Text-to-Speech
tts
vits
multilingual
piper
ayousanz commited on
Commit
ce006e5
·
verified ·
1 Parent(s): 5d52a01

Fix phoneme_id_map: PUA-encode multi-codepoint IPA phonemes (U+0254+U+026A, U+0153+U+0303, U+0250+U+0303 -> U+E062/E063/E064) for C++ runtime compatibility

Browse files
Files changed (1) hide show
  1. config.json +584 -584
config.json CHANGED
@@ -1,585 +1,585 @@
1
- {
2
- "dataset": "multilingual-6lang",
3
- "audio": {
4
- "sample_rate": 22050,
5
- "quality": "medium"
6
- },
7
- "language": {
8
- "code": "ja-en-zh-es-fr-pt"
9
- },
10
- "inference": {
11
- "noise_scale": 0.667,
12
- "length_scale": 1,
13
- "noise_w": 0.8
14
- },
15
- "phoneme_type": "multilingual",
16
- "phoneme_map": {},
17
- "phoneme_id_map": {
18
- "_": [
19
- 0
20
- ],
21
- "^": [
22
- 1
23
- ],
24
- "$": [
25
- 2
26
- ],
27
- "?": [
28
- 3
29
- ],
30
- "": [
31
- 4
32
- ],
33
- "": [
34
- 5
35
- ],
36
- "": [
37
- 6
38
- ],
39
- "#": [
40
- 7
41
- ],
42
- "[": [
43
- 8
44
- ],
45
- "]": [
46
- 9
47
- ],
48
- "a": [
49
- 10
50
- ],
51
- "i": [
52
- 11
53
- ],
54
- "u": [
55
- 12
56
- ],
57
- "e": [
58
- 13
59
- ],
60
- "o": [
61
- 14
62
- ],
63
- "A": [
64
- 15
65
- ],
66
- "I": [
67
- 16
68
- ],
69
- "U": [
70
- 17
71
- ],
72
- "E": [
73
- 18
74
- ],
75
- "O": [
76
- 19
77
- ],
78
- "": [
79
- 20
80
- ],
81
- "": [
82
- 21
83
- ],
84
- "": [
85
- 22
86
- ],
87
- "": [
88
- 23
89
- ],
90
- "": [
91
- 24
92
- ],
93
- "N": [
94
- 25
95
- ],
96
- "": [
97
- 26
98
- ],
99
- "": [
100
- 27
101
- ],
102
- "": [
103
- 28
104
- ],
105
- "": [
106
- 29
107
- ],
108
- "": [
109
- 30
110
- ],
111
- "q": [
112
- 31
113
- ],
114
- "k": [
115
- 32
116
- ],
117
- "": [
118
- 33
119
- ],
120
- "": [
121
- 34
122
- ],
123
- "g": [
124
- 35
125
- ],
126
- "": [
127
- 36
128
- ],
129
- "": [
130
- 37
131
- ],
132
- "t": [
133
- 38
134
- ],
135
- "": [
136
- 39
137
- ],
138
- "d": [
139
- 40
140
- ],
141
- "": [
142
- 41
143
- ],
144
- "p": [
145
- 42
146
- ],
147
- "": [
148
- 43
149
- ],
150
- "b": [
151
- 44
152
- ],
153
- "": [
154
- 45
155
- ],
156
- "": [
157
- 46
158
- ],
159
- "": [
160
- 47
161
- ],
162
- "s": [
163
- 48
164
- ],
165
- "": [
166
- 49
167
- ],
168
- "z": [
169
- 50
170
- ],
171
- "j": [
172
- 51
173
- ],
174
- "": [
175
- 52
176
- ],
177
- "f": [
178
- 53
179
- ],
180
- "h": [
181
- 54
182
- ],
183
- "": [
184
- 55
185
- ],
186
- "v": [
187
- 56
188
- ],
189
- "n": [
190
- 57
191
- ],
192
- "": [
193
- 58
194
- ],
195
- "m": [
196
- 59
197
- ],
198
- "": [
199
- 60
200
- ],
201
- "r": [
202
- 61
203
- ],
204
- "": [
205
- 62
206
- ],
207
- "w": [
208
- 63
209
- ],
210
- "y": [
211
- 64
212
- ],
213
- "ɪ": [
214
- 65
215
- ],
216
- "ʊ": [
217
- 66
218
- ],
219
- "ɛ": [
220
- 67
221
- ],
222
- "ɔ": [
223
- 68
224
- ],
225
- "æ": [
226
- 69
227
- ],
228
- "ɑ": [
229
- 70
230
- ],
231
- "ʌ": [
232
- 71
233
- ],
234
- "ə": [
235
- 72
236
- ],
237
- "ɜ": [
238
- 73
239
- ],
240
- "ɹ": [
241
- 74
242
- ],
243
- "ɝ": [
244
- 75
245
- ],
246
- "ɫ": [
247
- 76
248
- ],
249
- "ð": [
250
- 77
251
- ],
252
- "θ": [
253
- 78
254
- ],
255
- "ŋ": [
256
- 79
257
- ],
258
- "ʃ": [
259
- 80
260
- ],
261
- "ʒ": [
262
- 81
263
- ],
264
- "": [
265
- 82
266
- ],
267
- "": [
268
- 83
269
- ],
270
- "l": [
271
- 84
272
- ],
273
- "ɡ": [
274
- 85
275
- ],
276
- "x": [
277
- 86
278
- ],
279
- "ˈ": [
280
- 87
281
- ],
282
- "ˌ": [
283
- 88
284
- ],
285
- "ː": [
286
- 89
287
- ],
288
- "": [
289
- 90
290
- ],
291
- "": [
292
- 91
293
- ],
294
- "": [
295
- 92
296
- ],
297
- "": [
298
- 93
299
- ],
300
- "ɔɪ": [
301
- 94
302
- ],
303
- "": [
304
- 95
305
- ],
306
- "": [
307
- 96
308
- ],
309
- "": [
310
- 97
311
- ],
312
- "": [
313
- 98
314
- ],
315
- "": [
316
- 99
317
- ],
318
- "": [
319
- 100
320
- ],
321
- "": [
322
- 101
323
- ],
324
- "": [
325
- 102
326
- ],
327
- "": [
328
- 103
329
- ],
330
- "": [
331
- 104
332
- ],
333
- "": [
334
- 105
335
- ],
336
- "": [
337
- 106
338
- ],
339
- "": [
340
- 107
341
- ],
342
- "": [
343
- 108
344
- ],
345
- "": [
346
- 109
347
- ],
348
- "": [
349
- 110
350
- ],
351
- "": [
352
- 111
353
- ],
354
- "": [
355
- 112
356
- ],
357
- "": [
358
- 113
359
- ],
360
- "": [
361
- 114
362
- ],
363
- "": [
364
- 115
365
- ],
366
- "": [
367
- 116
368
- ],
369
- "": [
370
- 117
371
- ],
372
- "": [
373
- 118
374
- ],
375
- "": [
376
- 119
377
- ],
378
- "": [
379
- 120
380
- ],
381
- "": [
382
- 121
383
- ],
384
- "": [
385
- 122
386
- ],
387
- "": [
388
- 123
389
- ],
390
- "": [
391
- 124
392
- ],
393
- "": [
394
- 125
395
- ],
396
- "ɕ": [
397
- 126
398
- ],
399
- "ɚ": [
400
- 127
401
- ],
402
- "ɤ": [
403
- 128
404
- ],
405
- "ɨ": [
406
- 129
407
- ],
408
- "ɻ": [
409
- 130
410
- ],
411
- "ʂ": [
412
- 131
413
- ],
414
- "": [
415
- 132
416
- ],
417
- "": [
418
- 133
419
- ],
420
- "": [
421
- 134
422
- ],
423
- "": [
424
- 135
425
- ],
426
- "": [
427
- 136
428
- ],
429
- "": [
430
- 137
431
- ],
432
- "": [
433
- 138
434
- ],
435
- "": [
436
- 139
437
- ],
438
- "": [
439
- 140
440
- ],
441
- "ɲ": [
442
- 141
443
- ],
444
- "ʎ": [
445
- 142
446
- ],
447
- "β": [
448
- 143
449
- ],
450
- "ɣ": [
451
- 144
452
- ],
453
- "ʁ": [
454
- 145
455
- ],
456
- "": [
457
- 146
458
- ],
459
- "": [
460
- 147
461
- ],
462
- "": [
463
- 148
464
- ],
465
- "œ̃": [
466
- 149
467
- ],
468
- "ø": [
469
- 150
470
- ],
471
- "œ": [
472
- 151
473
- ],
474
- "ɐ": [
475
- 152
476
- ],
477
- "ɐ̃": [
478
- 153
479
- ],
480
- "ẽ": [
481
- 154
482
- ],
483
- "ĩ": [
484
- 155
485
- ],
486
- "õ": [
487
- 156
488
- ],
489
- "ũ": [
490
- 157
491
- ],
492
- "": [
493
- 158
494
- ],
495
- "": [
496
- 159
497
- ],
498
- "": [
499
- 160
500
- ],
501
- "": [
502
- 161
503
- ],
504
- "": [
505
- 162
506
- ],
507
- "": [
508
- 163
509
- ],
510
- "": [
511
- 164
512
- ],
513
- "": [
514
- 165
515
- ],
516
- "ɯ": [
517
- 166
518
- ],
519
- "ɾ": [
520
- 167
521
- ],
522
- "ɰ": [
523
- 168
524
- ],
525
- "ɖ": [
526
- 169
527
- ],
528
- "ʈ": [
529
- 170
530
- ],
531
- "ɳ": [
532
- 171
533
- ],
534
- "ɭ": [
535
- 172
536
- ]
537
- },
538
- "num_symbols": 173,
539
- "num_speakers": 0,
540
- "num_languages": 6,
541
- "language_id_map": {
542
- "ja": 0,
543
- "en": 1,
544
- "zh": 2,
545
- "es": 3,
546
- "fr": 4,
547
- "pt": 5
548
- },
549
- "prosody_num_symbols": 11,
550
- "prosody_id_map": {
551
- "0": [
552
- 0
553
- ],
554
- "1": [
555
- 1
556
- ],
557
- "2": [
558
- 2
559
- ],
560
- "3": [
561
- 3
562
- ],
563
- "4": [
564
- 4
565
- ],
566
- "5": [
567
- 5
568
- ],
569
- "6": [
570
- 6
571
- ],
572
- "7": [
573
- 7
574
- ],
575
- "8": [
576
- 8
577
- ],
578
- "9": [
579
- 9
580
- ],
581
- "10": [
582
- 10
583
- ]
584
- }
585
  }
 
1
+ {
2
+ "dataset": "multilingual-6lang",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "language": {
8
+ "code": "ja-en-zh-es-fr-pt"
9
+ },
10
+ "inference": {
11
+ "noise_scale": 0.667,
12
+ "length_scale": 1,
13
+ "noise_w": 0.8
14
+ },
15
+ "phoneme_type": "multilingual",
16
+ "phoneme_map": {},
17
+ "phoneme_id_map": {
18
+ "_": [
19
+ 0
20
+ ],
21
+ "^": [
22
+ 1
23
+ ],
24
+ "$": [
25
+ 2
26
+ ],
27
+ "?": [
28
+ 3
29
+ ],
30
+ "": [
31
+ 4
32
+ ],
33
+ "": [
34
+ 5
35
+ ],
36
+ "": [
37
+ 6
38
+ ],
39
+ "#": [
40
+ 7
41
+ ],
42
+ "[": [
43
+ 8
44
+ ],
45
+ "]": [
46
+ 9
47
+ ],
48
+ "a": [
49
+ 10
50
+ ],
51
+ "i": [
52
+ 11
53
+ ],
54
+ "u": [
55
+ 12
56
+ ],
57
+ "e": [
58
+ 13
59
+ ],
60
+ "o": [
61
+ 14
62
+ ],
63
+ "A": [
64
+ 15
65
+ ],
66
+ "I": [
67
+ 16
68
+ ],
69
+ "U": [
70
+ 17
71
+ ],
72
+ "E": [
73
+ 18
74
+ ],
75
+ "O": [
76
+ 19
77
+ ],
78
+ "": [
79
+ 20
80
+ ],
81
+ "": [
82
+ 21
83
+ ],
84
+ "": [
85
+ 22
86
+ ],
87
+ "": [
88
+ 23
89
+ ],
90
+ "": [
91
+ 24
92
+ ],
93
+ "N": [
94
+ 25
95
+ ],
96
+ "": [
97
+ 26
98
+ ],
99
+ "": [
100
+ 27
101
+ ],
102
+ "": [
103
+ 28
104
+ ],
105
+ "": [
106
+ 29
107
+ ],
108
+ "": [
109
+ 30
110
+ ],
111
+ "q": [
112
+ 31
113
+ ],
114
+ "k": [
115
+ 32
116
+ ],
117
+ "": [
118
+ 33
119
+ ],
120
+ "": [
121
+ 34
122
+ ],
123
+ "g": [
124
+ 35
125
+ ],
126
+ "": [
127
+ 36
128
+ ],
129
+ "": [
130
+ 37
131
+ ],
132
+ "t": [
133
+ 38
134
+ ],
135
+ "": [
136
+ 39
137
+ ],
138
+ "d": [
139
+ 40
140
+ ],
141
+ "": [
142
+ 41
143
+ ],
144
+ "p": [
145
+ 42
146
+ ],
147
+ "": [
148
+ 43
149
+ ],
150
+ "b": [
151
+ 44
152
+ ],
153
+ "": [
154
+ 45
155
+ ],
156
+ "": [
157
+ 46
158
+ ],
159
+ "": [
160
+ 47
161
+ ],
162
+ "s": [
163
+ 48
164
+ ],
165
+ "": [
166
+ 49
167
+ ],
168
+ "z": [
169
+ 50
170
+ ],
171
+ "j": [
172
+ 51
173
+ ],
174
+ "": [
175
+ 52
176
+ ],
177
+ "f": [
178
+ 53
179
+ ],
180
+ "h": [
181
+ 54
182
+ ],
183
+ "": [
184
+ 55
185
+ ],
186
+ "v": [
187
+ 56
188
+ ],
189
+ "n": [
190
+ 57
191
+ ],
192
+ "": [
193
+ 58
194
+ ],
195
+ "m": [
196
+ 59
197
+ ],
198
+ "": [
199
+ 60
200
+ ],
201
+ "r": [
202
+ 61
203
+ ],
204
+ "": [
205
+ 62
206
+ ],
207
+ "w": [
208
+ 63
209
+ ],
210
+ "y": [
211
+ 64
212
+ ],
213
+ "ɪ": [
214
+ 65
215
+ ],
216
+ "ʊ": [
217
+ 66
218
+ ],
219
+ "ɛ": [
220
+ 67
221
+ ],
222
+ "ɔ": [
223
+ 68
224
+ ],
225
+ "æ": [
226
+ 69
227
+ ],
228
+ "ɑ": [
229
+ 70
230
+ ],
231
+ "ʌ": [
232
+ 71
233
+ ],
234
+ "ə": [
235
+ 72
236
+ ],
237
+ "ɜ": [
238
+ 73
239
+ ],
240
+ "ɹ": [
241
+ 74
242
+ ],
243
+ "ɝ": [
244
+ 75
245
+ ],
246
+ "ɫ": [
247
+ 76
248
+ ],
249
+ "ð": [
250
+ 77
251
+ ],
252
+ "θ": [
253
+ 78
254
+ ],
255
+ "ŋ": [
256
+ 79
257
+ ],
258
+ "ʃ": [
259
+ 80
260
+ ],
261
+ "ʒ": [
262
+ 81
263
+ ],
264
+ "": [
265
+ 82
266
+ ],
267
+ "": [
268
+ 83
269
+ ],
270
+ "l": [
271
+ 84
272
+ ],
273
+ "ɡ": [
274
+ 85
275
+ ],
276
+ "x": [
277
+ 86
278
+ ],
279
+ "ˈ": [
280
+ 87
281
+ ],
282
+ "ˌ": [
283
+ 88
284
+ ],
285
+ "ː": [
286
+ 89
287
+ ],
288
+ "": [
289
+ 90
290
+ ],
291
+ "": [
292
+ 91
293
+ ],
294
+ "": [
295
+ 92
296
+ ],
297
+ "": [
298
+ 93
299
+ ],
300
+ "": [
301
+ 94
302
+ ],
303
+ "": [
304
+ 95
305
+ ],
306
+ "": [
307
+ 96
308
+ ],
309
+ "": [
310
+ 97
311
+ ],
312
+ "": [
313
+ 98
314
+ ],
315
+ "": [
316
+ 99
317
+ ],
318
+ "": [
319
+ 100
320
+ ],
321
+ "": [
322
+ 101
323
+ ],
324
+ "": [
325
+ 102
326
+ ],
327
+ "": [
328
+ 103
329
+ ],
330
+ "": [
331
+ 104
332
+ ],
333
+ "": [
334
+ 105
335
+ ],
336
+ "": [
337
+ 106
338
+ ],
339
+ "": [
340
+ 107
341
+ ],
342
+ "": [
343
+ 108
344
+ ],
345
+ "": [
346
+ 109
347
+ ],
348
+ "": [
349
+ 110
350
+ ],
351
+ "": [
352
+ 111
353
+ ],
354
+ "": [
355
+ 112
356
+ ],
357
+ "": [
358
+ 113
359
+ ],
360
+ "": [
361
+ 114
362
+ ],
363
+ "": [
364
+ 115
365
+ ],
366
+ "": [
367
+ 116
368
+ ],
369
+ "": [
370
+ 117
371
+ ],
372
+ "": [
373
+ 118
374
+ ],
375
+ "": [
376
+ 119
377
+ ],
378
+ "": [
379
+ 120
380
+ ],
381
+ "": [
382
+ 121
383
+ ],
384
+ "": [
385
+ 122
386
+ ],
387
+ "": [
388
+ 123
389
+ ],
390
+ "": [
391
+ 124
392
+ ],
393
+ "": [
394
+ 125
395
+ ],
396
+ "ɕ": [
397
+ 126
398
+ ],
399
+ "ɚ": [
400
+ 127
401
+ ],
402
+ "ɤ": [
403
+ 128
404
+ ],
405
+ "ɨ": [
406
+ 129
407
+ ],
408
+ "ɻ": [
409
+ 130
410
+ ],
411
+ "ʂ": [
412
+ 131
413
+ ],
414
+ "": [
415
+ 132
416
+ ],
417
+ "": [
418
+ 133
419
+ ],
420
+ "": [
421
+ 134
422
+ ],
423
+ "": [
424
+ 135
425
+ ],
426
+ "": [
427
+ 136
428
+ ],
429
+ "": [
430
+ 137
431
+ ],
432
+ "": [
433
+ 138
434
+ ],
435
+ "": [
436
+ 139
437
+ ],
438
+ "": [
439
+ 140
440
+ ],
441
+ "ɲ": [
442
+ 141
443
+ ],
444
+ "ʎ": [
445
+ 142
446
+ ],
447
+ "β": [
448
+ 143
449
+ ],
450
+ "ɣ": [
451
+ 144
452
+ ],
453
+ "ʁ": [
454
+ 145
455
+ ],
456
+ "": [
457
+ 146
458
+ ],
459
+ "": [
460
+ 147
461
+ ],
462
+ "": [
463
+ 148
464
+ ],
465
+ "": [
466
+ 149
467
+ ],
468
+ "ø": [
469
+ 150
470
+ ],
471
+ "œ": [
472
+ 151
473
+ ],
474
+ "ɐ": [
475
+ 152
476
+ ],
477
+ "": [
478
+ 153
479
+ ],
480
+ "ẽ": [
481
+ 154
482
+ ],
483
+ "ĩ": [
484
+ 155
485
+ ],
486
+ "õ": [
487
+ 156
488
+ ],
489
+ "ũ": [
490
+ 157
491
+ ],
492
+ "": [
493
+ 158
494
+ ],
495
+ "": [
496
+ 159
497
+ ],
498
+ "": [
499
+ 160
500
+ ],
501
+ "": [
502
+ 161
503
+ ],
504
+ "": [
505
+ 162
506
+ ],
507
+ "": [
508
+ 163
509
+ ],
510
+ "": [
511
+ 164
512
+ ],
513
+ "": [
514
+ 165
515
+ ],
516
+ "ɯ": [
517
+ 166
518
+ ],
519
+ "ɾ": [
520
+ 167
521
+ ],
522
+ "ɰ": [
523
+ 168
524
+ ],
525
+ "ɖ": [
526
+ 169
527
+ ],
528
+ "ʈ": [
529
+ 170
530
+ ],
531
+ "ɳ": [
532
+ 171
533
+ ],
534
+ "ɭ": [
535
+ 172
536
+ ]
537
+ },
538
+ "num_symbols": 173,
539
+ "num_speakers": 0,
540
+ "num_languages": 6,
541
+ "language_id_map": {
542
+ "ja": 0,
543
+ "en": 1,
544
+ "zh": 2,
545
+ "es": 3,
546
+ "fr": 4,
547
+ "pt": 5
548
+ },
549
+ "prosody_num_symbols": 11,
550
+ "prosody_id_map": {
551
+ "0": [
552
+ 0
553
+ ],
554
+ "1": [
555
+ 1
556
+ ],
557
+ "2": [
558
+ 2
559
+ ],
560
+ "3": [
561
+ 3
562
+ ],
563
+ "4": [
564
+ 4
565
+ ],
566
+ "5": [
567
+ 5
568
+ ],
569
+ "6": [
570
+ 6
571
+ ],
572
+ "7": [
573
+ 7
574
+ ],
575
+ "8": [
576
+ 8
577
+ ],
578
+ "9": [
579
+ 9
580
+ ],
581
+ "10": [
582
+ 10
583
+ ]
584
+ }
585
  }