Safetensors
wav2vec2-bert
indiejoseph commited on
Commit
05a0a95
·
verified ·
1 Parent(s): f923cfc

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. added_tokens.json +2 -2
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. tokenizer_config.json +1753 -81
  5. vocab.json +287 -78
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 82,
3
- "<s>": 81
4
  }
 
1
  {
2
+ "</s>": 291,
3
+ "<s>": 290
4
  }
config.json CHANGED
@@ -74,9 +74,9 @@
74
  1
75
  ],
76
  "torch_dtype": "float32",
77
- "transformers_version": "4.39.3",
78
  "use_intermediate_ffn_before_adapter": false,
79
  "use_weighted_layer_sum": false,
80
- "vocab_size": 83,
81
  "xvector_output_dim": 512
82
  }
 
74
  1
75
  ],
76
  "torch_dtype": "float32",
77
+ "transformers_version": "4.45.0.dev0",
78
  "use_intermediate_ffn_before_adapter": false,
79
  "use_weighted_layer_sum": false,
80
+ "vocab_size": 292,
81
  "xvector_output_dim": 512
82
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c18469221b41744812126ceae2a2f29a390789676cbcdd9b89afa9fd79387f3
3
- size 2423154860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbce4d6dfcd28928a3c2fc3b1bee90a6c879ac5927be8dd26d4875fef62e7052
3
+ size 2424011768
tokenizer_config.json CHANGED
@@ -25,7 +25,7 @@
25
  "special": false
26
  },
27
  "3": {
28
- "content": "1",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
@@ -33,7 +33,7 @@
33
  "special": false
34
  },
35
  "4": {
36
- "content": "2",
37
  "lstrip": false,
38
  "normalized": true,
39
  "rstrip": false,
@@ -41,7 +41,7 @@
41
  "special": false
42
  },
43
  "5": {
44
- "content": "3",
45
  "lstrip": false,
46
  "normalized": true,
47
  "rstrip": false,
@@ -49,7 +49,7 @@
49
  "special": false
50
  },
51
  "6": {
52
- "content": "4",
53
  "lstrip": false,
54
  "normalized": true,
55
  "rstrip": false,
@@ -57,7 +57,7 @@
57
  "special": false
58
  },
59
  "7": {
60
- "content": "5",
61
  "lstrip": false,
62
  "normalized": true,
63
  "rstrip": false,
@@ -65,7 +65,7 @@
65
  "special": false
66
  },
67
  "8": {
68
- "content": "6",
69
  "lstrip": false,
70
  "normalized": true,
71
  "rstrip": false,
@@ -73,7 +73,7 @@
73
  "special": false
74
  },
75
  "9": {
76
- "content": "M",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
@@ -81,7 +81,7 @@
81
  "special": false
82
  },
83
  "10": {
84
- "content": "Ng",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
@@ -89,7 +89,7 @@
89
  "special": false
90
  },
91
  "11": {
92
- "content": "aa",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
@@ -97,7 +97,7 @@
97
  "special": false
98
  },
99
  "12": {
100
- "content": "aai",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
@@ -105,7 +105,7 @@
105
  "special": false
106
  },
107
  "13": {
108
- "content": "aak",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  "special": false
114
  },
115
  "14": {
116
- "content": "aam",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
@@ -121,7 +121,7 @@
121
  "special": false
122
  },
123
  "15": {
124
- "content": "aan",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
@@ -129,7 +129,7 @@
129
  "special": false
130
  },
131
  "16": {
132
- "content": "aang",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
@@ -137,7 +137,7 @@
137
  "special": false
138
  },
139
  "17": {
140
- "content": "aap",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
@@ -145,7 +145,7 @@
145
  "special": false
146
  },
147
  "18": {
148
- "content": "aat",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
@@ -153,7 +153,7 @@
153
  "special": false
154
  },
155
  "19": {
156
- "content": "aau",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
@@ -161,7 +161,7 @@
161
  "special": false
162
  },
163
  "20": {
164
- "content": "ai",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
@@ -169,7 +169,7 @@
169
  "special": false
170
  },
171
  "21": {
172
- "content": "ak",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
@@ -177,7 +177,7 @@
177
  "special": false
178
  },
179
  "22": {
180
- "content": "am",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  "special": false
186
  },
187
  "23": {
188
- "content": "an",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
@@ -193,7 +193,7 @@
193
  "special": false
194
  },
195
  "24": {
196
- "content": "ang",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
@@ -201,7 +201,7 @@
201
  "special": false
202
  },
203
  "25": {
204
- "content": "ap",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
@@ -209,7 +209,7 @@
209
  "special": false
210
  },
211
  "26": {
212
- "content": "at",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
@@ -217,7 +217,7 @@
217
  "special": false
218
  },
219
  "27": {
220
- "content": "au",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
@@ -225,7 +225,7 @@
225
  "special": false
226
  },
227
  "28": {
228
- "content": "b",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
@@ -233,7 +233,7 @@
233
  "special": false
234
  },
235
  "29": {
236
- "content": "c",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
@@ -241,7 +241,7 @@
241
  "special": false
242
  },
243
  "30": {
244
- "content": "d",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
@@ -249,7 +249,7 @@
249
  "special": false
250
  },
251
  "31": {
252
- "content": "e",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  "special": false
258
  },
259
  "32": {
260
- "content": "ei",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
@@ -265,7 +265,7 @@
265
  "special": false
266
  },
267
  "33": {
268
- "content": "ek",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
@@ -273,7 +273,7 @@
273
  "special": false
274
  },
275
  "34": {
276
- "content": "eng",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
@@ -281,7 +281,7 @@
281
  "special": false
282
  },
283
  "35": {
284
- "content": "eoi",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
@@ -289,7 +289,7 @@
289
  "special": false
290
  },
291
  "36": {
292
- "content": "eon",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
@@ -297,7 +297,7 @@
297
  "special": false
298
  },
299
  "37": {
300
- "content": "eot",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
@@ -305,7 +305,7 @@
305
  "special": false
306
  },
307
  "38": {
308
- "content": "f",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
@@ -313,7 +313,7 @@
313
  "special": false
314
  },
315
  "39": {
316
- "content": "g",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
@@ -321,7 +321,7 @@
321
  "special": false
322
  },
323
  "40": {
324
- "content": "gw",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  "special": false
330
  },
331
  "41": {
332
- "content": "h",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
@@ -337,7 +337,7 @@
337
  "special": false
338
  },
339
  "42": {
340
- "content": "i",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
@@ -345,7 +345,7 @@
345
  "special": false
346
  },
347
  "43": {
348
- "content": "ik",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
@@ -353,7 +353,7 @@
353
  "special": false
354
  },
355
  "44": {
356
- "content": "im",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
@@ -361,7 +361,7 @@
361
  "special": false
362
  },
363
  "45": {
364
- "content": "in",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
@@ -369,7 +369,7 @@
369
  "special": false
370
  },
371
  "46": {
372
- "content": "ing",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
@@ -377,7 +377,7 @@
377
  "special": false
378
  },
379
  "47": {
380
- "content": "ip",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
@@ -385,7 +385,7 @@
385
  "special": false
386
  },
387
  "48": {
388
- "content": "it",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
@@ -393,7 +393,7 @@
393
  "special": false
394
  },
395
  "49": {
396
- "content": "iu",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  "special": false
402
  },
403
  "50": {
404
- "content": "j",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
@@ -409,7 +409,7 @@
409
  "special": false
410
  },
411
  "51": {
412
- "content": "k",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
@@ -417,7 +417,7 @@
417
  "special": false
418
  },
419
  "52": {
420
- "content": "kw",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
@@ -425,7 +425,7 @@
425
  "special": false
426
  },
427
  "53": {
428
- "content": "l",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
@@ -433,7 +433,7 @@
433
  "special": false
434
  },
435
  "54": {
436
- "content": "m",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
@@ -441,7 +441,7 @@
441
  "special": false
442
  },
443
  "55": {
444
- "content": "n",
445
  "lstrip": false,
446
  "normalized": true,
447
  "rstrip": false,
@@ -449,7 +449,7 @@
449
  "special": false
450
  },
451
  "56": {
452
- "content": "ng",
453
  "lstrip": false,
454
  "normalized": true,
455
  "rstrip": false,
@@ -457,7 +457,7 @@
457
  "special": false
458
  },
459
  "57": {
460
- "content": "o",
461
  "lstrip": false,
462
  "normalized": true,
463
  "rstrip": false,
@@ -465,7 +465,7 @@
465
  "special": false
466
  },
467
  "58": {
468
- "content": "oe",
469
  "lstrip": false,
470
  "normalized": true,
471
  "rstrip": false,
@@ -473,7 +473,7 @@
473
  "special": false
474
  },
475
  "59": {
476
- "content": "oek",
477
  "lstrip": false,
478
  "normalized": true,
479
  "rstrip": false,
@@ -481,7 +481,7 @@
481
  "special": false
482
  },
483
  "60": {
484
- "content": "oeng",
485
  "lstrip": false,
486
  "normalized": true,
487
  "rstrip": false,
@@ -489,7 +489,7 @@
489
  "special": false
490
  },
491
  "61": {
492
- "content": "oi",
493
  "lstrip": false,
494
  "normalized": true,
495
  "rstrip": false,
@@ -497,7 +497,7 @@
497
  "special": false
498
  },
499
  "62": {
500
- "content": "ok",
501
  "lstrip": false,
502
  "normalized": true,
503
  "rstrip": false,
@@ -505,7 +505,7 @@
505
  "special": false
506
  },
507
  "63": {
508
- "content": "on",
509
  "lstrip": false,
510
  "normalized": true,
511
  "rstrip": false,
@@ -513,7 +513,7 @@
513
  "special": false
514
  },
515
  "64": {
516
- "content": "ong",
517
  "lstrip": false,
518
  "normalized": true,
519
  "rstrip": false,
@@ -521,7 +521,7 @@
521
  "special": false
522
  },
523
  "65": {
524
- "content": "ot",
525
  "lstrip": false,
526
  "normalized": true,
527
  "rstrip": false,
@@ -529,7 +529,7 @@
529
  "special": false
530
  },
531
  "66": {
532
- "content": "ou",
533
  "lstrip": false,
534
  "normalized": true,
535
  "rstrip": false,
@@ -537,7 +537,7 @@
537
  "special": false
538
  },
539
  "67": {
540
- "content": "p",
541
  "lstrip": false,
542
  "normalized": true,
543
  "rstrip": false,
@@ -545,7 +545,7 @@
545
  "special": false
546
  },
547
  "68": {
548
- "content": "s",
549
  "lstrip": false,
550
  "normalized": true,
551
  "rstrip": false,
@@ -553,7 +553,7 @@
553
  "special": false
554
  },
555
  "69": {
556
- "content": "t",
557
  "lstrip": false,
558
  "normalized": true,
559
  "rstrip": false,
@@ -561,7 +561,7 @@
561
  "special": false
562
  },
563
  "70": {
564
- "content": "u",
565
  "lstrip": false,
566
  "normalized": true,
567
  "rstrip": false,
@@ -569,7 +569,7 @@
569
  "special": false
570
  },
571
  "71": {
572
- "content": "ui",
573
  "lstrip": false,
574
  "normalized": true,
575
  "rstrip": false,
@@ -577,7 +577,7 @@
577
  "special": false
578
  },
579
  "72": {
580
- "content": "uk",
581
  "lstrip": false,
582
  "normalized": true,
583
  "rstrip": false,
@@ -585,7 +585,7 @@
585
  "special": false
586
  },
587
  "73": {
588
- "content": "un",
589
  "lstrip": false,
590
  "normalized": true,
591
  "rstrip": false,
@@ -593,7 +593,7 @@
593
  "special": false
594
  },
595
  "74": {
596
- "content": "ung",
597
  "lstrip": false,
598
  "normalized": true,
599
  "rstrip": false,
@@ -601,7 +601,7 @@
601
  "special": false
602
  },
603
  "75": {
604
- "content": "ut",
605
  "lstrip": false,
606
  "normalized": true,
607
  "rstrip": false,
@@ -609,7 +609,7 @@
609
  "special": false
610
  },
611
  "76": {
612
- "content": "w",
613
  "lstrip": false,
614
  "normalized": true,
615
  "rstrip": false,
@@ -617,7 +617,7 @@
617
  "special": false
618
  },
619
  "77": {
620
- "content": "yu",
621
  "lstrip": false,
622
  "normalized": true,
623
  "rstrip": false,
@@ -625,7 +625,7 @@
625
  "special": false
626
  },
627
  "78": {
628
- "content": "yun",
629
  "lstrip": false,
630
  "normalized": true,
631
  "rstrip": false,
@@ -633,7 +633,7 @@
633
  "special": false
634
  },
635
  "79": {
636
- "content": "yut",
637
  "lstrip": false,
638
  "normalized": true,
639
  "rstrip": false,
@@ -641,7 +641,7 @@
641
  "special": false
642
  },
643
  "80": {
644
- "content": "z",
645
  "lstrip": false,
646
  "normalized": true,
647
  "rstrip": false,
@@ -649,14 +649,1686 @@
649
  "special": false
650
  },
651
  "81": {
652
- "content": "<s>",
653
  "lstrip": false,
654
- "normalized": false,
655
  "rstrip": false,
656
  "single_word": false,
657
- "special": true
658
  },
659
  "82": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
660
  "content": "</s>",
661
  "lstrip": false,
662
  "normalized": false,
 
25
  "special": false
26
  },
27
  "3": {
28
+ "content": "aa1",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
 
33
  "special": false
34
  },
35
  "4": {
36
+ "content": "aa2",
37
  "lstrip": false,
38
  "normalized": true,
39
  "rstrip": false,
 
41
  "special": false
42
  },
43
  "5": {
44
+ "content": "aa3",
45
  "lstrip": false,
46
  "normalized": true,
47
  "rstrip": false,
 
49
  "special": false
50
  },
51
  "6": {
52
+ "content": "aa4",
53
  "lstrip": false,
54
  "normalized": true,
55
  "rstrip": false,
 
57
  "special": false
58
  },
59
  "7": {
60
+ "content": "aa5",
61
  "lstrip": false,
62
  "normalized": true,
63
  "rstrip": false,
 
65
  "special": false
66
  },
67
  "8": {
68
+ "content": "aa6",
69
  "lstrip": false,
70
  "normalized": true,
71
  "rstrip": false,
 
73
  "special": false
74
  },
75
  "9": {
76
+ "content": "aai1",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
 
81
  "special": false
82
  },
83
  "10": {
84
+ "content": "aai2",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
 
89
  "special": false
90
  },
91
  "11": {
92
+ "content": "aai3",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
 
97
  "special": false
98
  },
99
  "12": {
100
+ "content": "aai4",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
 
105
  "special": false
106
  },
107
  "13": {
108
+ "content": "aai5",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
 
113
  "special": false
114
  },
115
  "14": {
116
+ "content": "aai6",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
 
121
  "special": false
122
  },
123
  "15": {
124
+ "content": "aak1",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
 
129
  "special": false
130
  },
131
  "16": {
132
+ "content": "aak2",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
 
137
  "special": false
138
  },
139
  "17": {
140
+ "content": "aak3",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
 
145
  "special": false
146
  },
147
  "18": {
148
+ "content": "aak6",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
 
153
  "special": false
154
  },
155
  "19": {
156
+ "content": "aam1",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
 
161
  "special": false
162
  },
163
  "20": {
164
+ "content": "aam2",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
 
169
  "special": false
170
  },
171
  "21": {
172
+ "content": "aam3",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
 
177
  "special": false
178
  },
179
  "22": {
180
+ "content": "aam4",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
 
185
  "special": false
186
  },
187
  "23": {
188
+ "content": "aam5",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
 
193
  "special": false
194
  },
195
  "24": {
196
+ "content": "aam6",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
 
201
  "special": false
202
  },
203
  "25": {
204
+ "content": "aan1",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
 
209
  "special": false
210
  },
211
  "26": {
212
+ "content": "aan2",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
 
217
  "special": false
218
  },
219
  "27": {
220
+ "content": "aan3",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
 
225
  "special": false
226
  },
227
  "28": {
228
+ "content": "aan4",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
 
233
  "special": false
234
  },
235
  "29": {
236
+ "content": "aan5",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
 
241
  "special": false
242
  },
243
  "30": {
244
+ "content": "aan6",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
 
249
  "special": false
250
  },
251
  "31": {
252
+ "content": "aang1",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
 
257
  "special": false
258
  },
259
  "32": {
260
+ "content": "aang2",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
 
265
  "special": false
266
  },
267
  "33": {
268
+ "content": "aang3",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
 
273
  "special": false
274
  },
275
  "34": {
276
+ "content": "aang4",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
 
281
  "special": false
282
  },
283
  "35": {
284
+ "content": "aang5",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
 
289
  "special": false
290
  },
291
  "36": {
292
+ "content": "aang6",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
 
297
  "special": false
298
  },
299
  "37": {
300
+ "content": "aap1",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
 
305
  "special": false
306
  },
307
  "38": {
308
+ "content": "aap2",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
 
313
  "special": false
314
  },
315
  "39": {
316
+ "content": "aap3",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
 
321
  "special": false
322
  },
323
  "40": {
324
+ "content": "aap6",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
 
329
  "special": false
330
  },
331
  "41": {
332
+ "content": "aat1",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
 
337
  "special": false
338
  },
339
  "42": {
340
+ "content": "aat2",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
 
345
  "special": false
346
  },
347
  "43": {
348
+ "content": "aat3",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
 
353
  "special": false
354
  },
355
  "44": {
356
+ "content": "aat6",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
 
361
  "special": false
362
  },
363
  "45": {
364
+ "content": "aau1",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
 
369
  "special": false
370
  },
371
  "46": {
372
+ "content": "aau2",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
 
377
  "special": false
378
  },
379
  "47": {
380
+ "content": "aau3",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
 
385
  "special": false
386
  },
387
  "48": {
388
+ "content": "aau4",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
 
393
  "special": false
394
  },
395
  "49": {
396
+ "content": "aau5",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
 
401
  "special": false
402
  },
403
  "50": {
404
+ "content": "aau6",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
 
409
  "special": false
410
  },
411
  "51": {
412
+ "content": "ai1",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
 
417
  "special": false
418
  },
419
  "52": {
420
+ "content": "ai2",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
 
425
  "special": false
426
  },
427
  "53": {
428
+ "content": "ai3",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
 
433
  "special": false
434
  },
435
  "54": {
436
+ "content": "ai4",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
 
441
  "special": false
442
  },
443
  "55": {
444
+ "content": "ai5",
445
  "lstrip": false,
446
  "normalized": true,
447
  "rstrip": false,
 
449
  "special": false
450
  },
451
  "56": {
452
+ "content": "ai6",
453
  "lstrip": false,
454
  "normalized": true,
455
  "rstrip": false,
 
457
  "special": false
458
  },
459
  "57": {
460
+ "content": "ak1",
461
  "lstrip": false,
462
  "normalized": true,
463
  "rstrip": false,
 
465
  "special": false
466
  },
467
  "58": {
468
+ "content": "ak2",
469
  "lstrip": false,
470
  "normalized": true,
471
  "rstrip": false,
 
473
  "special": false
474
  },
475
  "59": {
476
+ "content": "ak6",
477
  "lstrip": false,
478
  "normalized": true,
479
  "rstrip": false,
 
481
  "special": false
482
  },
483
  "60": {
484
+ "content": "am1",
485
  "lstrip": false,
486
  "normalized": true,
487
  "rstrip": false,
 
489
  "special": false
490
  },
491
  "61": {
492
+ "content": "am2",
493
  "lstrip": false,
494
  "normalized": true,
495
  "rstrip": false,
 
497
  "special": false
498
  },
499
  "62": {
500
+ "content": "am3",
501
  "lstrip": false,
502
  "normalized": true,
503
  "rstrip": false,
 
505
  "special": false
506
  },
507
  "63": {
508
+ "content": "am4",
509
  "lstrip": false,
510
  "normalized": true,
511
  "rstrip": false,
 
513
  "special": false
514
  },
515
  "64": {
516
+ "content": "am5",
517
  "lstrip": false,
518
  "normalized": true,
519
  "rstrip": false,
 
521
  "special": false
522
  },
523
  "65": {
524
+ "content": "am6",
525
  "lstrip": false,
526
  "normalized": true,
527
  "rstrip": false,
 
529
  "special": false
530
  },
531
  "66": {
532
+ "content": "an1",
533
  "lstrip": false,
534
  "normalized": true,
535
  "rstrip": false,
 
537
  "special": false
538
  },
539
  "67": {
540
+ "content": "an2",
541
  "lstrip": false,
542
  "normalized": true,
543
  "rstrip": false,
 
545
  "special": false
546
  },
547
  "68": {
548
+ "content": "an3",
549
  "lstrip": false,
550
  "normalized": true,
551
  "rstrip": false,
 
553
  "special": false
554
  },
555
  "69": {
556
+ "content": "an4",
557
  "lstrip": false,
558
  "normalized": true,
559
  "rstrip": false,
 
561
  "special": false
562
  },
563
  "70": {
564
+ "content": "an5",
565
  "lstrip": false,
566
  "normalized": true,
567
  "rstrip": false,
 
569
  "special": false
570
  },
571
  "71": {
572
+ "content": "an6",
573
  "lstrip": false,
574
  "normalized": true,
575
  "rstrip": false,
 
577
  "special": false
578
  },
579
  "72": {
580
+ "content": "ang1",
581
  "lstrip": false,
582
  "normalized": true,
583
  "rstrip": false,
 
585
  "special": false
586
  },
587
  "73": {
588
+ "content": "ang2",
589
  "lstrip": false,
590
  "normalized": true,
591
  "rstrip": false,
 
593
  "special": false
594
  },
595
  "74": {
596
+ "content": "ang3",
597
  "lstrip": false,
598
  "normalized": true,
599
  "rstrip": false,
 
601
  "special": false
602
  },
603
  "75": {
604
+ "content": "ang4",
605
  "lstrip": false,
606
  "normalized": true,
607
  "rstrip": false,
 
609
  "special": false
610
  },
611
  "76": {
612
+ "content": "ang6",
613
  "lstrip": false,
614
  "normalized": true,
615
  "rstrip": false,
 
617
  "special": false
618
  },
619
  "77": {
620
+ "content": "ap1",
621
  "lstrip": false,
622
  "normalized": true,
623
  "rstrip": false,
 
625
  "special": false
626
  },
627
  "78": {
628
+ "content": "ap2",
629
  "lstrip": false,
630
  "normalized": true,
631
  "rstrip": false,
 
633
  "special": false
634
  },
635
  "79": {
636
+ "content": "ap6",
637
  "lstrip": false,
638
  "normalized": true,
639
  "rstrip": false,
 
641
  "special": false
642
  },
643
  "80": {
644
+ "content": "at1",
645
  "lstrip": false,
646
  "normalized": true,
647
  "rstrip": false,
 
649
  "special": false
650
  },
651
  "81": {
652
+ "content": "at2",
653
  "lstrip": false,
654
+ "normalized": true,
655
  "rstrip": false,
656
  "single_word": false,
657
+ "special": false
658
  },
659
  "82": {
660
+ "content": "at3",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "83": {
668
+ "content": "at6",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "84": {
676
+ "content": "au1",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "85": {
684
+ "content": "au2",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "86": {
692
+ "content": "au3",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "87": {
700
+ "content": "au4",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "88": {
708
+ "content": "au5",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "89": {
716
+ "content": "au6",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "90": {
724
+ "content": "b",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "91": {
732
+ "content": "c",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "92": {
740
+ "content": "d",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "93": {
748
+ "content": "e1",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "94": {
756
+ "content": "e2",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95": {
764
+ "content": "e3",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "96": {
772
+ "content": "e4",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "97": {
780
+ "content": "e5",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "98": {
788
+ "content": "e6",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "99": {
796
+ "content": "ei1",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "100": {
804
+ "content": "ei2",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "101": {
812
+ "content": "ei3",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "102": {
820
+ "content": "ei4",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "103": {
828
+ "content": "ei5",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "104": {
836
+ "content": "ei6",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "105": {
844
+ "content": "ek1",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "106": {
852
+ "content": "ek2",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "107": {
860
+ "content": "ek3",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "108": {
868
+ "content": "ek6",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "109": {
876
+ "content": "eng1",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "110": {
884
+ "content": "eng2",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "111": {
892
+ "content": "eng3",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "112": {
900
+ "content": "eng4",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "113": {
908
+ "content": "eng5",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "114": {
916
+ "content": "eng6",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "115": {
924
+ "content": "eoi1",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ },
931
+ "116": {
932
+ "content": "eoi2",
933
+ "lstrip": false,
934
+ "normalized": true,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": false
938
+ },
939
+ "117": {
940
+ "content": "eoi3",
941
+ "lstrip": false,
942
+ "normalized": true,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": false
946
+ },
947
+ "118": {
948
+ "content": "eoi4",
949
+ "lstrip": false,
950
+ "normalized": true,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": false
954
+ },
955
+ "119": {
956
+ "content": "eoi5",
957
+ "lstrip": false,
958
+ "normalized": true,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": false
962
+ },
963
+ "120": {
964
+ "content": "eoi6",
965
+ "lstrip": false,
966
+ "normalized": true,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": false
970
+ },
971
+ "121": {
972
+ "content": "eon1",
973
+ "lstrip": false,
974
+ "normalized": true,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": false
978
+ },
979
+ "122": {
980
+ "content": "eon2",
981
+ "lstrip": false,
982
+ "normalized": true,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": false
986
+ },
987
+ "123": {
988
+ "content": "eon3",
989
+ "lstrip": false,
990
+ "normalized": true,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": false
994
+ },
995
+ "124": {
996
+ "content": "eon4",
997
+ "lstrip": false,
998
+ "normalized": true,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": false
1002
+ },
1003
+ "125": {
1004
+ "content": "eon5",
1005
+ "lstrip": false,
1006
+ "normalized": true,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": false
1010
+ },
1011
+ "126": {
1012
+ "content": "eon6",
1013
+ "lstrip": false,
1014
+ "normalized": true,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": false
1018
+ },
1019
+ "127": {
1020
+ "content": "eot1",
1021
+ "lstrip": false,
1022
+ "normalized": true,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": false
1026
+ },
1027
+ "128": {
1028
+ "content": "eot2",
1029
+ "lstrip": false,
1030
+ "normalized": true,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": false
1034
+ },
1035
+ "129": {
1036
+ "content": "eot6",
1037
+ "lstrip": false,
1038
+ "normalized": true,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": false
1042
+ },
1043
+ "130": {
1044
+ "content": "ep6",
1045
+ "lstrip": false,
1046
+ "normalized": true,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": false
1050
+ },
1051
+ "131": {
1052
+ "content": "eu6",
1053
+ "lstrip": false,
1054
+ "normalized": true,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": false
1058
+ },
1059
+ "132": {
1060
+ "content": "f",
1061
+ "lstrip": false,
1062
+ "normalized": true,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": false
1066
+ },
1067
+ "133": {
1068
+ "content": "g",
1069
+ "lstrip": false,
1070
+ "normalized": true,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": false
1074
+ },
1075
+ "134": {
1076
+ "content": "gw",
1077
+ "lstrip": false,
1078
+ "normalized": true,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": false
1082
+ },
1083
+ "135": {
1084
+ "content": "h",
1085
+ "lstrip": false,
1086
+ "normalized": true,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": false
1090
+ },
1091
+ "136": {
1092
+ "content": "i1",
1093
+ "lstrip": false,
1094
+ "normalized": true,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": false
1098
+ },
1099
+ "137": {
1100
+ "content": "i2",
1101
+ "lstrip": false,
1102
+ "normalized": true,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": false
1106
+ },
1107
+ "138": {
1108
+ "content": "i3",
1109
+ "lstrip": false,
1110
+ "normalized": true,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": false
1114
+ },
1115
+ "139": {
1116
+ "content": "i4",
1117
+ "lstrip": false,
1118
+ "normalized": true,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": false
1122
+ },
1123
+ "140": {
1124
+ "content": "i5",
1125
+ "lstrip": false,
1126
+ "normalized": true,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": false
1130
+ },
1131
+ "141": {
1132
+ "content": "i6",
1133
+ "lstrip": false,
1134
+ "normalized": true,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": false
1138
+ },
1139
+ "142": {
1140
+ "content": "ik1",
1141
+ "lstrip": false,
1142
+ "normalized": true,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": false
1146
+ },
1147
+ "143": {
1148
+ "content": "ik3",
1149
+ "lstrip": false,
1150
+ "normalized": true,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": false
1154
+ },
1155
+ "144": {
1156
+ "content": "ik4",
1157
+ "lstrip": false,
1158
+ "normalized": true,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": false
1162
+ },
1163
+ "145": {
1164
+ "content": "ik6",
1165
+ "lstrip": false,
1166
+ "normalized": true,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": false
1170
+ },
1171
+ "146": {
1172
+ "content": "im1",
1173
+ "lstrip": false,
1174
+ "normalized": true,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": false
1178
+ },
1179
+ "147": {
1180
+ "content": "im2",
1181
+ "lstrip": false,
1182
+ "normalized": true,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": false
1186
+ },
1187
+ "148": {
1188
+ "content": "im3",
1189
+ "lstrip": false,
1190
+ "normalized": true,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": false
1194
+ },
1195
+ "149": {
1196
+ "content": "im4",
1197
+ "lstrip": false,
1198
+ "normalized": true,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": false
1202
+ },
1203
+ "150": {
1204
+ "content": "im5",
1205
+ "lstrip": false,
1206
+ "normalized": true,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": false
1210
+ },
1211
+ "151": {
1212
+ "content": "im6",
1213
+ "lstrip": false,
1214
+ "normalized": true,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": false
1218
+ },
1219
+ "152": {
1220
+ "content": "in1",
1221
+ "lstrip": false,
1222
+ "normalized": true,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": false
1226
+ },
1227
+ "153": {
1228
+ "content": "in2",
1229
+ "lstrip": false,
1230
+ "normalized": true,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": false
1234
+ },
1235
+ "154": {
1236
+ "content": "in3",
1237
+ "lstrip": false,
1238
+ "normalized": true,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": false
1242
+ },
1243
+ "155": {
1244
+ "content": "in4",
1245
+ "lstrip": false,
1246
+ "normalized": true,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": false
1250
+ },
1251
+ "156": {
1252
+ "content": "in5",
1253
+ "lstrip": false,
1254
+ "normalized": true,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": false
1258
+ },
1259
+ "157": {
1260
+ "content": "in6",
1261
+ "lstrip": false,
1262
+ "normalized": true,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": false
1266
+ },
1267
+ "158": {
1268
+ "content": "ing1",
1269
+ "lstrip": false,
1270
+ "normalized": true,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": false
1274
+ },
1275
+ "159": {
1276
+ "content": "ing2",
1277
+ "lstrip": false,
1278
+ "normalized": true,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": false
1282
+ },
1283
+ "160": {
1284
+ "content": "ing3",
1285
+ "lstrip": false,
1286
+ "normalized": true,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": false
1290
+ },
1291
+ "161": {
1292
+ "content": "ing4",
1293
+ "lstrip": false,
1294
+ "normalized": true,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": false
1298
+ },
1299
+ "162": {
1300
+ "content": "ing5",
1301
+ "lstrip": false,
1302
+ "normalized": true,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": false
1306
+ },
1307
+ "163": {
1308
+ "content": "ing6",
1309
+ "lstrip": false,
1310
+ "normalized": true,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": false
1314
+ },
1315
+ "164": {
1316
+ "content": "ip1",
1317
+ "lstrip": false,
1318
+ "normalized": true,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": false
1322
+ },
1323
+ "165": {
1324
+ "content": "ip2",
1325
+ "lstrip": false,
1326
+ "normalized": true,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": false
1330
+ },
1331
+ "166": {
1332
+ "content": "ip3",
1333
+ "lstrip": false,
1334
+ "normalized": true,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": false
1338
+ },
1339
+ "167": {
1340
+ "content": "ip6",
1341
+ "lstrip": false,
1342
+ "normalized": true,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": false
1346
+ },
1347
+ "168": {
1348
+ "content": "it1",
1349
+ "lstrip": false,
1350
+ "normalized": true,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": false
1354
+ },
1355
+ "169": {
1356
+ "content": "it3",
1357
+ "lstrip": false,
1358
+ "normalized": true,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": false
1362
+ },
1363
+ "170": {
1364
+ "content": "it6",
1365
+ "lstrip": false,
1366
+ "normalized": true,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": false
1370
+ },
1371
+ "171": {
1372
+ "content": "iu1",
1373
+ "lstrip": false,
1374
+ "normalized": true,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": false
1378
+ },
1379
+ "172": {
1380
+ "content": "iu2",
1381
+ "lstrip": false,
1382
+ "normalized": true,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": false
1386
+ },
1387
+ "173": {
1388
+ "content": "iu3",
1389
+ "lstrip": false,
1390
+ "normalized": true,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": false
1394
+ },
1395
+ "174": {
1396
+ "content": "iu4",
1397
+ "lstrip": false,
1398
+ "normalized": true,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": false
1402
+ },
1403
+ "175": {
1404
+ "content": "iu5",
1405
+ "lstrip": false,
1406
+ "normalized": true,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": false
1410
+ },
1411
+ "176": {
1412
+ "content": "iu6",
1413
+ "lstrip": false,
1414
+ "normalized": true,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": false
1418
+ },
1419
+ "177": {
1420
+ "content": "j",
1421
+ "lstrip": false,
1422
+ "normalized": true,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": false
1426
+ },
1427
+ "178": {
1428
+ "content": "k",
1429
+ "lstrip": false,
1430
+ "normalized": true,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": false
1434
+ },
1435
+ "179": {
1436
+ "content": "kw",
1437
+ "lstrip": false,
1438
+ "normalized": true,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": false
1442
+ },
1443
+ "180": {
1444
+ "content": "l",
1445
+ "lstrip": false,
1446
+ "normalized": true,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": false
1450
+ },
1451
+ "181": {
1452
+ "content": "m",
1453
+ "lstrip": false,
1454
+ "normalized": true,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": false
1458
+ },
1459
+ "182": {
1460
+ "content": "m2",
1461
+ "lstrip": false,
1462
+ "normalized": true,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": false
1466
+ },
1467
+ "183": {
1468
+ "content": "m4",
1469
+ "lstrip": false,
1470
+ "normalized": true,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": false
1474
+ },
1475
+ "184": {
1476
+ "content": "m6",
1477
+ "lstrip": false,
1478
+ "normalized": true,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": false
1482
+ },
1483
+ "185": {
1484
+ "content": "n",
1485
+ "lstrip": false,
1486
+ "normalized": true,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": false
1490
+ },
1491
+ "186": {
1492
+ "content": "ng",
1493
+ "lstrip": false,
1494
+ "normalized": true,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": false
1498
+ },
1499
+ "187": {
1500
+ "content": "ng4",
1501
+ "lstrip": false,
1502
+ "normalized": true,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": false
1506
+ },
1507
+ "188": {
1508
+ "content": "ng5",
1509
+ "lstrip": false,
1510
+ "normalized": true,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": false
1514
+ },
1515
+ "189": {
1516
+ "content": "ng6",
1517
+ "lstrip": false,
1518
+ "normalized": true,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": false
1522
+ },
1523
+ "190": {
1524
+ "content": "o1",
1525
+ "lstrip": false,
1526
+ "normalized": true,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": false
1530
+ },
1531
+ "191": {
1532
+ "content": "o2",
1533
+ "lstrip": false,
1534
+ "normalized": true,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": false
1538
+ },
1539
+ "192": {
1540
+ "content": "o3",
1541
+ "lstrip": false,
1542
+ "normalized": true,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": false
1546
+ },
1547
+ "193": {
1548
+ "content": "o4",
1549
+ "lstrip": false,
1550
+ "normalized": true,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": false
1554
+ },
1555
+ "194": {
1556
+ "content": "o5",
1557
+ "lstrip": false,
1558
+ "normalized": true,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": false
1562
+ },
1563
+ "195": {
1564
+ "content": "o6",
1565
+ "lstrip": false,
1566
+ "normalized": true,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": false
1570
+ },
1571
+ "196": {
1572
+ "content": "oe1",
1573
+ "lstrip": false,
1574
+ "normalized": true,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": false
1578
+ },
1579
+ "197": {
1580
+ "content": "oe2",
1581
+ "lstrip": false,
1582
+ "normalized": true,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": false
1586
+ },
1587
+ "198": {
1588
+ "content": "oe3",
1589
+ "lstrip": false,
1590
+ "normalized": true,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": false
1594
+ },
1595
+ "199": {
1596
+ "content": "oe4",
1597
+ "lstrip": false,
1598
+ "normalized": true,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": false
1602
+ },
1603
+ "200": {
1604
+ "content": "oek2",
1605
+ "lstrip": false,
1606
+ "normalized": true,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": false
1610
+ },
1611
+ "201": {
1612
+ "content": "oek3",
1613
+ "lstrip": false,
1614
+ "normalized": true,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": false
1618
+ },
1619
+ "202": {
1620
+ "content": "oek6",
1621
+ "lstrip": false,
1622
+ "normalized": true,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": false
1626
+ },
1627
+ "203": {
1628
+ "content": "oeng1",
1629
+ "lstrip": false,
1630
+ "normalized": true,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": false
1634
+ },
1635
+ "204": {
1636
+ "content": "oeng2",
1637
+ "lstrip": false,
1638
+ "normalized": true,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": false
1642
+ },
1643
+ "205": {
1644
+ "content": "oeng3",
1645
+ "lstrip": false,
1646
+ "normalized": true,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": false
1650
+ },
1651
+ "206": {
1652
+ "content": "oeng4",
1653
+ "lstrip": false,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": false
1658
+ },
1659
+ "207": {
1660
+ "content": "oeng5",
1661
+ "lstrip": false,
1662
+ "normalized": true,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": false
1666
+ },
1667
+ "208": {
1668
+ "content": "oeng6",
1669
+ "lstrip": false,
1670
+ "normalized": true,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": false
1674
+ },
1675
+ "209": {
1676
+ "content": "oi1",
1677
+ "lstrip": false,
1678
+ "normalized": true,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": false
1682
+ },
1683
+ "210": {
1684
+ "content": "oi2",
1685
+ "lstrip": false,
1686
+ "normalized": true,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": false
1690
+ },
1691
+ "211": {
1692
+ "content": "oi3",
1693
+ "lstrip": false,
1694
+ "normalized": true,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": false
1698
+ },
1699
+ "212": {
1700
+ "content": "oi4",
1701
+ "lstrip": false,
1702
+ "normalized": true,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": false
1706
+ },
1707
+ "213": {
1708
+ "content": "oi6",
1709
+ "lstrip": false,
1710
+ "normalized": true,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": false
1714
+ },
1715
+ "214": {
1716
+ "content": "ok1",
1717
+ "lstrip": false,
1718
+ "normalized": true,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": false
1722
+ },
1723
+ "215": {
1724
+ "content": "ok2",
1725
+ "lstrip": false,
1726
+ "normalized": true,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": false
1730
+ },
1731
+ "216": {
1732
+ "content": "ok3",
1733
+ "lstrip": false,
1734
+ "normalized": true,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": false
1738
+ },
1739
+ "217": {
1740
+ "content": "ok6",
1741
+ "lstrip": false,
1742
+ "normalized": true,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": false
1746
+ },
1747
+ "218": {
1748
+ "content": "on1",
1749
+ "lstrip": false,
1750
+ "normalized": true,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": false
1754
+ },
1755
+ "219": {
1756
+ "content": "on2",
1757
+ "lstrip": false,
1758
+ "normalized": true,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": false
1762
+ },
1763
+ "220": {
1764
+ "content": "on3",
1765
+ "lstrip": false,
1766
+ "normalized": true,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": false
1770
+ },
1771
+ "221": {
1772
+ "content": "on4",
1773
+ "lstrip": false,
1774
+ "normalized": true,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": false
1778
+ },
1779
+ "222": {
1780
+ "content": "on5",
1781
+ "lstrip": false,
1782
+ "normalized": true,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": false
1786
+ },
1787
+ "223": {
1788
+ "content": "on6",
1789
+ "lstrip": false,
1790
+ "normalized": true,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": false
1794
+ },
1795
+ "224": {
1796
+ "content": "ong1",
1797
+ "lstrip": false,
1798
+ "normalized": true,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": false
1802
+ },
1803
+ "225": {
1804
+ "content": "ong2",
1805
+ "lstrip": false,
1806
+ "normalized": true,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": false
1810
+ },
1811
+ "226": {
1812
+ "content": "ong3",
1813
+ "lstrip": false,
1814
+ "normalized": true,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": false
1818
+ },
1819
+ "227": {
1820
+ "content": "ong4",
1821
+ "lstrip": false,
1822
+ "normalized": true,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": false
1826
+ },
1827
+ "228": {
1828
+ "content": "ong5",
1829
+ "lstrip": false,
1830
+ "normalized": true,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": false
1834
+ },
1835
+ "229": {
1836
+ "content": "ong6",
1837
+ "lstrip": false,
1838
+ "normalized": true,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": false
1842
+ },
1843
+ "230": {
1844
+ "content": "ot3",
1845
+ "lstrip": false,
1846
+ "normalized": true,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": false
1850
+ },
1851
+ "231": {
1852
+ "content": "ou1",
1853
+ "lstrip": false,
1854
+ "normalized": true,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": false
1858
+ },
1859
+ "232": {
1860
+ "content": "ou2",
1861
+ "lstrip": false,
1862
+ "normalized": true,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": false
1866
+ },
1867
+ "233": {
1868
+ "content": "ou3",
1869
+ "lstrip": false,
1870
+ "normalized": true,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": false
1874
+ },
1875
+ "234": {
1876
+ "content": "ou4",
1877
+ "lstrip": false,
1878
+ "normalized": true,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": false
1882
+ },
1883
+ "235": {
1884
+ "content": "ou5",
1885
+ "lstrip": false,
1886
+ "normalized": true,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": false
1890
+ },
1891
+ "236": {
1892
+ "content": "ou6",
1893
+ "lstrip": false,
1894
+ "normalized": true,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": false
1898
+ },
1899
+ "237": {
1900
+ "content": "p",
1901
+ "lstrip": false,
1902
+ "normalized": true,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": false
1906
+ },
1907
+ "238": {
1908
+ "content": "s",
1909
+ "lstrip": false,
1910
+ "normalized": true,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": false
1914
+ },
1915
+ "239": {
1916
+ "content": "t",
1917
+ "lstrip": false,
1918
+ "normalized": true,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": false
1922
+ },
1923
+ "240": {
1924
+ "content": "u1",
1925
+ "lstrip": false,
1926
+ "normalized": true,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": false
1930
+ },
1931
+ "241": {
1932
+ "content": "u2",
1933
+ "lstrip": false,
1934
+ "normalized": true,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": false
1938
+ },
1939
+ "242": {
1940
+ "content": "u3",
1941
+ "lstrip": false,
1942
+ "normalized": true,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": false
1946
+ },
1947
+ "243": {
1948
+ "content": "u4",
1949
+ "lstrip": false,
1950
+ "normalized": true,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": false
1954
+ },
1955
+ "244": {
1956
+ "content": "u5",
1957
+ "lstrip": false,
1958
+ "normalized": true,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": false
1962
+ },
1963
+ "245": {
1964
+ "content": "u6",
1965
+ "lstrip": false,
1966
+ "normalized": true,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": false
1970
+ },
1971
+ "246": {
1972
+ "content": "ui1",
1973
+ "lstrip": false,
1974
+ "normalized": true,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": false
1978
+ },
1979
+ "247": {
1980
+ "content": "ui2",
1981
+ "lstrip": false,
1982
+ "normalized": true,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": false
1986
+ },
1987
+ "248": {
1988
+ "content": "ui3",
1989
+ "lstrip": false,
1990
+ "normalized": true,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": false
1994
+ },
1995
+ "249": {
1996
+ "content": "ui4",
1997
+ "lstrip": false,
1998
+ "normalized": true,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": false
2002
+ },
2003
+ "250": {
2004
+ "content": "ui5",
2005
+ "lstrip": false,
2006
+ "normalized": true,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": false
2010
+ },
2011
+ "251": {
2012
+ "content": "ui6",
2013
+ "lstrip": false,
2014
+ "normalized": true,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": false
2018
+ },
2019
+ "252": {
2020
+ "content": "uk1",
2021
+ "lstrip": false,
2022
+ "normalized": true,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": false
2026
+ },
2027
+ "253": {
2028
+ "content": "uk2",
2029
+ "lstrip": false,
2030
+ "normalized": true,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": false
2034
+ },
2035
+ "254": {
2036
+ "content": "uk4",
2037
+ "lstrip": false,
2038
+ "normalized": true,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": false
2042
+ },
2043
+ "255": {
2044
+ "content": "uk6",
2045
+ "lstrip": false,
2046
+ "normalized": true,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": false
2050
+ },
2051
+ "256": {
2052
+ "content": "un1",
2053
+ "lstrip": false,
2054
+ "normalized": true,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": false
2058
+ },
2059
+ "257": {
2060
+ "content": "un2",
2061
+ "lstrip": false,
2062
+ "normalized": true,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ },
2067
+ "258": {
2068
+ "content": "un3",
2069
+ "lstrip": false,
2070
+ "normalized": true,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": false
2074
+ },
2075
+ "259": {
2076
+ "content": "un4",
2077
+ "lstrip": false,
2078
+ "normalized": true,
2079
+ "rstrip": false,
2080
+ "single_word": false,
2081
+ "special": false
2082
+ },
2083
+ "260": {
2084
+ "content": "un5",
2085
+ "lstrip": false,
2086
+ "normalized": true,
2087
+ "rstrip": false,
2088
+ "single_word": false,
2089
+ "special": false
2090
+ },
2091
+ "261": {
2092
+ "content": "un6",
2093
+ "lstrip": false,
2094
+ "normalized": true,
2095
+ "rstrip": false,
2096
+ "single_word": false,
2097
+ "special": false
2098
+ },
2099
+ "262": {
2100
+ "content": "ung1",
2101
+ "lstrip": false,
2102
+ "normalized": true,
2103
+ "rstrip": false,
2104
+ "single_word": false,
2105
+ "special": false
2106
+ },
2107
+ "263": {
2108
+ "content": "ung2",
2109
+ "lstrip": false,
2110
+ "normalized": true,
2111
+ "rstrip": false,
2112
+ "single_word": false,
2113
+ "special": false
2114
+ },
2115
+ "264": {
2116
+ "content": "ung3",
2117
+ "lstrip": false,
2118
+ "normalized": true,
2119
+ "rstrip": false,
2120
+ "single_word": false,
2121
+ "special": false
2122
+ },
2123
+ "265": {
2124
+ "content": "ung4",
2125
+ "lstrip": false,
2126
+ "normalized": true,
2127
+ "rstrip": false,
2128
+ "single_word": false,
2129
+ "special": false
2130
+ },
2131
+ "266": {
2132
+ "content": "ung5",
2133
+ "lstrip": false,
2134
+ "normalized": true,
2135
+ "rstrip": false,
2136
+ "single_word": false,
2137
+ "special": false
2138
+ },
2139
+ "267": {
2140
+ "content": "ung6",
2141
+ "lstrip": false,
2142
+ "normalized": true,
2143
+ "rstrip": false,
2144
+ "single_word": false,
2145
+ "special": false
2146
+ },
2147
+ "268": {
2148
+ "content": "ut1",
2149
+ "lstrip": false,
2150
+ "normalized": true,
2151
+ "rstrip": false,
2152
+ "single_word": false,
2153
+ "special": false
2154
+ },
2155
+ "269": {
2156
+ "content": "ut3",
2157
+ "lstrip": false,
2158
+ "normalized": true,
2159
+ "rstrip": false,
2160
+ "single_word": false,
2161
+ "special": false
2162
+ },
2163
+ "270": {
2164
+ "content": "ut6",
2165
+ "lstrip": false,
2166
+ "normalized": true,
2167
+ "rstrip": false,
2168
+ "single_word": false,
2169
+ "special": false
2170
+ },
2171
+ "271": {
2172
+ "content": "w",
2173
+ "lstrip": false,
2174
+ "normalized": true,
2175
+ "rstrip": false,
2176
+ "single_word": false,
2177
+ "special": false
2178
+ },
2179
+ "272": {
2180
+ "content": "yu1",
2181
+ "lstrip": false,
2182
+ "normalized": true,
2183
+ "rstrip": false,
2184
+ "single_word": false,
2185
+ "special": false
2186
+ },
2187
+ "273": {
2188
+ "content": "yu2",
2189
+ "lstrip": false,
2190
+ "normalized": true,
2191
+ "rstrip": false,
2192
+ "single_word": false,
2193
+ "special": false
2194
+ },
2195
+ "274": {
2196
+ "content": "yu3",
2197
+ "lstrip": false,
2198
+ "normalized": true,
2199
+ "rstrip": false,
2200
+ "single_word": false,
2201
+ "special": false
2202
+ },
2203
+ "275": {
2204
+ "content": "yu4",
2205
+ "lstrip": false,
2206
+ "normalized": true,
2207
+ "rstrip": false,
2208
+ "single_word": false,
2209
+ "special": false
2210
+ },
2211
+ "276": {
2212
+ "content": "yu5",
2213
+ "lstrip": false,
2214
+ "normalized": true,
2215
+ "rstrip": false,
2216
+ "single_word": false,
2217
+ "special": false
2218
+ },
2219
+ "277": {
2220
+ "content": "yu6",
2221
+ "lstrip": false,
2222
+ "normalized": true,
2223
+ "rstrip": false,
2224
+ "single_word": false,
2225
+ "special": false
2226
+ },
2227
+ "278": {
2228
+ "content": "yun1",
2229
+ "lstrip": false,
2230
+ "normalized": true,
2231
+ "rstrip": false,
2232
+ "single_word": false,
2233
+ "special": false
2234
+ },
2235
+ "279": {
2236
+ "content": "yun2",
2237
+ "lstrip": false,
2238
+ "normalized": true,
2239
+ "rstrip": false,
2240
+ "single_word": false,
2241
+ "special": false
2242
+ },
2243
+ "280": {
2244
+ "content": "yun3",
2245
+ "lstrip": false,
2246
+ "normalized": true,
2247
+ "rstrip": false,
2248
+ "single_word": false,
2249
+ "special": false
2250
+ },
2251
+ "281": {
2252
+ "content": "yun4",
2253
+ "lstrip": false,
2254
+ "normalized": true,
2255
+ "rstrip": false,
2256
+ "single_word": false,
2257
+ "special": false
2258
+ },
2259
+ "282": {
2260
+ "content": "yun5",
2261
+ "lstrip": false,
2262
+ "normalized": true,
2263
+ "rstrip": false,
2264
+ "single_word": false,
2265
+ "special": false
2266
+ },
2267
+ "283": {
2268
+ "content": "yun6",
2269
+ "lstrip": false,
2270
+ "normalized": true,
2271
+ "rstrip": false,
2272
+ "single_word": false,
2273
+ "special": false
2274
+ },
2275
+ "284": {
2276
+ "content": "yut1",
2277
+ "lstrip": false,
2278
+ "normalized": true,
2279
+ "rstrip": false,
2280
+ "single_word": false,
2281
+ "special": false
2282
+ },
2283
+ "285": {
2284
+ "content": "yut2",
2285
+ "lstrip": false,
2286
+ "normalized": true,
2287
+ "rstrip": false,
2288
+ "single_word": false,
2289
+ "special": false
2290
+ },
2291
+ "286": {
2292
+ "content": "yut3",
2293
+ "lstrip": false,
2294
+ "normalized": true,
2295
+ "rstrip": false,
2296
+ "single_word": false,
2297
+ "special": false
2298
+ },
2299
+ "287": {
2300
+ "content": "yut4",
2301
+ "lstrip": false,
2302
+ "normalized": true,
2303
+ "rstrip": false,
2304
+ "single_word": false,
2305
+ "special": false
2306
+ },
2307
+ "288": {
2308
+ "content": "yut6",
2309
+ "lstrip": false,
2310
+ "normalized": true,
2311
+ "rstrip": false,
2312
+ "single_word": false,
2313
+ "special": false
2314
+ },
2315
+ "289": {
2316
+ "content": "z",
2317
+ "lstrip": false,
2318
+ "normalized": true,
2319
+ "rstrip": false,
2320
+ "single_word": false,
2321
+ "special": false
2322
+ },
2323
+ "290": {
2324
+ "content": "<s>",
2325
+ "lstrip": false,
2326
+ "normalized": false,
2327
+ "rstrip": false,
2328
+ "single_word": false,
2329
+ "special": true
2330
+ },
2331
+ "291": {
2332
  "content": "</s>",
2333
  "lstrip": false,
2334
  "normalized": false,
vocab.json CHANGED
@@ -1,83 +1,292 @@
1
  {
2
- "1": 3,
3
- "2": 4,
4
- "3": 5,
5
- "4": 6,
6
- "5": 7,
7
- "6": 8,
8
- "M": 9,
9
- "Ng": 10,
10
  "[PAD]": 0,
11
  "[UNK]": 1,
12
- "aa": 11,
13
- "aai": 12,
14
- "aak": 13,
15
- "aam": 14,
16
- "aan": 15,
17
- "aang": 16,
18
- "aap": 17,
19
- "aat": 18,
20
- "aau": 19,
21
- "ai": 20,
22
- "ak": 21,
23
- "am": 22,
24
- "an": 23,
25
- "ang": 24,
26
- "ap": 25,
27
- "at": 26,
28
- "au": 27,
29
- "b": 28,
30
- "c": 29,
31
- "d": 30,
32
- "e": 31,
33
- "ei": 32,
34
- "ek": 33,
35
- "eng": 34,
36
- "eoi": 35,
37
- "eon": 36,
38
- "eot": 37,
39
- "f": 38,
40
- "g": 39,
41
- "gw": 40,
42
- "h": 41,
43
- "i": 42,
44
- "ik": 43,
45
- "im": 44,
46
- "in": 45,
47
- "ing": 46,
48
- "ip": 47,
49
- "it": 48,
50
- "iu": 49,
51
- "j": 50,
52
- "k": 51,
53
- "kw": 52,
54
- "l": 53,
55
- "m": 54,
56
- "n": 55,
57
- "ng": 56,
58
- "o": 57,
59
- "oe": 58,
60
- "oek": 59,
61
- "oeng": 60,
62
- "oi": 61,
63
- "ok": 62,
64
- "on": 63,
65
- "ong": 64,
66
- "ot": 65,
67
- "ou": 66,
68
- "p": 67,
69
- "s": 68,
70
- "t": 69,
71
- "u": 70,
72
- "ui": 71,
73
- "uk": 72,
74
- "un": 73,
75
- "ung": 74,
76
- "ut": 75,
77
- "w": 76,
78
- "yu": 77,
79
- "yun": 78,
80
- "yut": 79,
81
- "z": 80,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  "|": 2
83
  }
 
1
  {
 
 
 
 
 
 
 
 
2
  "[PAD]": 0,
3
  "[UNK]": 1,
4
+ "aa1": 3,
5
+ "aa2": 4,
6
+ "aa3": 5,
7
+ "aa4": 6,
8
+ "aa5": 7,
9
+ "aa6": 8,
10
+ "aai1": 9,
11
+ "aai2": 10,
12
+ "aai3": 11,
13
+ "aai4": 12,
14
+ "aai5": 13,
15
+ "aai6": 14,
16
+ "aak1": 15,
17
+ "aak2": 16,
18
+ "aak3": 17,
19
+ "aak6": 18,
20
+ "aam1": 19,
21
+ "aam2": 20,
22
+ "aam3": 21,
23
+ "aam4": 22,
24
+ "aam5": 23,
25
+ "aam6": 24,
26
+ "aan1": 25,
27
+ "aan2": 26,
28
+ "aan3": 27,
29
+ "aan4": 28,
30
+ "aan5": 29,
31
+ "aan6": 30,
32
+ "aang1": 31,
33
+ "aang2": 32,
34
+ "aang3": 33,
35
+ "aang4": 34,
36
+ "aang5": 35,
37
+ "aang6": 36,
38
+ "aap1": 37,
39
+ "aap2": 38,
40
+ "aap3": 39,
41
+ "aap6": 40,
42
+ "aat1": 41,
43
+ "aat2": 42,
44
+ "aat3": 43,
45
+ "aat6": 44,
46
+ "aau1": 45,
47
+ "aau2": 46,
48
+ "aau3": 47,
49
+ "aau4": 48,
50
+ "aau5": 49,
51
+ "aau6": 50,
52
+ "ai1": 51,
53
+ "ai2": 52,
54
+ "ai3": 53,
55
+ "ai4": 54,
56
+ "ai5": 55,
57
+ "ai6": 56,
58
+ "ak1": 57,
59
+ "ak2": 58,
60
+ "ak6": 59,
61
+ "am1": 60,
62
+ "am2": 61,
63
+ "am3": 62,
64
+ "am4": 63,
65
+ "am5": 64,
66
+ "am6": 65,
67
+ "an1": 66,
68
+ "an2": 67,
69
+ "an3": 68,
70
+ "an4": 69,
71
+ "an5": 70,
72
+ "an6": 71,
73
+ "ang1": 72,
74
+ "ang2": 73,
75
+ "ang3": 74,
76
+ "ang4": 75,
77
+ "ang6": 76,
78
+ "ap1": 77,
79
+ "ap2": 78,
80
+ "ap6": 79,
81
+ "at1": 80,
82
+ "at2": 81,
83
+ "at3": 82,
84
+ "at6": 83,
85
+ "au1": 84,
86
+ "au2": 85,
87
+ "au3": 86,
88
+ "au4": 87,
89
+ "au5": 88,
90
+ "au6": 89,
91
+ "b": 90,
92
+ "c": 91,
93
+ "d": 92,
94
+ "e1": 93,
95
+ "e2": 94,
96
+ "e3": 95,
97
+ "e4": 96,
98
+ "e5": 97,
99
+ "e6": 98,
100
+ "ei1": 99,
101
+ "ei2": 100,
102
+ "ei3": 101,
103
+ "ei4": 102,
104
+ "ei5": 103,
105
+ "ei6": 104,
106
+ "ek1": 105,
107
+ "ek2": 106,
108
+ "ek3": 107,
109
+ "ek6": 108,
110
+ "eng1": 109,
111
+ "eng2": 110,
112
+ "eng3": 111,
113
+ "eng4": 112,
114
+ "eng5": 113,
115
+ "eng6": 114,
116
+ "eoi1": 115,
117
+ "eoi2": 116,
118
+ "eoi3": 117,
119
+ "eoi4": 118,
120
+ "eoi5": 119,
121
+ "eoi6": 120,
122
+ "eon1": 121,
123
+ "eon2": 122,
124
+ "eon3": 123,
125
+ "eon4": 124,
126
+ "eon5": 125,
127
+ "eon6": 126,
128
+ "eot1": 127,
129
+ "eot2": 128,
130
+ "eot6": 129,
131
+ "ep6": 130,
132
+ "eu6": 131,
133
+ "f": 132,
134
+ "g": 133,
135
+ "gw": 134,
136
+ "h": 135,
137
+ "i1": 136,
138
+ "i2": 137,
139
+ "i3": 138,
140
+ "i4": 139,
141
+ "i5": 140,
142
+ "i6": 141,
143
+ "ik1": 142,
144
+ "ik3": 143,
145
+ "ik4": 144,
146
+ "ik6": 145,
147
+ "im1": 146,
148
+ "im2": 147,
149
+ "im3": 148,
150
+ "im4": 149,
151
+ "im5": 150,
152
+ "im6": 151,
153
+ "in1": 152,
154
+ "in2": 153,
155
+ "in3": 154,
156
+ "in4": 155,
157
+ "in5": 156,
158
+ "in6": 157,
159
+ "ing1": 158,
160
+ "ing2": 159,
161
+ "ing3": 160,
162
+ "ing4": 161,
163
+ "ing5": 162,
164
+ "ing6": 163,
165
+ "ip1": 164,
166
+ "ip2": 165,
167
+ "ip3": 166,
168
+ "ip6": 167,
169
+ "it1": 168,
170
+ "it3": 169,
171
+ "it6": 170,
172
+ "iu1": 171,
173
+ "iu2": 172,
174
+ "iu3": 173,
175
+ "iu4": 174,
176
+ "iu5": 175,
177
+ "iu6": 176,
178
+ "j": 177,
179
+ "k": 178,
180
+ "kw": 179,
181
+ "l": 180,
182
+ "m": 181,
183
+ "m2": 182,
184
+ "m4": 183,
185
+ "m6": 184,
186
+ "n": 185,
187
+ "ng": 186,
188
+ "ng4": 187,
189
+ "ng5": 188,
190
+ "ng6": 189,
191
+ "o1": 190,
192
+ "o2": 191,
193
+ "o3": 192,
194
+ "o4": 193,
195
+ "o5": 194,
196
+ "o6": 195,
197
+ "oe1": 196,
198
+ "oe2": 197,
199
+ "oe3": 198,
200
+ "oe4": 199,
201
+ "oek2": 200,
202
+ "oek3": 201,
203
+ "oek6": 202,
204
+ "oeng1": 203,
205
+ "oeng2": 204,
206
+ "oeng3": 205,
207
+ "oeng4": 206,
208
+ "oeng5": 207,
209
+ "oeng6": 208,
210
+ "oi1": 209,
211
+ "oi2": 210,
212
+ "oi3": 211,
213
+ "oi4": 212,
214
+ "oi6": 213,
215
+ "ok1": 214,
216
+ "ok2": 215,
217
+ "ok3": 216,
218
+ "ok6": 217,
219
+ "on1": 218,
220
+ "on2": 219,
221
+ "on3": 220,
222
+ "on4": 221,
223
+ "on5": 222,
224
+ "on6": 223,
225
+ "ong1": 224,
226
+ "ong2": 225,
227
+ "ong3": 226,
228
+ "ong4": 227,
229
+ "ong5": 228,
230
+ "ong6": 229,
231
+ "ot3": 230,
232
+ "ou1": 231,
233
+ "ou2": 232,
234
+ "ou3": 233,
235
+ "ou4": 234,
236
+ "ou5": 235,
237
+ "ou6": 236,
238
+ "p": 237,
239
+ "s": 238,
240
+ "t": 239,
241
+ "u1": 240,
242
+ "u2": 241,
243
+ "u3": 242,
244
+ "u4": 243,
245
+ "u5": 244,
246
+ "u6": 245,
247
+ "ui1": 246,
248
+ "ui2": 247,
249
+ "ui3": 248,
250
+ "ui4": 249,
251
+ "ui5": 250,
252
+ "ui6": 251,
253
+ "uk1": 252,
254
+ "uk2": 253,
255
+ "uk4": 254,
256
+ "uk6": 255,
257
+ "un1": 256,
258
+ "un2": 257,
259
+ "un3": 258,
260
+ "un4": 259,
261
+ "un5": 260,
262
+ "un6": 261,
263
+ "ung1": 262,
264
+ "ung2": 263,
265
+ "ung3": 264,
266
+ "ung4": 265,
267
+ "ung5": 266,
268
+ "ung6": 267,
269
+ "ut1": 268,
270
+ "ut3": 269,
271
+ "ut6": 270,
272
+ "w": 271,
273
+ "yu1": 272,
274
+ "yu2": 273,
275
+ "yu3": 274,
276
+ "yu4": 275,
277
+ "yu5": 276,
278
+ "yu6": 277,
279
+ "yun1": 278,
280
+ "yun2": 279,
281
+ "yun3": 280,
282
+ "yun4": 281,
283
+ "yun5": 282,
284
+ "yun6": 283,
285
+ "yut1": 284,
286
+ "yut2": 285,
287
+ "yut3": 286,
288
+ "yut4": 287,
289
+ "yut6": 288,
290
+ "z": 289,
291
  "|": 2
292
  }