jz703 commited on
Commit
f1f7ac9
1 Parent(s): f769ff2

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +84 -0
  2. tokenizer_config.json +659 -0
  3. vocab.json +116 -116
added_tokens.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 117,
3
+ "<s>": 116,
4
+ "[PAD]": 119,
5
+ "[UNK]": 118,
6
+ "aɪ": 15,
7
+ "aɪə": 4,
8
+ "aɪɚ": 79,
9
+ "aʊ": 75,
10
+ "dʒ": 25,
11
+ "eɪ": 113,
12
+ "iə": 72,
13
+ "iː": 36,
14
+ "n̩": 2,
15
+ "oʊ": 106,
16
+ "oː": 81,
17
+ "oːɹ": 57,
18
+ "tʃ": 84,
19
+ "uː": 82,
20
+ "ɑː": 114,
21
+ "ɑːɹ": 69,
22
+ "ɔɪ": 48,
23
+ "ɔː": 47,
24
+ "ɔːɹ": 71,
25
+ "əl": 80,
26
+ "ɛɹ": 107,
27
+ "ɜː": 95,
28
+ "ɪɹ": 65,
29
+ "ʊɹ": 54,
30
+ "ˈaɪ": 14,
31
+ "ˈaɪə": 99,
32
+ "ˈaɪɚ": 12,
33
+ "ˈaʊ": 38,
34
+ "ˈeɪ": 52,
35
+ "ˈiə": 53,
36
+ "ˈiː": 63,
37
+ "ˈoʊ": 11,
38
+ "ˈoː": 66,
39
+ "ˈoːɹ": 24,
40
+ "ˈuː": 115,
41
+ "ˈæ": 21,
42
+ "ˈɑː": 98,
43
+ "ˈɑːɹ": 74,
44
+ "ˈɔ": 56,
45
+ "ˈɔɪ": 91,
46
+ "ˈɔː": 108,
47
+ "ˈɔːɹ": 105,
48
+ "ˈɚ": 90,
49
+ "ˈɛ": 31,
50
+ "ˈɛɹ": 22,
51
+ "ˈɜː": 89,
52
+ "ˈɪ": 45,
53
+ "ˈɪɹ": 3,
54
+ "ˈʊ": 102,
55
+ "ˈʊɹ": 49,
56
+ "ˈʌ": 23,
57
+ "ˌaɪ": 33,
58
+ "ˌaɪɚ": 94,
59
+ "ˌaʊ": 111,
60
+ "ˌeɪ": 8,
61
+ "ˌiə": 19,
62
+ "ˌiː": 13,
63
+ "ˌn̩": 35,
64
+ "ˌoʊ": 58,
65
+ "ˌoː": 40,
66
+ "ˌoːɹ": 6,
67
+ "ˌuː": 39,
68
+ "ˌæ": 97,
69
+ "ˌɐ": 61,
70
+ "ˌɑː": 44,
71
+ "ˌɑːɹ": 93,
72
+ "ˌɔ": 18,
73
+ "ˌɔɪ": 10,
74
+ "ˌɔː": 70,
75
+ "ˌɔːɹ": 100,
76
+ "ˌɛ": 86,
77
+ "ˌɛɹ": 60,
78
+ "ˌɜː": 64,
79
+ "ˌɪ": 20,
80
+ "ˌɪɹ": 26,
81
+ "ˌʊ": 34,
82
+ "ˌʊɹ": 101,
83
+ "ˌʌ": 88
84
+ }
tokenizer_config.json CHANGED
@@ -1,4 +1,663 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "do_lower_case": false,
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "2": {
4
+ "content": "n̩",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "3": {
12
+ "content": "ˈɪɹ",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "4": {
20
+ "content": "aɪə",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "6": {
28
+ "content": "ˌoːɹ",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "8": {
36
+ "content": "ˌeɪ",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "10": {
44
+ "content": "ˌɔɪ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "11": {
52
+ "content": "ˈoʊ",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "12": {
60
+ "content": "ˈaɪɚ",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "13": {
68
+ "content": "ˌiː",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "14": {
76
+ "content": "ˈaɪ",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "15": {
84
+ "content": "aɪ",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "18": {
92
+ "content": "ˌɔ",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "19": {
100
+ "content": "ˌiə",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "20": {
108
+ "content": "ˌɪ",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "21": {
116
+ "content": "ˈæ",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "22": {
124
+ "content": "ˈɛɹ",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "23": {
132
+ "content": "ˈʌ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "24": {
140
+ "content": "ˈoːɹ",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "25": {
148
+ "content": "dʒ",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "26": {
156
+ "content": "ˌɪɹ",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "31": {
164
+ "content": "ˈɛ",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "33": {
172
+ "content": "ˌaɪ",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "34": {
180
+ "content": "ˌʊ",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "35": {
188
+ "content": "ˌn̩",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "36": {
196
+ "content": "iː",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "38": {
204
+ "content": "ˈaʊ",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "39": {
212
+ "content": "ˌuː",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "40": {
220
+ "content": "ˌoː",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "44": {
228
+ "content": "ˌɑː",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "45": {
236
+ "content": "ˈɪ",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "47": {
244
+ "content": "ɔː",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "48": {
252
+ "content": "ɔɪ",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "49": {
260
+ "content": "ˈʊɹ",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "52": {
268
+ "content": "ˈeɪ",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "53": {
276
+ "content": "ˈiə",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "54": {
284
+ "content": "ʊɹ",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "56": {
292
+ "content": "ˈɔ",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "57": {
300
+ "content": "oːɹ",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "58": {
308
+ "content": "ˌoʊ",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "60": {
316
+ "content": "ˌɛɹ",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "61": {
324
+ "content": "ˌɐ",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "63": {
332
+ "content": "ˈiː",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "64": {
340
+ "content": "ˌɜː",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "65": {
348
+ "content": "ɪɹ",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "66": {
356
+ "content": "ˈoː",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "69": {
364
+ "content": "ɑːɹ",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "70": {
372
+ "content": "ˌɔː",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "71": {
380
+ "content": "ɔːɹ",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "72": {
388
+ "content": "iə",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "74": {
396
+ "content": "ˈɑːɹ",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "75": {
404
+ "content": "aʊ",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "79": {
412
+ "content": "aɪɚ",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "80": {
420
+ "content": "əl",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "81": {
428
+ "content": "oː",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "82": {
436
+ "content": "uː",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "84": {
444
+ "content": "tʃ",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "86": {
452
+ "content": "ˌɛ",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "88": {
460
+ "content": "ˌʌ",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "89": {
468
+ "content": "ˈɜː",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "90": {
476
+ "content": "ˈɚ",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "91": {
484
+ "content": "ˈɔɪ",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "93": {
492
+ "content": "ˌɑːɹ",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "94": {
500
+ "content": "ˌaɪɚ",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "95": {
508
+ "content": "ɜː",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "97": {
516
+ "content": "ˌæ",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "98": {
524
+ "content": "ˈɑː",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "99": {
532
+ "content": "ˈaɪə",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "100": {
540
+ "content": "ˌɔːɹ",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "101": {
548
+ "content": "ˌʊɹ",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "102": {
556
+ "content": "ˈʊ",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "105": {
564
+ "content": "ˈɔːɹ",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "106": {
572
+ "content": "oʊ",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "107": {
580
+ "content": "ɛɹ",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "108": {
588
+ "content": "ˈɔː",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "111": {
596
+ "content": "ˌaʊ",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "113": {
604
+ "content": "eɪ",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "114": {
612
+ "content": "ɑː",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "115": {
620
+ "content": "ˈuː",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "116": {
628
+ "content": "<s>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "117": {
636
+ "content": "</s>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "118": {
644
+ "content": "[UNK]",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "119": {
652
+ "content": "[PAD]",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ }
659
+ },
660
+ "additional_special_tokens": [],
661
  "bos_token": "<s>",
662
  "clean_up_tokenization_spaces": true,
663
  "do_lower_case": false,
vocab.json CHANGED
@@ -1,118 +1,118 @@
1
  {
2
- "aɪ": 33,
3
- "aɪə": 55,
4
- "aɪɚ": 56,
5
- "aʊ": 36,
6
- "b": 27,
7
- "d": 104,
8
- "dʒ": 43,
9
- "eɪ": 54,
10
- "f": 64,
11
- "h": 82,
12
- "i": 114,
13
- "iə": 111,
14
- "iː": 66,
15
- "j": 63,
16
- "k": 9,
17
- "l": 75,
18
- "m": 93,
19
- "n": 69,
20
- "n̩": 61,
21
- "oʊ": 91,
22
- "oː": 14,
23
- "oːɹ": 72,
24
- "p": 59,
25
- "r": 68,
26
- "s": 73,
27
- "t": 13,
28
- "tʃ": 106,
29
- "uː": 99,
30
- "v": 102,
31
- "w": 105,
32
- "x": 110,
33
- "z": 53,
34
- "|": 0,
35
- "æ": 89,
36
- "ð": 17,
37
- "ŋ": 6,
38
- "ɐ": 38,
39
- "ɑː": 84,
40
- "ɑːɹ": 74,
41
- "ɔ": 51,
42
- "ɔɪ": 40,
43
- "ɔː": 58,
44
- "ɔːɹ": 77,
45
- "ə": 41,
46
- "əl": 52,
47
- "ɚ": 100,
48
- "ɛ": 81,
49
- "ɛɹ": 2,
50
- "ɜː": 26,
51
- "ɡ": 21,
52
- "ɪ": 57,
53
- "ɪɹ": 24,
54
- "ɹ": 92,
55
- "ɾ": 45,
56
- "ʃ": 5,
57
- "ʊ": 25,
58
- "ʊɹ": 94,
59
- "ʌ": 15,
60
- "ʒ": 101,
61
- "ʔ": 76,
62
- "ˈaɪ": 47,
63
- "ˈaɪə": 48,
64
- "ˈaɪɚ": 42,
65
- "ˈaʊ": 96,
66
- "ˈeɪ": 7,
67
- "ˈiə": 31,
68
- "ˈiː": 80,
69
- "ˈoʊ": 1,
70
- "ˈoː": 12,
71
- "ˈoːɹ": 109,
72
- "ˈuː": 108,
73
- "ˈæ": 95,
74
- "ˈɑː": 97,
75
- "ˈɑːɹ": 60,
76
- "ˈɔ": 20,
77
- "ˈɔɪ": 113,
78
- "ˈɔː": 83,
79
- "ˈɔːɹ": 30,
80
- "ˈɚ": 8,
81
- "ˈɛ": 86,
82
- "ˈɛɹ": 16,
83
- "ˈɜː": 11,
84
- "ˈɪ": 18,
85
- "ˈɪɹ": 67,
86
- "ˈʊ": 78,
87
- "ˈʊɹ": 112,
88
- "ˈʌ": 103,
89
- "ˌaɪ": 35,
90
- "ˌaɪɚ": 37,
91
- "ˌaʊ": 79,
92
- "ˌeɪ": 19,
93
- "ˌiə": 107,
94
- "ˌiː": 115,
95
- "ˌn̩": 23,
96
- "ˌoʊ": 71,
97
- "ˌoː": 65,
98
- "ˌoːɹ": 32,
99
- "ˌuː": 88,
100
- "ˌæ": 29,
101
- "ˌɐ": 44,
102
- "ˌɑː": 10,
103
- "ˌɑːɹ": 50,
104
- "ˌɔ": 3,
105
- "ˌɔɪ": 90,
106
- "ˌɔː": 4,
107
- "ˌɔːɹ": 98,
108
- "ˌɛ": 87,
109
- "ˌɛɹ": 34,
110
- "ˌɜː": 22,
111
- "ˌɪ": 46,
112
- "ˌɪɹ": 28,
113
- "ˌʊ": 85,
114
- "ˌʊɹ": 62,
115
- "ˌʌ": 49,
116
- "θ": 39,
117
- "ᵻ": 70
118
  }
 
1
  {
2
+ "aɪ": 15,
3
+ "aɪə": 4,
4
+ "aɪɚ": 79,
5
+ "aʊ": 75,
6
+ "b": 32,
7
+ "d": 5,
8
+ "dʒ": 25,
9
+ "eɪ": 113,
10
+ "f": 46,
11
+ "h": 68,
12
+ "i": 73,
13
+ "iə": 72,
14
+ "iː": 36,
15
+ "j": 28,
16
+ "k": 78,
17
+ "l": 37,
18
+ "m": 7,
19
+ "n": 103,
20
+ "n̩": 2,
21
+ "oʊ": 106,
22
+ "oː": 81,
23
+ "oːɹ": 57,
24
+ "p": 50,
25
+ "r": 76,
26
+ "s": 29,
27
+ "t": 110,
28
+ "tʃ": 84,
29
+ "uː": 82,
30
+ "v": 30,
31
+ "w": 9,
32
+ "x": 16,
33
+ "z": 0,
34
+ "|": 1,
35
+ "æ": 104,
36
+ "ð": 92,
37
+ "ŋ": 62,
38
+ "ɐ": 17,
39
+ "ɑː": 114,
40
+ "ɑːɹ": 69,
41
+ "ɔ": 109,
42
+ "ɔɪ": 48,
43
+ "ɔː": 47,
44
+ "ɔːɹ": 71,
45
+ "ə": 112,
46
+ "əl": 80,
47
+ "ɚ": 41,
48
+ "ɛ": 67,
49
+ "ɛɹ": 107,
50
+ "ɜː": 95,
51
+ "ɡ": 43,
52
+ "ɪ": 59,
53
+ "ɪɹ": 65,
54
+ "ɹ": 87,
55
+ "ɾ": 83,
56
+ "ʃ": 42,
57
+ "ʊ": 55,
58
+ "ʊɹ": 54,
59
+ "ʌ": 27,
60
+ "ʒ": 96,
61
+ "ʔ": 77,
62
+ "ˈaɪ": 14,
63
+ "ˈaɪə": 99,
64
+ "ˈaɪɚ": 12,
65
+ "ˈaʊ": 38,
66
+ "ˈeɪ": 52,
67
+ "ˈiə": 53,
68
+ "ˈiː": 63,
69
+ "ˈoʊ": 11,
70
+ "ˈoː": 66,
71
+ "ˈoːɹ": 24,
72
+ "ˈuː": 115,
73
+ "ˈæ": 21,
74
+ "ˈɑː": 98,
75
+ "ˈɑːɹ": 74,
76
+ "ˈɔ": 56,
77
+ "ˈɔɪ": 91,
78
+ "ˈɔː": 108,
79
+ "ˈɔːɹ": 105,
80
+ "ˈɚ": 90,
81
+ "ˈɛ": 31,
82
+ "ˈɛɹ": 22,
83
+ "ˈɜː": 89,
84
+ "ˈɪ": 45,
85
+ "ˈɪɹ": 3,
86
+ "ˈʊ": 102,
87
+ "ˈʊɹ": 49,
88
+ "ˈʌ": 23,
89
+ "ˌaɪ": 33,
90
+ "ˌaɪɚ": 94,
91
+ "ˌaʊ": 111,
92
+ "ˌeɪ": 8,
93
+ "ˌiə": 19,
94
+ "ˌiː": 13,
95
+ "ˌn̩": 35,
96
+ "ˌoʊ": 58,
97
+ "ˌoː": 40,
98
+ "ˌoːɹ": 6,
99
+ "ˌuː": 39,
100
+ "ˌæ": 97,
101
+ "ˌɐ": 61,
102
+ "ˌɑː": 44,
103
+ "ˌɑːɹ": 93,
104
+ "ˌɔ": 18,
105
+ "ˌɔɪ": 10,
106
+ "ˌɔː": 70,
107
+ "ˌɔːɹ": 100,
108
+ "ˌɛ": 86,
109
+ "ˌɛɹ": 60,
110
+ "ˌɜː": 64,
111
+ "ˌɪ": 20,
112
+ "ˌɪɹ": 26,
113
+ "ˌʊ": 34,
114
+ "ˌʊɹ": 101,
115
+ "ˌʌ": 88,
116
+ "θ": 51,
117
+ "ᵻ": 85
118
  }