ONNX
Michael Hansen commited on
Commit
1af0d6b
·
1 Parent(s): 5b59605

Add hi voices

Browse files
.gitattributes CHANGED
@@ -38,7 +38,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
38
  *.db filter=lfs diff=lfs merge=lfs -text
39
  *.voice filter=lfs diff=lfs merge=lfs -text
40
  *.mp3 filter=lfs diff=lfs merge=lfs -text
41
- hi/hi_IN/pratham/medium/samples/test_1.wav filter=lfs diff=lfs merge=lfs -text
42
- hi/hi_IN/pratham/medium/samples/test.wav filter=lfs diff=lfs merge=lfs -text
43
- hi/hi_IN/priyamvada/medium/samples/test_f.wav filter=lfs diff=lfs merge=lfs -text
44
- hi/hi_IN/priyamvada/medium/samples/test1_f.wav filter=lfs diff=lfs merge=lfs -text
 
38
  *.db filter=lfs diff=lfs merge=lfs -text
39
  *.voice filter=lfs diff=lfs merge=lfs -text
40
  *.mp3 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
_script/voicefest.py CHANGED
@@ -33,6 +33,7 @@ _LANGUAGES = {
33
  "fi_FI": Language("Suomi", "Finnish", "Finland"),
34
  "fr_FR": Language("Français", "French", "France"),
35
  "is_IS": Language("íslenska", "Icelandic", "Iceland"),
 
36
  "it_IT": Language("Italiano", "Italian", "Italy"),
37
  "he_IL": Language("עברית", "Hebrew", "Israel"),
38
  "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
 
33
  "fi_FI": Language("Suomi", "Finnish", "Finland"),
34
  "fr_FR": Language("Français", "French", "France"),
35
  "is_IS": Language("íslenska", "Icelandic", "Iceland"),
36
+ "hi_IN": Language("हिन्दी", "Hindi", "India"),
37
  "it_IT": Language("Italiano", "Italian", "Italy"),
38
  "he_IL": Language("עברית", "Hebrew", "Israel"),
39
  "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
hi/hi_IN/pratham/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for pratham (medium)
2
+
3
+ * Language: hi_IN (Hindi, India)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * License: http://creativecommons.org/licenses/by-nc-sa/4.0/
11
+
12
+ ## Training
13
+
14
+ Dataset: https://github.com/AI4Bharat/indicnlp_corpus
15
+ Trained by: https://github.com/PravalX
hi/hi_IN/pratham/medium/hi_IN-pratham-medium.onnx.json CHANGED
@@ -1,497 +1,502 @@
1
  {
2
- "dataset": "",
3
- "audio": {
4
- "sample_rate": 22050,
5
- "quality": "training_dir"
6
- },
7
- "espeak": {
8
- "voice": "hi"
9
- },
10
- "language": {
11
- "code": "hi"
12
- },
13
- "inference": {
14
- "noise_scale": 0.667,
15
- "length_scale": 1,
16
- "noise_w": 0.8
17
- },
18
- "phoneme_type": "espeak",
19
- "phoneme_map": {},
20
- "phoneme_id_map": {
21
- " ": [
22
- 3
23
- ],
24
- "!": [
25
- 4
26
- ],
27
- "\"": [
28
- 150
29
- ],
30
- "#": [
31
- 149
32
- ],
33
- "$": [
34
- 2
35
- ],
36
- "'": [
37
- 5
38
- ],
39
- "(": [
40
- 6
41
- ],
42
- ")": [
43
- 7
44
- ],
45
- ",": [
46
- 8
47
- ],
48
- "-": [
49
- 9
50
- ],
51
- ".": [
52
- 10
53
- ],
54
- "0": [
55
- 130
56
- ],
57
- "1": [
58
- 131
59
- ],
60
- "2": [
61
- 132
62
- ],
63
- "3": [
64
- 133
65
- ],
66
- "4": [
67
- 134
68
- ],
69
- "5": [
70
- 135
71
- ],
72
- "6": [
73
- 136
74
- ],
75
- "7": [
76
- 137
77
- ],
78
- "8": [
79
- 138
80
- ],
81
- "9": [
82
- 139
83
- ],
84
- ":": [
85
- 11
86
- ],
87
- ";": [
88
- 12
89
- ],
90
- "?": [
91
- 13
92
- ],
93
- "X": [
94
- 156
95
- ],
96
- "^": [
97
- 1
98
- ],
99
- "_": [
100
- 0
101
- ],
102
- "a": [
103
- 14
104
- ],
105
- "b": [
106
- 15
107
- ],
108
- "c": [
109
- 16
110
- ],
111
- "d": [
112
- 17
113
- ],
114
- "e": [
115
- 18
116
- ],
117
- "f": [
118
- 19
119
- ],
120
- "g": [
121
- 154
122
- ],
123
- "h": [
124
- 20
125
- ],
126
- "i": [
127
- 21
128
- ],
129
- "j": [
130
- 22
131
- ],
132
- "k": [
133
- 23
134
- ],
135
- "l": [
136
- 24
137
- ],
138
- "m": [
139
- 25
140
- ],
141
- "n": [
142
- 26
143
- ],
144
- "o": [
145
- 27
146
- ],
147
- "p": [
148
- 28
149
- ],
150
- "q": [
151
- 29
152
- ],
153
- "r": [
154
- 30
155
- ],
156
- "s": [
157
- 31
158
- ],
159
- "t": [
160
- 32
161
- ],
162
- "u": [
163
- 33
164
- ],
165
- "v": [
166
- 34
167
- ],
168
- "w": [
169
- 35
170
- ],
171
- "x": [
172
- 36
173
- ],
174
- "y": [
175
- 37
176
- ],
177
- "z": [
178
- 38
179
- ],
180
- "æ": [
181
- 39
182
- ],
183
- "ç": [
184
- 40
185
- ],
186
- "ð": [
187
- 41
188
- ],
189
- "ø": [
190
- 42
191
- ],
192
- "ħ": [
193
- 43
194
- ],
195
- "ŋ": [
196
- 44
197
- ],
198
- "œ": [
199
- 45
200
- ],
201
- "ǀ": [
202
- 46
203
- ],
204
- "ǁ": [
205
- 47
206
- ],
207
- "ǂ": [
208
- 48
209
- ],
210
- "ǃ": [
211
- 49
212
- ],
213
- "ɐ": [
214
- 50
215
- ],
216
- "ɑ": [
217
- 51
218
- ],
219
- "ɒ": [
220
- 52
221
- ],
222
- "ɓ": [
223
- 53
224
- ],
225
- "ɔ": [
226
- 54
227
- ],
228
- "ɕ": [
229
- 55
230
- ],
231
- "ɖ": [
232
- 56
233
- ],
234
- "ɗ": [
235
- 57
236
- ],
237
- "ɘ": [
238
- 58
239
- ],
240
- "ə": [
241
- 59
242
- ],
243
- "ɚ": [
244
- 60
245
- ],
246
- "ɛ": [
247
- 61
248
- ],
249
- "ɜ": [
250
- 62
251
- ],
252
- "ɞ": [
253
- 63
254
- ],
255
- "ɟ": [
256
- 64
257
- ],
258
- "ɠ": [
259
- 65
260
- ],
261
- "ɡ": [
262
- 66
263
- ],
264
- "ɢ": [
265
- 67
266
- ],
267
- "ɣ": [
268
- 68
269
- ],
270
- "ɤ": [
271
- 69
272
- ],
273
- "ɥ": [
274
- 70
275
- ],
276
- "ɦ": [
277
- 71
278
- ],
279
- "ɧ": [
280
- 72
281
- ],
282
- "ɨ": [
283
- 73
284
- ],
285
- "ɪ": [
286
- 74
287
- ],
288
- "ɫ": [
289
- 75
290
- ],
291
- "ɬ": [
292
- 76
293
- ],
294
- "ɭ": [
295
- 77
296
- ],
297
- "ɮ": [
298
- 78
299
- ],
300
- "ɯ": [
301
- 79
302
- ],
303
- "ɰ": [
304
- 80
305
- ],
306
- "ɱ": [
307
- 81
308
- ],
309
- "ɲ": [
310
- 82
311
- ],
312
- "ɳ": [
313
- 83
314
- ],
315
- "ɴ": [
316
- 84
317
- ],
318
- "ɵ": [
319
- 85
320
- ],
321
- "ɶ": [
322
- 86
323
- ],
324
- "ɸ": [
325
- 87
326
- ],
327
- "ɹ": [
328
- 88
329
- ],
330
- "ɺ": [
331
- 89
332
- ],
333
- "ɻ": [
334
- 90
335
- ],
336
- "ɽ": [
337
- 91
338
- ],
339
- "ɾ": [
340
- 92
341
- ],
342
- "ʀ": [
343
- 93
344
- ],
345
- "ʁ": [
346
- 94
347
- ],
348
- "ʂ": [
349
- 95
350
- ],
351
- "ʃ": [
352
- 96
353
- ],
354
- "ʄ": [
355
- 97
356
- ],
357
- "ʈ": [
358
- 98
359
- ],
360
- "ʉ": [
361
- 99
362
- ],
363
- "ʊ": [
364
- 100
365
- ],
366
- "ʋ": [
367
- 101
368
- ],
369
- "ʌ": [
370
- 102
371
- ],
372
- "ʍ": [
373
- 103
374
- ],
375
- "ʎ": [
376
- 104
377
- ],
378
- "ʏ": [
379
- 105
380
- ],
381
- "ʐ": [
382
- 106
383
- ],
384
- "ʑ": [
385
- 107
386
- ],
387
- "ʒ": [
388
- 108
389
- ],
390
- "ʔ": [
391
- 109
392
- ],
393
- "ʕ": [
394
- 110
395
- ],
396
- "ʘ": [
397
- 111
398
- ],
399
- "ʙ": [
400
- 112
401
- ],
402
- "ʛ": [
403
- 113
404
- ],
405
- "ʜ": [
406
- 114
407
- ],
408
- "ʝ": [
409
- 115
410
- ],
411
- "ʟ": [
412
- 116
413
- ],
414
- "ʡ": [
415
- 117
416
- ],
417
- "ʢ": [
418
- 118
419
- ],
420
- "ʦ": [
421
- 155
422
- ],
423
- "ʰ": [
424
- 145
425
- ],
426
- "ʲ": [
427
- 119
428
- ],
429
- "ˈ": [
430
- 120
431
- ],
432
- "ˌ": [
433
- 121
434
- ],
435
- "ː": [
436
- 122
437
- ],
438
- "ˑ": [
439
- 123
440
- ],
441
- "˞": [
442
- 124
443
- ],
444
- "ˤ": [
445
- 146
446
- ],
447
- "̃": [
448
- 141
449
- ],
450
- "̧": [
451
- 140
452
- ],
453
- "̩": [
454
- 144
455
- ],
456
- "̪": [
457
- 142
458
- ],
459
- "̯": [
460
- 143
461
- ],
462
- "̺": [
463
- 152
464
- ],
465
- "̻": [
466
- 153
467
- ],
468
- "β": [
469
- 125
470
- ],
471
- "ε": [
472
- 147
473
- ],
474
- "θ": [
475
- 126
476
- ],
477
- "χ": [
478
- 127
479
- ],
480
- "ᵻ": [
481
- 128
482
- ],
483
- "↑": [
484
- 151
485
- ],
486
- "↓": [
487
- 148
488
- ],
489
- "ⱱ": [
490
- 129
491
- ]
492
- },
493
- "num_symbols": 256,
494
- "num_speakers": 1,
495
- "speaker_id_map": {},
496
- "piper_version": "1.0.0"
497
- }
 
 
 
 
 
 
1
  {
2
+ "dataset": "pratham",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "hi"
9
+ },
10
+ "language": {
11
+ "code": "hi_IN",
12
+ "family": "hi",
13
+ "region": "IN",
14
+ "name_native": "हिन्दी",
15
+ "name_english": "Hindi",
16
+ "country_english": "India"
17
+ },
18
+ "inference": {
19
+ "noise_scale": 0.667,
20
+ "length_scale": 1,
21
+ "noise_w": 0.8
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
+ ],
44
+ "(": [
45
+ 6
46
+ ],
47
+ ")": [
48
+ 7
49
+ ],
50
+ ",": [
51
+ 8
52
+ ],
53
+ "-": [
54
+ 9
55
+ ],
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
+ ],
92
+ ";": [
93
+ 12
94
+ ],
95
+ "?": [
96
+ 13
97
+ ],
98
+ "X": [
99
+ 156
100
+ ],
101
+ "^": [
102
+ 1
103
+ ],
104
+ "_": [
105
+ 0
106
+ ],
107
+ "a": [
108
+ 14
109
+ ],
110
+ "b": [
111
+ 15
112
+ ],
113
+ "c": [
114
+ 16
115
+ ],
116
+ "d": [
117
+ 17
118
+ ],
119
+ "e": [
120
+ 18
121
+ ],
122
+ "f": [
123
+ 19
124
+ ],
125
+ "g": [
126
+ 154
127
+ ],
128
+ "h": [
129
+ 20
130
+ ],
131
+ "i": [
132
+ 21
133
+ ],
134
+ "j": [
135
+ 22
136
+ ],
137
+ "k": [
138
+ 23
139
+ ],
140
+ "l": [
141
+ 24
142
+ ],
143
+ "m": [
144
+ 25
145
+ ],
146
+ "n": [
147
+ 26
148
+ ],
149
+ "o": [
150
+ 27
151
+ ],
152
+ "p": [
153
+ 28
154
+ ],
155
+ "q": [
156
+ 29
157
+ ],
158
+ "r": [
159
+ 30
160
+ ],
161
+ "s": [
162
+ 31
163
+ ],
164
+ "t": [
165
+ 32
166
+ ],
167
+ "u": [
168
+ 33
169
+ ],
170
+ "v": [
171
+ 34
172
+ ],
173
+ "w": [
174
+ 35
175
+ ],
176
+ "x": [
177
+ 36
178
+ ],
179
+ "y": [
180
+ 37
181
+ ],
182
+ "z": [
183
+ 38
184
+ ],
185
+ "æ": [
186
+ 39
187
+ ],
188
+ "ç": [
189
+ 40
190
+ ],
191
+ "ð": [
192
+ 41
193
+ ],
194
+ "ø": [
195
+ 42
196
+ ],
197
+ "ħ": [
198
+ 43
199
+ ],
200
+ "ŋ": [
201
+ 44
202
+ ],
203
+ "œ": [
204
+ 45
205
+ ],
206
+ "ǀ": [
207
+ 46
208
+ ],
209
+ "ǁ": [
210
+ 47
211
+ ],
212
+ "ǂ": [
213
+ 48
214
+ ],
215
+ "ǃ": [
216
+ 49
217
+ ],
218
+ "ɐ": [
219
+ 50
220
+ ],
221
+ "ɑ": [
222
+ 51
223
+ ],
224
+ "ɒ": [
225
+ 52
226
+ ],
227
+ "ɓ": [
228
+ 53
229
+ ],
230
+ "ɔ": [
231
+ 54
232
+ ],
233
+ "ɕ": [
234
+ 55
235
+ ],
236
+ "ɖ": [
237
+ 56
238
+ ],
239
+ "ɗ": [
240
+ 57
241
+ ],
242
+ "ɘ": [
243
+ 58
244
+ ],
245
+ "ə": [
246
+ 59
247
+ ],
248
+ "ɚ": [
249
+ 60
250
+ ],
251
+ "ɛ": [
252
+ 61
253
+ ],
254
+ "ɜ": [
255
+ 62
256
+ ],
257
+ "ɞ": [
258
+ 63
259
+ ],
260
+ "ɟ": [
261
+ 64
262
+ ],
263
+ "ɠ": [
264
+ 65
265
+ ],
266
+ "ɡ": [
267
+ 66
268
+ ],
269
+ "ɢ": [
270
+ 67
271
+ ],
272
+ "ɣ": [
273
+ 68
274
+ ],
275
+ "ɤ": [
276
+ 69
277
+ ],
278
+ "ɥ": [
279
+ 70
280
+ ],
281
+ "ɦ": [
282
+ 71
283
+ ],
284
+ "ɧ": [
285
+ 72
286
+ ],
287
+ "ɨ": [
288
+ 73
289
+ ],
290
+ "ɪ": [
291
+ 74
292
+ ],
293
+ "ɫ": [
294
+ 75
295
+ ],
296
+ "ɬ": [
297
+ 76
298
+ ],
299
+ "ɭ": [
300
+ 77
301
+ ],
302
+ "ɮ": [
303
+ 78
304
+ ],
305
+ "ɯ": [
306
+ 79
307
+ ],
308
+ "ɰ": [
309
+ 80
310
+ ],
311
+ "ɱ": [
312
+ 81
313
+ ],
314
+ "ɲ": [
315
+ 82
316
+ ],
317
+ "ɳ": [
318
+ 83
319
+ ],
320
+ "ɴ": [
321
+ 84
322
+ ],
323
+ "ɵ": [
324
+ 85
325
+ ],
326
+ "ɶ": [
327
+ 86
328
+ ],
329
+ "ɸ": [
330
+ 87
331
+ ],
332
+ "ɹ": [
333
+ 88
334
+ ],
335
+ "ɺ": [
336
+ 89
337
+ ],
338
+ "ɻ": [
339
+ 90
340
+ ],
341
+ "ɽ": [
342
+ 91
343
+ ],
344
+ "ɾ": [
345
+ 92
346
+ ],
347
+ "ʀ": [
348
+ 93
349
+ ],
350
+ "ʁ": [
351
+ 94
352
+ ],
353
+ "ʂ": [
354
+ 95
355
+ ],
356
+ "ʃ": [
357
+ 96
358
+ ],
359
+ "ʄ": [
360
+ 97
361
+ ],
362
+ "ʈ": [
363
+ 98
364
+ ],
365
+ "ʉ": [
366
+ 99
367
+ ],
368
+ "ʊ": [
369
+ 100
370
+ ],
371
+ "ʋ": [
372
+ 101
373
+ ],
374
+ "ʌ": [
375
+ 102
376
+ ],
377
+ "ʍ": [
378
+ 103
379
+ ],
380
+ "ʎ": [
381
+ 104
382
+ ],
383
+ "ʏ": [
384
+ 105
385
+ ],
386
+ "ʐ": [
387
+ 106
388
+ ],
389
+ "ʑ": [
390
+ 107
391
+ ],
392
+ "ʒ": [
393
+ 108
394
+ ],
395
+ "ʔ": [
396
+ 109
397
+ ],
398
+ "ʕ": [
399
+ 110
400
+ ],
401
+ "ʘ": [
402
+ 111
403
+ ],
404
+ "ʙ": [
405
+ 112
406
+ ],
407
+ "ʛ": [
408
+ 113
409
+ ],
410
+ "ʜ": [
411
+ 114
412
+ ],
413
+ "ʝ": [
414
+ 115
415
+ ],
416
+ "ʟ": [
417
+ 116
418
+ ],
419
+ "ʡ": [
420
+ 117
421
+ ],
422
+ "ʢ": [
423
+ 118
424
+ ],
425
+ "ʦ": [
426
+ 155
427
+ ],
428
+ "ʰ": [
429
+ 145
430
+ ],
431
+ "ʲ": [
432
+ 119
433
+ ],
434
+ "ˈ": [
435
+ 120
436
+ ],
437
+ "ˌ": [
438
+ 121
439
+ ],
440
+ "ː": [
441
+ 122
442
+ ],
443
+ "ˑ": [
444
+ 123
445
+ ],
446
+ "˞": [
447
+ 124
448
+ ],
449
+ "ˤ": [
450
+ 146
451
+ ],
452
+ "̃": [
453
+ 141
454
+ ],
455
+ "̧": [
456
+ 140
457
+ ],
458
+ "̩": [
459
+ 144
460
+ ],
461
+ "̪": [
462
+ 142
463
+ ],
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
+ "ᵻ": [
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
+ }
hi/hi_IN/pratham/medium/samples/{test.wav → speaker_0.mp3} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f30577666c0a81469a0f27b90d66e4062c8b35fcb1fc82e13dad0e821262d84
3
- size 223788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ba9d3c44753f7ad2d3e1a05eeacd3375dde5f909eed20a4bb0616c18f87ec0
3
+ size 417082
hi/hi_IN/pratham/medium/samples/test_1.wav DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:57889997d7e3bb105e9d8c76e5f9c2ef17329a43480558e188cba8c41729335d
3
- size 2037292
 
 
 
 
hi/hi_IN/priyamvada/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for priyamvada (medium)
2
+
3
+ * Language: hi_IN (Hindi, India)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * License: http://creativecommons.org/licenses/by-nc-sa/4.0/
11
+
12
+ ## Training
13
+
14
+ Dataset: https://github.com/AI4Bharat/indicnlp_corpus
15
+ Trained by: https://github.com/PravalX
hi/hi_IN/priyamvada/medium/hi_IN-priyamvada-medium.onnx.json CHANGED
@@ -1,497 +1,502 @@
1
  {
2
- "dataset": "",
3
- "audio": {
4
- "sample_rate": 22050,
5
- "quality": "training_dir"
6
- },
7
- "espeak": {
8
- "voice": "hi"
9
- },
10
- "language": {
11
- "code": "hi"
12
- },
13
- "inference": {
14
- "noise_scale": 0.667,
15
- "length_scale": 1,
16
- "noise_w": 0.8
17
- },
18
- "phoneme_type": "espeak",
19
- "phoneme_map": {},
20
- "phoneme_id_map": {
21
- " ": [
22
- 3
23
- ],
24
- "!": [
25
- 4
26
- ],
27
- "\"": [
28
- 150
29
- ],
30
- "#": [
31
- 149
32
- ],
33
- "$": [
34
- 2
35
- ],
36
- "'": [
37
- 5
38
- ],
39
- "(": [
40
- 6
41
- ],
42
- ")": [
43
- 7
44
- ],
45
- ",": [
46
- 8
47
- ],
48
- "-": [
49
- 9
50
- ],
51
- ".": [
52
- 10
53
- ],
54
- "0": [
55
- 130
56
- ],
57
- "1": [
58
- 131
59
- ],
60
- "2": [
61
- 132
62
- ],
63
- "3": [
64
- 133
65
- ],
66
- "4": [
67
- 134
68
- ],
69
- "5": [
70
- 135
71
- ],
72
- "6": [
73
- 136
74
- ],
75
- "7": [
76
- 137
77
- ],
78
- "8": [
79
- 138
80
- ],
81
- "9": [
82
- 139
83
- ],
84
- ":": [
85
- 11
86
- ],
87
- ";": [
88
- 12
89
- ],
90
- "?": [
91
- 13
92
- ],
93
- "X": [
94
- 156
95
- ],
96
- "^": [
97
- 1
98
- ],
99
- "_": [
100
- 0
101
- ],
102
- "a": [
103
- 14
104
- ],
105
- "b": [
106
- 15
107
- ],
108
- "c": [
109
- 16
110
- ],
111
- "d": [
112
- 17
113
- ],
114
- "e": [
115
- 18
116
- ],
117
- "f": [
118
- 19
119
- ],
120
- "g": [
121
- 154
122
- ],
123
- "h": [
124
- 20
125
- ],
126
- "i": [
127
- 21
128
- ],
129
- "j": [
130
- 22
131
- ],
132
- "k": [
133
- 23
134
- ],
135
- "l": [
136
- 24
137
- ],
138
- "m": [
139
- 25
140
- ],
141
- "n": [
142
- 26
143
- ],
144
- "o": [
145
- 27
146
- ],
147
- "p": [
148
- 28
149
- ],
150
- "q": [
151
- 29
152
- ],
153
- "r": [
154
- 30
155
- ],
156
- "s": [
157
- 31
158
- ],
159
- "t": [
160
- 32
161
- ],
162
- "u": [
163
- 33
164
- ],
165
- "v": [
166
- 34
167
- ],
168
- "w": [
169
- 35
170
- ],
171
- "x": [
172
- 36
173
- ],
174
- "y": [
175
- 37
176
- ],
177
- "z": [
178
- 38
179
- ],
180
- "æ": [
181
- 39
182
- ],
183
- "ç": [
184
- 40
185
- ],
186
- "ð": [
187
- 41
188
- ],
189
- "ø": [
190
- 42
191
- ],
192
- "ħ": [
193
- 43
194
- ],
195
- "ŋ": [
196
- 44
197
- ],
198
- "œ": [
199
- 45
200
- ],
201
- "ǀ": [
202
- 46
203
- ],
204
- "ǁ": [
205
- 47
206
- ],
207
- "ǂ": [
208
- 48
209
- ],
210
- "ǃ": [
211
- 49
212
- ],
213
- "ɐ": [
214
- 50
215
- ],
216
- "ɑ": [
217
- 51
218
- ],
219
- "ɒ": [
220
- 52
221
- ],
222
- "ɓ": [
223
- 53
224
- ],
225
- "ɔ": [
226
- 54
227
- ],
228
- "ɕ": [
229
- 55
230
- ],
231
- "ɖ": [
232
- 56
233
- ],
234
- "ɗ": [
235
- 57
236
- ],
237
- "ɘ": [
238
- 58
239
- ],
240
- "ə": [
241
- 59
242
- ],
243
- "ɚ": [
244
- 60
245
- ],
246
- "ɛ": [
247
- 61
248
- ],
249
- "ɜ": [
250
- 62
251
- ],
252
- "ɞ": [
253
- 63
254
- ],
255
- "ɟ": [
256
- 64
257
- ],
258
- "ɠ": [
259
- 65
260
- ],
261
- "ɡ": [
262
- 66
263
- ],
264
- "ɢ": [
265
- 67
266
- ],
267
- "ɣ": [
268
- 68
269
- ],
270
- "ɤ": [
271
- 69
272
- ],
273
- "ɥ": [
274
- 70
275
- ],
276
- "ɦ": [
277
- 71
278
- ],
279
- "ɧ": [
280
- 72
281
- ],
282
- "ɨ": [
283
- 73
284
- ],
285
- "ɪ": [
286
- 74
287
- ],
288
- "ɫ": [
289
- 75
290
- ],
291
- "ɬ": [
292
- 76
293
- ],
294
- "ɭ": [
295
- 77
296
- ],
297
- "ɮ": [
298
- 78
299
- ],
300
- "ɯ": [
301
- 79
302
- ],
303
- "ɰ": [
304
- 80
305
- ],
306
- "ɱ": [
307
- 81
308
- ],
309
- "ɲ": [
310
- 82
311
- ],
312
- "ɳ": [
313
- 83
314
- ],
315
- "ɴ": [
316
- 84
317
- ],
318
- "ɵ": [
319
- 85
320
- ],
321
- "ɶ": [
322
- 86
323
- ],
324
- "ɸ": [
325
- 87
326
- ],
327
- "ɹ": [
328
- 88
329
- ],
330
- "ɺ": [
331
- 89
332
- ],
333
- "ɻ": [
334
- 90
335
- ],
336
- "ɽ": [
337
- 91
338
- ],
339
- "ɾ": [
340
- 92
341
- ],
342
- "ʀ": [
343
- 93
344
- ],
345
- "ʁ": [
346
- 94
347
- ],
348
- "ʂ": [
349
- 95
350
- ],
351
- "ʃ": [
352
- 96
353
- ],
354
- "ʄ": [
355
- 97
356
- ],
357
- "ʈ": [
358
- 98
359
- ],
360
- "ʉ": [
361
- 99
362
- ],
363
- "ʊ": [
364
- 100
365
- ],
366
- "ʋ": [
367
- 101
368
- ],
369
- "ʌ": [
370
- 102
371
- ],
372
- "ʍ": [
373
- 103
374
- ],
375
- "ʎ": [
376
- 104
377
- ],
378
- "ʏ": [
379
- 105
380
- ],
381
- "ʐ": [
382
- 106
383
- ],
384
- "ʑ": [
385
- 107
386
- ],
387
- "ʒ": [
388
- 108
389
- ],
390
- "ʔ": [
391
- 109
392
- ],
393
- "ʕ": [
394
- 110
395
- ],
396
- "ʘ": [
397
- 111
398
- ],
399
- "ʙ": [
400
- 112
401
- ],
402
- "ʛ": [
403
- 113
404
- ],
405
- "ʜ": [
406
- 114
407
- ],
408
- "ʝ": [
409
- 115
410
- ],
411
- "ʟ": [
412
- 116
413
- ],
414
- "ʡ": [
415
- 117
416
- ],
417
- "ʢ": [
418
- 118
419
- ],
420
- "ʦ": [
421
- 155
422
- ],
423
- "ʰ": [
424
- 145
425
- ],
426
- "ʲ": [
427
- 119
428
- ],
429
- "ˈ": [
430
- 120
431
- ],
432
- "ˌ": [
433
- 121
434
- ],
435
- "ː": [
436
- 122
437
- ],
438
- "ˑ": [
439
- 123
440
- ],
441
- "˞": [
442
- 124
443
- ],
444
- "ˤ": [
445
- 146
446
- ],
447
- "̃": [
448
- 141
449
- ],
450
- "̧": [
451
- 140
452
- ],
453
- "̩": [
454
- 144
455
- ],
456
- "̪": [
457
- 142
458
- ],
459
- "̯": [
460
- 143
461
- ],
462
- "̺": [
463
- 152
464
- ],
465
- "̻": [
466
- 153
467
- ],
468
- "β": [
469
- 125
470
- ],
471
- "ε": [
472
- 147
473
- ],
474
- "θ": [
475
- 126
476
- ],
477
- "χ": [
478
- 127
479
- ],
480
- "ᵻ": [
481
- 128
482
- ],
483
- "↑": [
484
- 151
485
- ],
486
- "↓": [
487
- 148
488
- ],
489
- "ⱱ": [
490
- 129
491
- ]
492
- },
493
- "num_symbols": 256,
494
- "num_speakers": 1,
495
- "speaker_id_map": {},
496
- "piper_version": "1.0.0"
497
- }
 
 
 
 
 
 
1
  {
2
+ "dataset": "priyamvada",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "hi"
9
+ },
10
+ "language": {
11
+ "code": "hi_IN",
12
+ "family": "hi",
13
+ "region": "IN",
14
+ "name_native": "हिन्दी",
15
+ "name_english": "Hindi",
16
+ "country_english": "India"
17
+ },
18
+ "inference": {
19
+ "noise_scale": 0.667,
20
+ "length_scale": 1,
21
+ "noise_w": 0.8
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
+ ],
44
+ "(": [
45
+ 6
46
+ ],
47
+ ")": [
48
+ 7
49
+ ],
50
+ ",": [
51
+ 8
52
+ ],
53
+ "-": [
54
+ 9
55
+ ],
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
+ ],
92
+ ";": [
93
+ 12
94
+ ],
95
+ "?": [
96
+ 13
97
+ ],
98
+ "X": [
99
+ 156
100
+ ],
101
+ "^": [
102
+ 1
103
+ ],
104
+ "_": [
105
+ 0
106
+ ],
107
+ "a": [
108
+ 14
109
+ ],
110
+ "b": [
111
+ 15
112
+ ],
113
+ "c": [
114
+ 16
115
+ ],
116
+ "d": [
117
+ 17
118
+ ],
119
+ "e": [
120
+ 18
121
+ ],
122
+ "f": [
123
+ 19
124
+ ],
125
+ "g": [
126
+ 154
127
+ ],
128
+ "h": [
129
+ 20
130
+ ],
131
+ "i": [
132
+ 21
133
+ ],
134
+ "j": [
135
+ 22
136
+ ],
137
+ "k": [
138
+ 23
139
+ ],
140
+ "l": [
141
+ 24
142
+ ],
143
+ "m": [
144
+ 25
145
+ ],
146
+ "n": [
147
+ 26
148
+ ],
149
+ "o": [
150
+ 27
151
+ ],
152
+ "p": [
153
+ 28
154
+ ],
155
+ "q": [
156
+ 29
157
+ ],
158
+ "r": [
159
+ 30
160
+ ],
161
+ "s": [
162
+ 31
163
+ ],
164
+ "t": [
165
+ 32
166
+ ],
167
+ "u": [
168
+ 33
169
+ ],
170
+ "v": [
171
+ 34
172
+ ],
173
+ "w": [
174
+ 35
175
+ ],
176
+ "x": [
177
+ 36
178
+ ],
179
+ "y": [
180
+ 37
181
+ ],
182
+ "z": [
183
+ 38
184
+ ],
185
+ "æ": [
186
+ 39
187
+ ],
188
+ "ç": [
189
+ 40
190
+ ],
191
+ "ð": [
192
+ 41
193
+ ],
194
+ "ø": [
195
+ 42
196
+ ],
197
+ "ħ": [
198
+ 43
199
+ ],
200
+ "ŋ": [
201
+ 44
202
+ ],
203
+ "œ": [
204
+ 45
205
+ ],
206
+ "ǀ": [
207
+ 46
208
+ ],
209
+ "ǁ": [
210
+ 47
211
+ ],
212
+ "ǂ": [
213
+ 48
214
+ ],
215
+ "ǃ": [
216
+ 49
217
+ ],
218
+ "ɐ": [
219
+ 50
220
+ ],
221
+ "ɑ": [
222
+ 51
223
+ ],
224
+ "ɒ": [
225
+ 52
226
+ ],
227
+ "ɓ": [
228
+ 53
229
+ ],
230
+ "ɔ": [
231
+ 54
232
+ ],
233
+ "ɕ": [
234
+ 55
235
+ ],
236
+ "ɖ": [
237
+ 56
238
+ ],
239
+ "ɗ": [
240
+ 57
241
+ ],
242
+ "ɘ": [
243
+ 58
244
+ ],
245
+ "ə": [
246
+ 59
247
+ ],
248
+ "ɚ": [
249
+ 60
250
+ ],
251
+ "ɛ": [
252
+ 61
253
+ ],
254
+ "ɜ": [
255
+ 62
256
+ ],
257
+ "ɞ": [
258
+ 63
259
+ ],
260
+ "ɟ": [
261
+ 64
262
+ ],
263
+ "ɠ": [
264
+ 65
265
+ ],
266
+ "ɡ": [
267
+ 66
268
+ ],
269
+ "ɢ": [
270
+ 67
271
+ ],
272
+ "ɣ": [
273
+ 68
274
+ ],
275
+ "ɤ": [
276
+ 69
277
+ ],
278
+ "ɥ": [
279
+ 70
280
+ ],
281
+ "ɦ": [
282
+ 71
283
+ ],
284
+ "ɧ": [
285
+ 72
286
+ ],
287
+ "ɨ": [
288
+ 73
289
+ ],
290
+ "ɪ": [
291
+ 74
292
+ ],
293
+ "ɫ": [
294
+ 75
295
+ ],
296
+ "ɬ": [
297
+ 76
298
+ ],
299
+ "ɭ": [
300
+ 77
301
+ ],
302
+ "ɮ": [
303
+ 78
304
+ ],
305
+ "ɯ": [
306
+ 79
307
+ ],
308
+ "ɰ": [
309
+ 80
310
+ ],
311
+ "ɱ": [
312
+ 81
313
+ ],
314
+ "ɲ": [
315
+ 82
316
+ ],
317
+ "ɳ": [
318
+ 83
319
+ ],
320
+ "ɴ": [
321
+ 84
322
+ ],
323
+ "ɵ": [
324
+ 85
325
+ ],
326
+ "ɶ": [
327
+ 86
328
+ ],
329
+ "ɸ": [
330
+ 87
331
+ ],
332
+ "ɹ": [
333
+ 88
334
+ ],
335
+ "ɺ": [
336
+ 89
337
+ ],
338
+ "ɻ": [
339
+ 90
340
+ ],
341
+ "ɽ": [
342
+ 91
343
+ ],
344
+ "ɾ": [
345
+ 92
346
+ ],
347
+ "ʀ": [
348
+ 93
349
+ ],
350
+ "ʁ": [
351
+ 94
352
+ ],
353
+ "ʂ": [
354
+ 95
355
+ ],
356
+ "ʃ": [
357
+ 96
358
+ ],
359
+ "ʄ": [
360
+ 97
361
+ ],
362
+ "ʈ": [
363
+ 98
364
+ ],
365
+ "ʉ": [
366
+ 99
367
+ ],
368
+ "ʊ": [
369
+ 100
370
+ ],
371
+ "ʋ": [
372
+ 101
373
+ ],
374
+ "ʌ": [
375
+ 102
376
+ ],
377
+ "ʍ": [
378
+ 103
379
+ ],
380
+ "ʎ": [
381
+ 104
382
+ ],
383
+ "ʏ": [
384
+ 105
385
+ ],
386
+ "ʐ": [
387
+ 106
388
+ ],
389
+ "ʑ": [
390
+ 107
391
+ ],
392
+ "ʒ": [
393
+ 108
394
+ ],
395
+ "ʔ": [
396
+ 109
397
+ ],
398
+ "ʕ": [
399
+ 110
400
+ ],
401
+ "ʘ": [
402
+ 111
403
+ ],
404
+ "ʙ": [
405
+ 112
406
+ ],
407
+ "ʛ": [
408
+ 113
409
+ ],
410
+ "ʜ": [
411
+ 114
412
+ ],
413
+ "ʝ": [
414
+ 115
415
+ ],
416
+ "ʟ": [
417
+ 116
418
+ ],
419
+ "ʡ": [
420
+ 117
421
+ ],
422
+ "ʢ": [
423
+ 118
424
+ ],
425
+ "ʦ": [
426
+ 155
427
+ ],
428
+ "ʰ": [
429
+ 145
430
+ ],
431
+ "ʲ": [
432
+ 119
433
+ ],
434
+ "ˈ": [
435
+ 120
436
+ ],
437
+ "ˌ": [
438
+ 121
439
+ ],
440
+ "ː": [
441
+ 122
442
+ ],
443
+ "ˑ": [
444
+ 123
445
+ ],
446
+ "˞": [
447
+ 124
448
+ ],
449
+ "ˤ": [
450
+ 146
451
+ ],
452
+ "̃": [
453
+ 141
454
+ ],
455
+ "̧": [
456
+ 140
457
+ ],
458
+ "̩": [
459
+ 144
460
+ ],
461
+ "̪": [
462
+ 142
463
+ ],
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
+ "ᵻ": [
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
+ }
hi/hi_IN/priyamvada/medium/samples/{test_f.wav → speaker_0.mp3} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b980960bbbe4b36db19e97eec54580b274033a4d54a947015d1a262b750371b
3
- size 270892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b64364b95d56ce84ccd5a663b9b42fdae094fe0ff1e37544a92b7e9aa8dd770
3
+ size 423372
hi/hi_IN/priyamvada/medium/samples/test1_f.wav DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:077ebe234ba85ef01d1f19e6c7eb6ca97dacf3ae03f69c867075b4d0d9e83c9a
3
- size 2467372
 
 
 
 
voices.json CHANGED
@@ -4791,6 +4791,66 @@
4791
  },
4792
  "aliases": []
4793
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4794
  "hu_HU-anna-medium": {
4795
  "key": "hu_HU-anna-medium",
4796
  "name": "anna",
 
4791
  },
4792
  "aliases": []
4793
  },
4794
+ "hi_IN-pratham-medium": {
4795
+ "key": "hi_IN-pratham-medium",
4796
+ "name": "pratham",
4797
+ "language": {
4798
+ "code": "hi_IN",
4799
+ "family": "hi",
4800
+ "region": "IN",
4801
+ "name_native": "हिन्दी",
4802
+ "name_english": "Hindi",
4803
+ "country_english": "India"
4804
+ },
4805
+ "quality": "medium",
4806
+ "num_speakers": 1,
4807
+ "speaker_id_map": {},
4808
+ "files": {
4809
+ "hi/hi_IN/pratham/medium/hi_IN-pratham-medium.onnx": {
4810
+ "size_bytes": 63516050,
4811
+ "md5_digest": "f1e5a629a9e533a7155910530109eb86"
4812
+ },
4813
+ "hi/hi_IN/pratham/medium/hi_IN-pratham-medium.onnx.json": {
4814
+ "size_bytes": 4970,
4815
+ "md5_digest": "ab655cdad90f1939f00d1b3aaf440e99"
4816
+ },
4817
+ "hi/hi_IN/pratham/medium/MODEL_CARD": {
4818
+ "size_bytes": 304,
4819
+ "md5_digest": "eccc77c3d857a883e85c52cb17653c1f"
4820
+ }
4821
+ },
4822
+ "aliases": []
4823
+ },
4824
+ "hi_IN-priyamvada-medium": {
4825
+ "key": "hi_IN-priyamvada-medium",
4826
+ "name": "priyamvada",
4827
+ "language": {
4828
+ "code": "hi_IN",
4829
+ "family": "hi",
4830
+ "region": "IN",
4831
+ "name_native": "हिन्दी",
4832
+ "name_english": "Hindi",
4833
+ "country_english": "India"
4834
+ },
4835
+ "quality": "medium",
4836
+ "num_speakers": 1,
4837
+ "speaker_id_map": {},
4838
+ "files": {
4839
+ "hi/hi_IN/priyamvada/medium/hi_IN-priyamvada-medium.onnx": {
4840
+ "size_bytes": 63516050,
4841
+ "md5_digest": "7d5e20c2d1e72de8ed772f222e679626"
4842
+ },
4843
+ "hi/hi_IN/priyamvada/medium/hi_IN-priyamvada-medium.onnx.json": {
4844
+ "size_bytes": 4973,
4845
+ "md5_digest": "599ca4dc5d421a9c66692433f618e080"
4846
+ },
4847
+ "hi/hi_IN/priyamvada/medium/MODEL_CARD": {
4848
+ "size_bytes": 307,
4849
+ "md5_digest": "e2b745cf97087be0a97c7f10215bfa70"
4850
+ }
4851
+ },
4852
+ "aliases": []
4853
+ },
4854
  "hu_HU-anna-medium": {
4855
  "key": "hu_HU-anna-medium",
4856
  "name": "anna",