ONNX

PR: Update it_IT-serena-medium and it_IT-serena-high (fixed: sentence-initial word collapse)

#96
by bacca87 - opened
it/it_IT/serena/high/it_IT-serena-high.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:743240dae6ecab12cdc3eee9260cbf688a04e066775d0ce28b8007dad12f42d0
3
- size 114199010
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7462fbdf03727fb4c0c161286ad538fe6436b7e4b1c3059ef52930032475955f
3
+ size 114204024
it/it_IT/serena/high/it_IT-serena-high.onnx.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "dataset": "serena",
3
  "audio": {
4
  "sample_rate": 22050,
5
  "quality": "high"
@@ -7,37 +6,30 @@
7
  "espeak": {
8
  "voice": "it"
9
  },
10
- "language": {
11
- "code": "it_IT",
12
- "family": "it",
13
- "region": "IT",
14
- "name_native": "Italiano",
15
- "name_english": "Italian",
16
- "country_english": "Italy"
17
- },
18
  "inference": {
19
  "noise_scale": 0.6,
20
- "length_scale": 1,
21
  "noise_w": 0.4
22
  },
23
- "phoneme_type": "espeak",
24
- "phoneme_map": {},
25
  "phoneme_id_map": {
 
 
 
 
 
 
 
 
 
26
  " ": [
27
  3
28
  ],
29
  "!": [
30
  4
31
  ],
32
- "\"": [
33
- 150
34
- ],
35
- "#": [
36
- 149
37
- ],
38
- "$": [
39
- 2
40
- ],
41
  "'": [
42
  5
43
  ],
@@ -56,36 +48,6 @@
56
  ".": [
57
  10
58
  ],
59
- "0": [
60
- 130
61
- ],
62
- "1": [
63
- 131
64
- ],
65
- "2": [
66
- 132
67
- ],
68
- "3": [
69
- 133
70
- ],
71
- "4": [
72
- 134
73
- ],
74
- "5": [
75
- 135
76
- ],
77
- "6": [
78
- 136
79
- ],
80
- "7": [
81
- 137
82
- ],
83
- "8": [
84
- 138
85
- ],
86
- "9": [
87
- 139
88
- ],
89
  ":": [
90
  11
91
  ],
@@ -95,15 +57,6 @@
95
  "?": [
96
  13
97
  ],
98
- "X": [
99
- 156
100
- ],
101
- "^": [
102
- 1
103
- ],
104
- "_": [
105
- 0
106
- ],
107
  "a": [
108
  14
109
  ],
@@ -122,9 +75,6 @@
122
  "f": [
123
  19
124
  ],
125
- "g": [
126
- 154
127
- ],
128
  "h": [
129
  20
130
  ],
@@ -422,12 +372,6 @@
422
  "ʢ": [
423
  118
424
  ],
425
- "ʦ": [
426
- 155
427
- ],
428
- "ʰ": [
429
- 145
430
- ],
431
  "ʲ": [
432
  119
433
  ],
@@ -446,17 +390,56 @@
446
  "˞": [
447
  124
448
  ],
449
- "ˤ": [
450
- 146
451
  ],
452
- "̃": [
453
- 141
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
454
  ],
455
  "̧": [
456
  140
457
  ],
458
- "̩": [
459
- 144
460
  ],
461
  "̪": [
462
  142
@@ -464,39 +447,84 @@
464
  "̯": [
465
  143
466
  ],
467
- "̺": [
468
- 152
469
  ],
470
- "̻": [
471
- 153
472
  ],
473
- "β": [
474
- 125
475
  ],
476
  "ε": [
477
  147
478
  ],
479
- "θ": [
480
- 126
481
  ],
482
- "χ": [
483
- 127
484
  ],
485
- "": [
486
- 128
487
  ],
488
  "↑": [
489
  151
490
  ],
491
- "": [
492
- 148
493
  ],
494
- "": [
495
- 129
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
496
  ]
497
  },
498
- "num_symbols": 256,
499
- "num_speakers": 1,
500
  "speaker_id_map": {},
501
- "piper_version": "1.0.0"
502
- }
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
 
2
  "audio": {
3
  "sample_rate": 22050,
4
  "quality": "high"
 
6
  "espeak": {
7
  "voice": "it"
8
  },
9
+ "phoneme_type": "espeak",
10
+ "num_symbols": 256,
11
+ "num_speakers": 1,
 
 
 
 
 
12
  "inference": {
13
  "noise_scale": 0.6,
14
+ "length_scale": 1.0,
15
  "noise_w": 0.4
16
  },
 
 
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
  ],
 
48
  ".": [
49
  10
50
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  ":": [
52
  11
53
  ],
 
57
  "?": [
58
  13
59
  ],
 
 
 
 
 
 
 
 
 
60
  "a": [
61
  14
62
  ],
 
75
  "f": [
76
  19
77
  ],
 
 
 
78
  "h": [
79
  20
80
  ],
 
372
  "ʢ": [
373
  118
374
  ],
 
 
 
 
 
 
375
  "ʲ": [
376
  119
377
  ],
 
390
  "˞": [
391
  124
392
  ],
393
+ "β": [
394
+ 125
395
  ],
396
+ "θ": [
397
+ 126
398
+ ],
399
+ "χ": [
400
+ 127
401
+ ],
402
+ "ᵻ": [
403
+ 128
404
+ ],
405
+ "ⱱ": [
406
+ 129
407
+ ],
408
+ "0": [
409
+ 130
410
+ ],
411
+ "1": [
412
+ 131
413
+ ],
414
+ "2": [
415
+ 132
416
+ ],
417
+ "3": [
418
+ 133
419
+ ],
420
+ "4": [
421
+ 134
422
+ ],
423
+ "5": [
424
+ 135
425
+ ],
426
+ "6": [
427
+ 136
428
+ ],
429
+ "7": [
430
+ 137
431
+ ],
432
+ "8": [
433
+ 138
434
+ ],
435
+ "9": [
436
+ 139
437
  ],
438
  "̧": [
439
  140
440
  ],
441
+ "̃": [
442
+ 141
443
  ],
444
  "̪": [
445
  142
 
447
  "̯": [
448
  143
449
  ],
450
+ "̩": [
451
+ 144
452
  ],
453
+ "ʰ": [
454
+ 145
455
  ],
456
+ "ˤ": [
457
+ 146
458
  ],
459
  "ε": [
460
  147
461
  ],
462
+ "": [
463
+ 148
464
  ],
465
+ "#": [
466
+ 149
467
  ],
468
+ "\"": [
469
+ 150
470
  ],
471
  "↑": [
472
  151
473
  ],
474
+ "̺": [
475
+ 152
476
  ],
477
+ "̻": [
478
+ 153
479
+ ],
480
+ "g": [
481
+ 154
482
+ ],
483
+ "ʦ": [
484
+ 155
485
+ ],
486
+ "X": [
487
+ 156
488
+ ],
489
+ "̝": [
490
+ 157
491
+ ],
492
+ "̊": [
493
+ 158
494
+ ],
495
+ "ɝ": [
496
+ 159
497
+ ],
498
+ "ʷ": [
499
+ 160
500
+ ],
501
+ "aɪ": [
502
+ 161
503
+ ],
504
+ "aʊ": [
505
+ 162
506
+ ],
507
+ "ɔɪ": [
508
+ 163
509
+ ],
510
+ "eɪ": [
511
+ 164
512
+ ],
513
+ "oʊ": [
514
+ 165
515
  ]
516
  },
 
 
517
  "speaker_id_map": {},
518
+ "hop_length": 256,
519
+ "default_speaker_id": 0,
520
+ "piper_version": "1.5.0",
521
+ "language": {
522
+ "code": "it_IT",
523
+ "family": "it",
524
+ "region": "IT",
525
+ "name_native": "Italiano",
526
+ "name_english": "Italian",
527
+ "country_english": "Italy"
528
+ },
529
+ "dataset": "serena"
530
+ }
it/it_IT/serena/high/samples/speaker_0.mp3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc3ed06a45739f43fb89fc293117f668ee0db455c2db6449d0f0e44466134feb
3
- size 126504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:773344bd87d51b4e16c4aa79aedc144c3d830b999b3aef609ed2070c38ba4f15
3
+ size 70043
it/it_IT/serena/medium/it_IT-serena-medium.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f1493311db17fec0e95cdf3c92f82b5006159b7743e057a749187469dfa7cf0
3
- size 63511037
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4e26b2c1236e2a44d2e295cad564d94a0d8b0a9fca1ccdfd70dd4af3116eb5
3
+ size 63516051
it/it_IT/serena/medium/it_IT-serena-medium.onnx.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "dataset": "serena",
3
  "audio": {
4
  "sample_rate": 22050,
5
  "quality": "medium"
@@ -7,37 +6,30 @@
7
  "espeak": {
8
  "voice": "it"
9
  },
10
- "language": {
11
- "code": "it_IT",
12
- "family": "it",
13
- "region": "IT",
14
- "name_native": "Italiano",
15
- "name_english": "Italian",
16
- "country_english": "Italy"
17
- },
18
  "inference": {
19
  "noise_scale": 0.6,
20
- "length_scale": 1,
21
  "noise_w": 0.4
22
  },
23
- "phoneme_type": "espeak",
24
- "phoneme_map": {},
25
  "phoneme_id_map": {
 
 
 
 
 
 
 
 
 
26
  " ": [
27
  3
28
  ],
29
  "!": [
30
  4
31
  ],
32
- "\"": [
33
- 150
34
- ],
35
- "#": [
36
- 149
37
- ],
38
- "$": [
39
- 2
40
- ],
41
  "'": [
42
  5
43
  ],
@@ -56,36 +48,6 @@
56
  ".": [
57
  10
58
  ],
59
- "0": [
60
- 130
61
- ],
62
- "1": [
63
- 131
64
- ],
65
- "2": [
66
- 132
67
- ],
68
- "3": [
69
- 133
70
- ],
71
- "4": [
72
- 134
73
- ],
74
- "5": [
75
- 135
76
- ],
77
- "6": [
78
- 136
79
- ],
80
- "7": [
81
- 137
82
- ],
83
- "8": [
84
- 138
85
- ],
86
- "9": [
87
- 139
88
- ],
89
  ":": [
90
  11
91
  ],
@@ -95,15 +57,6 @@
95
  "?": [
96
  13
97
  ],
98
- "X": [
99
- 156
100
- ],
101
- "^": [
102
- 1
103
- ],
104
- "_": [
105
- 0
106
- ],
107
  "a": [
108
  14
109
  ],
@@ -122,9 +75,6 @@
122
  "f": [
123
  19
124
  ],
125
- "g": [
126
- 154
127
- ],
128
  "h": [
129
  20
130
  ],
@@ -422,12 +372,6 @@
422
  "ʢ": [
423
  118
424
  ],
425
- "ʦ": [
426
- 155
427
- ],
428
- "ʰ": [
429
- 145
430
- ],
431
  "ʲ": [
432
  119
433
  ],
@@ -446,17 +390,56 @@
446
  "˞": [
447
  124
448
  ],
449
- "ˤ": [
450
- 146
451
  ],
452
- "̃": [
453
- 141
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
454
  ],
455
  "̧": [
456
  140
457
  ],
458
- "̩": [
459
- 144
460
  ],
461
  "̪": [
462
  142
@@ -464,39 +447,84 @@
464
  "̯": [
465
  143
466
  ],
467
- "̺": [
468
- 152
469
  ],
470
- "̻": [
471
- 153
472
  ],
473
- "β": [
474
- 125
475
  ],
476
  "ε": [
477
  147
478
  ],
479
- "θ": [
480
- 126
481
  ],
482
- "χ": [
483
- 127
484
  ],
485
- "": [
486
- 128
487
  ],
488
  "↑": [
489
  151
490
  ],
491
- "": [
492
- 148
493
  ],
494
- "": [
495
- 129
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
496
  ]
497
  },
498
- "num_symbols": 256,
499
- "num_speakers": 1,
500
  "speaker_id_map": {},
501
- "piper_version": "1.0.0"
502
- }
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
 
2
  "audio": {
3
  "sample_rate": 22050,
4
  "quality": "medium"
 
6
  "espeak": {
7
  "voice": "it"
8
  },
9
+ "phoneme_type": "espeak",
10
+ "num_symbols": 256,
11
+ "num_speakers": 1,
 
 
 
 
 
12
  "inference": {
13
  "noise_scale": 0.6,
14
+ "length_scale": 1.0,
15
  "noise_w": 0.4
16
  },
 
 
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
  ],
 
48
  ".": [
49
  10
50
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  ":": [
52
  11
53
  ],
 
57
  "?": [
58
  13
59
  ],
 
 
 
 
 
 
 
 
 
60
  "a": [
61
  14
62
  ],
 
75
  "f": [
76
  19
77
  ],
 
 
 
78
  "h": [
79
  20
80
  ],
 
372
  "ʢ": [
373
  118
374
  ],
 
 
 
 
 
 
375
  "ʲ": [
376
  119
377
  ],
 
390
  "˞": [
391
  124
392
  ],
393
+ "β": [
394
+ 125
395
  ],
396
+ "θ": [
397
+ 126
398
+ ],
399
+ "χ": [
400
+ 127
401
+ ],
402
+ "ᵻ": [
403
+ 128
404
+ ],
405
+ "ⱱ": [
406
+ 129
407
+ ],
408
+ "0": [
409
+ 130
410
+ ],
411
+ "1": [
412
+ 131
413
+ ],
414
+ "2": [
415
+ 132
416
+ ],
417
+ "3": [
418
+ 133
419
+ ],
420
+ "4": [
421
+ 134
422
+ ],
423
+ "5": [
424
+ 135
425
+ ],
426
+ "6": [
427
+ 136
428
+ ],
429
+ "7": [
430
+ 137
431
+ ],
432
+ "8": [
433
+ 138
434
+ ],
435
+ "9": [
436
+ 139
437
  ],
438
  "̧": [
439
  140
440
  ],
441
+ "̃": [
442
+ 141
443
  ],
444
  "̪": [
445
  142
 
447
  "̯": [
448
  143
449
  ],
450
+ "̩": [
451
+ 144
452
  ],
453
+ "ʰ": [
454
+ 145
455
  ],
456
+ "ˤ": [
457
+ 146
458
  ],
459
  "ε": [
460
  147
461
  ],
462
+ "": [
463
+ 148
464
  ],
465
+ "#": [
466
+ 149
467
  ],
468
+ "\"": [
469
+ 150
470
  ],
471
  "↑": [
472
  151
473
  ],
474
+ "̺": [
475
+ 152
476
  ],
477
+ "̻": [
478
+ 153
479
+ ],
480
+ "g": [
481
+ 154
482
+ ],
483
+ "ʦ": [
484
+ 155
485
+ ],
486
+ "X": [
487
+ 156
488
+ ],
489
+ "̝": [
490
+ 157
491
+ ],
492
+ "̊": [
493
+ 158
494
+ ],
495
+ "ɝ": [
496
+ 159
497
+ ],
498
+ "ʷ": [
499
+ 160
500
+ ],
501
+ "aɪ": [
502
+ 161
503
+ ],
504
+ "aʊ": [
505
+ 162
506
+ ],
507
+ "ɔɪ": [
508
+ 163
509
+ ],
510
+ "eɪ": [
511
+ 164
512
+ ],
513
+ "oʊ": [
514
+ 165
515
  ]
516
  },
 
 
517
  "speaker_id_map": {},
518
+ "hop_length": 256,
519
+ "default_speaker_id": 0,
520
+ "piper_version": "1.5.0",
521
+ "language": {
522
+ "code": "it_IT",
523
+ "family": "it",
524
+ "region": "IT",
525
+ "name_native": "Italiano",
526
+ "name_english": "Italian",
527
+ "country_english": "Italy"
528
+ },
529
+ "dataset": "serena"
530
+ }
it/it_IT/serena/medium/samples/speaker_0.mp3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf7efbf87f01bac0096943d1c78301e53b835772c3d4e64231c05670976dea01
3
- size 125979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf3d2daf422893881cd9238fead9ee6d7aac7885ec24b5d04812ad0e4fcbea1
3
+ size 72576