip": false,
222
- "normalized": true,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": false
226
- },
227
- "99": {
228
- "content": "ẩ",
229
- "lstrip": false,
230
- "normalized": true,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": false
234
- },
235
- "100": {
236
- "content": "ẫ",
237
- "lstrip": false,
238
- "normalized": true,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": false
242
- },
243
- "101": {
244
- "content": "ắ",
245
- "lstrip": false,
246
- "normalized": true,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": false
250
- },
251
- "102": {
252
- "content": "ằ",
253
- "lstrip": false,
254
- "normalized": true,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": false
258
- },
259
- "103": {
260
- "content": "ẵ",
261
- "lstrip": false,
262
- "normalized": true,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": false
266
- },
267
- "104": {
268
- "content": "ặ",
269
- "lstrip": false,
270
- "normalized": true,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": false
274
- },
275
- "105": {
276
- "content": "ẳ",
277
- "lstrip": false,
278
- "normalized": true,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": false
282
- },
283
- "106": {
284
- "content": "è",
285
- "lstrip": false,
286
- "normalized": true,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": false
290
- },
291
- "107": {
292
- "content": "ẻ",
293
- "lstrip": false,
294
- "normalized": true,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": false
298
- },
299
- "108": {
300
- "content": "ẽ",
301
- "lstrip": false,
302
- "normalized": true,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": false
306
- },
307
- "109": {
308
- "content": "ẹ",
309
- "lstrip": false,
310
- "normalized": true,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": false
314
- },
315
- "110": {
316
- "content": "É",
317
- "lstrip": false,
318
- "normalized": true,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": false
322
- },
323
- "111": {
324
- "content": "È",
325
- "lstrip": false,
326
- "normalized": true,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": false
330
- },
331
- "112": {
332
- "content": "Ẻ",
333
- "lstrip": false,
334
- "normalized": true,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": false
338
- },
339
- "113": {
340
- "content": "Ẽ",
341
- "lstrip": false,
342
- "normalized": true,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": false
346
- },
347
- "114": {
348
- "content": "Ẹ",
349
- "lstrip": false,
350
- "normalized": true,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": false
354
- },
355
- "115": {
356
- "content": "ó",
357
- "lstrip": false,
358
- "normalized": true,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": false
362
- },
363
- "116": {
364
- "content": "ò",
365
- "lstrip": false,
366
- "normalized": true,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": false
370
- },
371
- "117": {
372
- "content": "ỏ",
373
- "lstrip": false,
374
- "normalized": true,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": false
378
- },
379
- "118": {
380
- "content": "õ",
381
- "lstrip": false,
382
- "normalized": true,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": false
386
- },
387
- "119": {
388
- "content": "ọ",
389
- "lstrip": false,
390
- "normalized": true,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "120": {
396
- "content": "Ó",
397
- "lstrip": false,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "121": {
404
- "content": "Ò",
405
- "lstrip": false,
406
- "normalized": true,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "122": {
412
- "content": "Ỏ",
413
- "lstrip": false,
414
- "normalized": true,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "123": {
420
- "content": "Õ",
421
- "lstrip": false,
422
- "normalized": true,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "124": {
428
- "content": "Ọ",
429
- "lstrip": false,
430
- "normalized": true,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "125": {
436
- "content": "ố",
437
- "lstrip": false,
438
- "normalized": true,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "126": {
444
- "content": "ồ",
445
- "lstrip": false,
446
- "normalized": true,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "127": {
452
- "content": "ỗ",
453
- "lstrip": false,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "128": {
460
- "content": "ổ",
461
- "lstrip": false,
462
- "normalized": true,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "129": {
468
- "content": "ộ",
469
- "lstrip": false,
470
- "normalized": true,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "130": {
476
- "content": "Ố",
477
- "lstrip": false,
478
- "normalized": true,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "131": {
484
- "content": "Ồ",
485
- "lstrip": false,
486
- "normalized": true,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": false
490
- },
491
- "132": {
492
- "content": "Ộ",
493
- "lstrip": false,
494
- "normalized": true,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": false
498
- },
499
- "133": {
500
- "content": "Ổ",
501
- "lstrip": false,
502
- "normalized": true,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": false
506
- },
507
- "134": {
508
- "content": "Ỗ",
509
- "lstrip": false,
510
- "normalized": true,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": false
514
- },
515
- "135": {
516
- "content": "ớ",
517
- "lstrip": false,
518
- "normalized": true,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": false
522
- },
523
- "136": {
524
- "content": "ờ",
525
- "lstrip": false,
526
- "normalized": true,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": false
530
- },
531
- "137": {
532
- "content": "ở",
533
- "lstrip": false,
534
- "normalized": true,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": false
538
- },
539
- "138": {
540
- "content": "ỡ",
541
- "lstrip": false,
542
- "normalized": true,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": false
546
- },
547
- "139": {
548
- "content": "ợ",
549
- "lstrip": false,
550
- "normalized": true,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": false
554
- },
555
- "140": {
556
- "content": "Ớ",
557
- "lstrip": false,
558
- "normalized": true,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": false
562
- },
563
- "141": {
564
- "content": "Ờ",
565
- "lstrip": false,
566
- "normalized": true,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": false
570
- },
571
- "142": {
572
- "content": "Ợ",
573
- "lstrip": false,
574
- "normalized": true,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": false
578
- },
579
- "143": {
580
- "content": "Ở",
581
- "lstrip": false,
582
- "normalized": true,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": false
586
- },
587
- "144": {
588
- "content": "Ỡ",
589
- "lstrip": false,
590
- "normalized": true,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": false
594
- },
595
- "145": {
596
- "content": "í",
597
- "lstrip": false,
598
- "normalized": true,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": false
602
- },
603
- "146": {
604
- "content": "ì",
605
- "lstrip": false,
606
- "normalized": true,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": false
610
- },
611
- "147": {
612
- "content": "ị",
613
- "lstrip": false,
614
- "normalized": true,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": false
618
- },
619
- "148": {
620
- "content": "ĩ",
621
- "lstrip": false,
622
- "normalized": true,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": false
626
- },
627
- "149": {
628
- "content": "ỉ",
629
- "lstrip": false,
630
- "normalized": true,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": false
634
- },
635
- "150": {
636
- "content": "Í",
637
- "lstrip": false,
638
- "normalized": true,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": false
642
- },
643
- "151": {
644
- "content": "Ì",
645
- "lstrip": false,
646
- "normalized": true,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": false
650
- },
651
- "152": {
652
- "content": "Ỉ",
653
- "lstrip": false,
654
- "normalized": true,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": false
658
- },
659
- "153": {
660
- "content": "Ĩ",
661
- "lstrip": false,
662
- "normalized": true,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": false
666
- },
667
- "154": {
668
- "content": "Ị",
669
- "lstrip": false,
670
- "normalized": true,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": false
674
- },
675
- "155": {
676
- "content": "ý",
677
- "lstrip": false,
678
- "normalized": true,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": false
682
- },
683
- "156": {
684
- "content": "ỳ",
685
- "lstrip": false,
686
- "normalized": true,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": false
690
- },
691
- "157": {
692
- "content": "ỷ",
693
- "lstrip": false,
694
- "normalized": true,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": false
698
- },
699
- "158": {
700
- "content": "ỹ",
701
- "lstrip": false,
702
- "normalized": true,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": false
706
- },
707
- "159": {
708
- "content": "ỵ",
709
- "lstrip": false,
710
- "normalized": true,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": false
714
- },
715
- "160": {
716
- "content": "Ý",
717
- "lstrip": false,
718
- "normalized": true,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": false
722
- },
723
- "161": {
724
- "content": "Ỳ",
725
- "lstrip": false,
726
- "normalized": true,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": false
730
- },
731
- "162": {
732
- "content": "Ỷ",
733
- "lstrip": false,
734
- "normalized": true,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": false
738
- },
739
- "163": {
740
- "content": "Ỵ",
741
- "lstrip": false,
742
- "normalized": true,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": false
746
- },
747
- "164": {
748
- "content": "Ỹ",
749
- "lstrip": false,
750
- "normalized": true,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": false
754
- },
755
- "165": {
756
- "content": "ế",
757
- "lstrip": false,
758
- "normalized": true,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": false
762
- },
763
- "166": {
764
- "content": "ề",
765
- "lstrip": false,
766
- "normalized": true,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": false
770
- },
771
- "167": {
772
- "content": "ể",
773
- "lstrip": false,
774
- "normalized": true,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": false
778
- },
779
- "168": {
780
- "content": "ễ",
781
- "lstrip": false,
782
- "normalized": true,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": false
786
- },
787
- "169": {
788
- "content": "ệ",
789
- "lstrip": false,
790
- "normalized": true,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": false
794
- },
795
- "170": {
796
- "content": "Ế",
797
- "lstrip": false,
798
- "normalized": true,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": false
802
- },
803
- "171": {
804
- "content": "Ề",
805
- "lstrip": false,
806
- "normalized": true,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": false
810
- },
811
- "172": {
812
- "content": "Ể",
813
- "lstrip": false,
814
- "normalized": true,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": false
818
- },
819
- "173": {
820
- "content": "Ễ",
821
- "lstrip": false,
822
- "normalized": true,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": false
826
- },
827
- "174": {
828
- "content": "Ệ",
829
- "lstrip": false,
830
- "normalized": true,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": false
834
- },
835
- "175": {
836
- "content": "Đ",
837
- "lstrip": false,
838
- "normalized": true,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": false
842
- },
843
- "176": {
844
- "content": "đ",
845
- "lstrip": false,
846
- "normalized": true,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": false
850
- },
851
- "177": {
852
- "content": " ",
853
- "lstrip": false,
854
- "normalized": true,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": false
858
  }
859
  },
860
  "bos_token": "<s>",
 
32
  "single_word": false,
33
  "special": true
34
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "79": {
36
  "content": "<mask>",
37
  "lstrip": true,
 
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  }
51
  },
52
  "bos_token": "<s>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ecd6d6ed9dff5c2bbe1ef736c2cbdc598085c8f2a7a26d0ac50f61923ad122
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9cdf6e3be7665bc234975c669b27c236a24be00036817a759a62644955df280
3
  size 5368