Hugging Face's logo

rhasspy
/
piper-voices

ONNX
Model card Files
xet
 Community
98

htoc

#74
by hanktiong - opened
base: refs/heads/main
←
from: refs/pr/74
Discussion Files changed
+27
-10142
This view is limited to 50 files because it contains too many changes. See the raw diff here.
Files changed (50) hide show
  1. _script/voicefest.py +4 -10
  2. bn/bn_BD/google/medium/MODEL_CARD +0 -48
  3. bn/bn_BD/google/medium/bn_BD-google-medium.onnx +0 -3
  4. bn/bn_BD/google/medium/bn_BD-google-medium.onnx.json +0 -546
  5. bn/bn_BD/google/medium/samples/speaker_0.mp3 +0 -3
  6. bn/bn_BD/google/medium/samples/speaker_1.mp3 +0 -3
  7. bn/bn_BD/google/medium/samples/speaker_10.mp3 +0 -3
  8. bn/bn_BD/google/medium/samples/speaker_11.mp3 +0 -3
  9. bn/bn_BD/google/medium/samples/speaker_12.mp3 +0 -3
  10. bn/bn_BD/google/medium/samples/speaker_13.mp3 +0 -3
  11. bn/bn_BD/google/medium/samples/speaker_14.mp3 +0 -3
  12. bn/bn_BD/google/medium/samples/speaker_15.mp3 +0 -3
  13. bn/bn_BD/google/medium/samples/speaker_2.mp3 +0 -3
  14. bn/bn_BD/google/medium/samples/speaker_3.mp3 +0 -3
  15. bn/bn_BD/google/medium/samples/speaker_4.mp3 +0 -3
  16. bn/bn_BD/google/medium/samples/speaker_5.mp3 +0 -3
  17. bn/bn_BD/google/medium/samples/speaker_6.mp3 +0 -3
  18. bn/bn_BD/google/medium/samples/speaker_7.mp3 +0 -3
  19. bn/bn_BD/google/medium/samples/speaker_8.mp3 +0 -3
  20. bn/bn_BD/google/medium/samples/speaker_9.mp3 +0 -3
  21. cs/cs_CZ/jirka/low/MODEL_CARD +1 -1
  22. cs/cs_CZ/kasandra/medium/MODEL_CARD +0 -16
  23. cs/cs_CZ/kasandra/medium/cs_CZ-kasandra-medium.onnx +0 -3
  24. cs/cs_CZ/kasandra/medium/cs_CZ-kasandra-medium.onnx.json +0 -195
  25. cs/cs_CZ/kasandra/medium/samples/speaker_0.mp3 +0 -3
  26. de/de_DE/thorsten/high/MODEL_CARD +1 -1
  27. el/el_GR/joy/medium/MODEL_CARD +0 -16
  28. el/el_GR/joy/medium/el_GR-joy-medium.onnx +0 -3
  29. el/el_GR/joy/medium/el_GR-joy-medium.onnx.json +0 -509
  30. el/el_GR/joy/medium/samples/speaker_0.mp3 +0 -3
  31. en/en_US/amy/medium/MODEL_CARD +1 -1
  32. en/en_US/ljspeech/high/MODEL_CARD +1 -1
  33. en/en_US/mike/medium/MODEL_CARD +0 -15
  34. en/en_US/mike/medium/en_US-mike-medium.onnx +0 -3
  35. en/en_US/mike/medium/en_US-mike-medium.onnx.json +0 -551
  36. en/en_US/mike/medium/samples/speaker_0.mp3 +0 -3
  37. es/es_AR/daniela/high/MODEL_CARD +1 -1
  38. es/es_MX/ald/x_low/MODEL_CARD +0 -19
  39. es/es_MX/ald/x_low/es_MX-ald-x_low.onnx +0 -3
  40. es/es_MX/ald/x_low/es_MX-ald-x_low.onnx.json +0 -493
  41. es/es_MX/ald/x_low/samples/speaker_0.mp3 +0 -3
  42. et/et_EE/news/medium/MODEL_CARD +0 -16
  43. et/et_EE/news/medium/et_EE-news-medium.onnx +0 -3
  44. et/et_EE/news/medium/et_EE-news-medium.onnx.json +0 -535
  45. et/et_EE/news/medium/samples/speaker_0.mp3 +0 -3
  46. et/et_EE/news/medium/samples/speaker_1.mp3 +0 -3
  47. et/et_EE/news/medium/samples/speaker_2.mp3 +0 -3
  48. et/et_EE/news/medium/samples/speaker_3.mp3 +0 -3
  49. he/he_IL/saspeech/medium/MODEL_CARD +0 -15
  50. he/he_IL/saspeech/medium/he_IL-saspeech-medium.onnx +0 -3
_script/voicefest.py CHANGED
@@ -20,7 +20,6 @@ class Language:
20
  _LANGUAGES = {
21
  "ar_JO": Language("العربية", "Arabic", "Jordan"),
22
  "bg_BG": Language("български", "Bulgarian", "Bulgaria"),
23
- "bn_BD": Language("বাংলা", "Bengali", "Bangladesh"),
24
  "ca_ES": Language("Català", "Catalan", "Spain"),
25
  "cs_CZ": Language("Čeština", "Czech", "Czech Republic"),
26
  "cy_GB": Language("Cymraeg", "Welsh", "Great Britain"),
@@ -32,31 +31,26 @@ _LANGUAGES = {
32
  "es_AR": Language("Español", "Spanish", "Argentina"),
33
  "es_ES": Language("Español", "Spanish", "Spain"),
34
  "es_MX": Language("Español", "Spanish", "Mexico"),
35
- "et_EE": Language("eesti", "Estonian", "Estonia"),
36
  "eu_ES": Language("Euskara", "Basque", "Spain"),
37
  "fa_IR": Language("فارسی", "Farsi", "Iran"),
38
  "fi_FI": Language("Suomi", "Finnish", "Finland"),
39
  "fr_FR": Language("Français", "French", "France"),
40
- "he_IL": Language("עִבְרִית‎", "Hebrew", "Israel"),
41
  "hi_IN": Language("हिन्दी", "Hindi", "India"),
42
- "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
43
- "hy_AM": Language("հայերեն", "Armenian", "Armenia"),
44
  "id_ID": Language("Bahasa Indonesia", "Indonesian", "Indonesia"),
45
- "is_IS": Language("íslenska", "Icelandic", "Iceland"),
46
  "it_IT": Language("Italiano", "Italian", "Italy"),
47
- "ja_JA": Language("日本語", "Japanese", "Japan"),
 
48
  "ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
49
  "kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
50
- "ko_KR": Language("한국어", "Korean", "South Korea"),
51
  "ku_TR": Language("Kurmancî", "Kurmanji Kurdish", "Turkey"),
52
  "lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
53
  "lv_LV": Language("Latviešu", "Latvian", "Latvia"),
54
- "ml_IN": Language("മലയാളം", "Malayalam", "India"),
55
- "mr_IN": Language("मराठी, 𑘦𑘨𑘰𑘙𑘲", "Marathi", "India"),
56
  "ne_NP": Language("नेपाली", "Nepali", "Nepal"),
57
  "nl_BE": Language("Nederlands", "Dutch", "Belgium"),
58
  "nl_NL": Language("Nederlands", "Dutch", "Netherlands"),
59
  "no_NO": Language("Norsk", "Norwegian", "Norway"),
 
60
  "pl_PL": Language("Polski", "Polish", "Poland"),
61
  "pt_BR": Language("Português", "Portuguese", "Brazil"),
62
  "pt_PT": Language("Português", "Portuguese", "Portugal"),
 
20
  _LANGUAGES = {
21
  "ar_JO": Language("العربية", "Arabic", "Jordan"),
22
  "bg_BG": Language("български", "Bulgarian", "Bulgaria"),
 
23
  "ca_ES": Language("Català", "Catalan", "Spain"),
24
  "cs_CZ": Language("Čeština", "Czech", "Czech Republic"),
25
  "cy_GB": Language("Cymraeg", "Welsh", "Great Britain"),
 
31
  "es_AR": Language("Español", "Spanish", "Argentina"),
32
  "es_ES": Language("Español", "Spanish", "Spain"),
33
  "es_MX": Language("Español", "Spanish", "Mexico"),
 
34
  "eu_ES": Language("Euskara", "Basque", "Spain"),
35
  "fa_IR": Language("فارسی", "Farsi", "Iran"),
36
  "fi_FI": Language("Suomi", "Finnish", "Finland"),
37
  "fr_FR": Language("Français", "French", "France"),
38
+ "is_IS": Language("íslenska", "Icelandic", "Iceland"),
39
  "hi_IN": Language("हिन्दी", "Hindi", "India"),
 
 
40
  "id_ID": Language("Bahasa Indonesia", "Indonesian", "Indonesia"),
 
41
  "it_IT": Language("Italiano", "Italian", "Italy"),
42
+ "he_IL": Language("עברית", "Hebrew", "Israel"),
43
+ "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
44
  "ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
45
  "kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
 
46
  "ku_TR": Language("Kurmancî", "Kurmanji Kurdish", "Turkey"),
47
  "lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
48
  "lv_LV": Language("Latviešu", "Latvian", "Latvia"),
 
 
49
  "ne_NP": Language("नेपाली", "Nepali", "Nepal"),
50
  "nl_BE": Language("Nederlands", "Dutch", "Belgium"),
51
  "nl_NL": Language("Nederlands", "Dutch", "Netherlands"),
52
  "no_NO": Language("Norsk", "Norwegian", "Norway"),
53
+ "ml_IN": Language("മലയാളം", "Malayalam", "India"),
54
  "pl_PL": Language("Polski", "Polish", "Poland"),
55
  "pt_BR": Language("Português", "Portuguese", "Brazil"),
56
  "pt_PT": Language("Português", "Portuguese", "Portugal"),
bn/bn_BD/google/medium/MODEL_CARD DELETED
@@ -1,48 +0,0 @@
1
- # Model card for google (medium)
2
-
3
- * Language: bn_BD (Bengali, Bangladesh), bn_IN (Bengali, India)
4
- * Speakers: 16
5
- * Quality: medium
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- * URL: http://www.openslr.org/37/
11
- * License: Attribution-ShareAlike 4.0 International
12
- * URL: http://festvox.org/cmu_indic/index.html
13
- * License: See CMU License below
14
-
15
- ## Training
16
-
17
- Finetuned from LibriTTS-R voice (medium quality)
18
-
19
- ## CMU License
20
-
21
- Language Technologies Institute
22
- Carnegie Mellon University
23
- Copyright (c) 2009-2017
24
- All Rights Reserved.
25
-
26
- Permission is hereby granted, free of charge, to use and distribute
27
- this data, software and its documentation without restriction, including
28
- without limitation the rights to use, copy, modify, merge, publish,
29
- distribute, sublicense, and/or sell copies of this work, and to
30
- permit persons to whom this work is furnished to do so, subject to
31
- the following conditions:
32
- 1. The code must retain the above copyright notice, this list of
33
- conditions and the following disclaimer.
34
- 2. Any modifications must be clearly marked as such.
35
- 3. Original authors' names are not deleted.
36
- 4. The authors' names are not used to endorse or promote products
37
- derived from this software without specific prior written
38
- permission.
39
-
40
- CARNEGIE MELLON UNIVERSITY AND THE CONTRIBUTORS TO THIS WORK
41
- DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING
42
- ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT
43
- SHALL CARNEGIE MELLON UNIVERSITY NOR THE CONTRIBUTORS BE LIABLE
44
- FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
45
- WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
46
- AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
47
- ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
48
- THIS SOFTWARE.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bn/bn_BD/google/medium/bn_BD-google-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2e7518ed5534a755024a48c71b80bf617efaf12570bbdf3ce255a9526a8afd3
3
- size 76782515
 
 
 
 
bn/bn_BD/google/medium/bn_BD-google-medium.onnx.json DELETED
@@ -1,546 +0,0 @@
1
- {
2
- "audio": {
3
- "sample_rate": 22050,
4
- "quality": "medium"
5
- },
6
- "espeak": {
7
- "voice": "bn"
8
- },
9
- "phoneme_type": "espeak",
10
- "num_symbols": 256,
11
- "num_speakers": 16,
12
- "inference": {
13
- "noise_scale": 0.667,
14
- "length_scale": 1.0,
15
- "noise_w": 0.8
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
- ],
36
- "(": [
37
- 6
38
- ],
39
- ")": [
40
- 7
41
- ],
42
- ",": [
43
- 8
44
- ],
45
- "-": [
46
- 9
47
- ],
48
- ".": [
49
- 10
50
- ],
51
- ":": [
52
- 11
53
- ],
54
- ";": [
55
- 12
56
- ],
57
- "?": [
58
- 13
59
- ],
60
- "a": [
61
- 14
62
- ],
63
- "b": [
64
- 15
65
- ],
66
- "c": [
67
- 16
68
- ],
69
- "d": [
70
- 17
71
- ],
72
- "e": [
73
- 18
74
- ],
75
- "f": [
76
- 19
77
- ],
78
- "h": [
79
- 20
80
- ],
81
- "i": [
82
- 21
83
- ],
84
- "j": [
85
- 22
86
- ],
87
- "k": [
88
- 23
89
- ],
90
- "l": [
91
- 24
92
- ],
93
- "m": [
94
- 25
95
- ],
96
- "n": [
97
- 26
98
- ],
99
- "o": [
100
- 27
101
- ],
102
- "p": [
103
- 28
104
- ],
105
- "q": [
106
- 29
107
- ],
108
- "r": [
109
- 30
110
- ],
111
- "s": [
112
- 31
113
- ],
114
- "t": [
115
- 32
116
- ],
117
- "u": [
118
- 33
119
- ],
120
- "v": [
121
- 34
122
- ],
123
- "w": [
124
- 35
125
- ],
126
- "x": [
127
- 36
128
- ],
129
- "y": [
130
- 37
131
- ],
132
- "z": [
133
- 38
134
- ],
135
- "æ": [
136
- 39
137
- ],
138
- "ç": [
139
- 40
140
- ],
141
- "ð": [
142
- 41
143
- ],
144
- "ø": [
145
- 42
146
- ],
147
- "ħ": [
148
- 43
149
- ],
150
- "ŋ": [
151
- 44
152
- ],
153
- "œ": [
154
- 45
155
- ],
156
- "ǀ": [
157
- 46
158
- ],
159
- "ǁ": [
160
- 47
161
- ],
162
- "ǂ": [
163
- 48
164
- ],
165
- "ǃ": [
166
- 49
167
- ],
168
- "ɐ": [
169
- 50
170
- ],
171
- "ɑ": [
172
- 51
173
- ],
174
- "ɒ": [
175
- 52
176
- ],
177
- "ɓ": [
178
- 53
179
- ],
180
- "ɔ": [
181
- 54
182
- ],
183
- "ɕ": [
184
- 55
185
- ],
186
- "ɖ": [
187
- 56
188
- ],
189
- "ɗ": [
190
- 57
191
- ],
192
- "ɘ": [
193
- 58
194
- ],
195
- "ə": [
196
- 59
197
- ],
198
- "ɚ": [
199
- 60
200
- ],
201
- "ɛ": [
202
- 61
203
- ],
204
- "ɜ": [
205
- 62
206
- ],
207
- "ɞ": [
208
- 63
209
- ],
210
- "ɟ": [
211
- 64
212
- ],
213
- "ɠ": [
214
- 65
215
- ],
216
- "ɡ": [
217
- 66
218
- ],
219
- "ɢ": [
220
- 67
221
- ],
222
- "ɣ": [
223
- 68
224
- ],
225
- "ɤ": [
226
- 69
227
- ],
228
- "ɥ": [
229
- 70
230
- ],
231
- "ɦ": [
232
- 71
233
- ],
234
- "ɧ": [
235
- 72
236
- ],
237
- "ɨ": [
238
- 73
239
- ],
240
- "ɪ": [
241
- 74
242
- ],
243
- "ɫ": [
244
- 75
245
- ],
246
- "ɬ": [
247
- 76
248
- ],
249
- "ɭ": [
250
- 77
251
- ],
252
- "ɮ": [
253
- 78
254
- ],
255
- "ɯ": [
256
- 79
257
- ],
258
- "ɰ": [
259
- 80
260
- ],
261
- "ɱ": [
262
- 81
263
- ],
264
- "ɲ": [
265
- 82
266
- ],
267
- "ɳ": [
268
- 83
269
- ],
270
- "ɴ": [
271
- 84
272
- ],
273
- "ɵ": [
274
- 85
275
- ],
276
- "ɶ": [
277
- 86
278
- ],
279
- "ɸ": [
280
- 87
281
- ],
282
- "ɹ": [
283
- 88
284
- ],
285
- "ɺ": [
286
- 89
287
- ],
288
- "ɻ": [
289
- 90
290
- ],
291
- "ɽ": [
292
- 91
293
- ],
294
- "ɾ": [
295
- 92
296
- ],
297
- "ʀ": [
298
- 93
299
- ],
300
- "ʁ": [
301
- 94
302
- ],
303
- "ʂ": [
304
- 95
305
- ],
306
- "ʃ": [
307
- 96
308
- ],
309
- "ʄ": [
310
- 97
311
- ],
312
- "ʈ": [
313
- 98
314
- ],
315
- "ʉ": [
316
- 99
317
- ],
318
- "ʊ": [
319
- 100
320
- ],
321
- "ʋ": [
322
- 101
323
- ],
324
- "ʌ": [
325
- 102
326
- ],
327
- "ʍ": [
328
- 103
329
- ],
330
- "ʎ": [
331
- 104
332
- ],
333
- "ʏ": [
334
- 105
335
- ],
336
- "ʐ": [
337
- 106
338
- ],
339
- "ʑ": [
340
- 107
341
- ],
342
- "ʒ": [
343
- 108
344
- ],
345
- "ʔ": [
346
- 109
347
- ],
348
- "ʕ": [
349
- 110
350
- ],
351
- "ʘ": [
352
- 111
353
- ],
354
- "ʙ": [
355
- 112
356
- ],
357
- "ʛ": [
358
- 113
359
- ],
360
- "ʜ": [
361
- 114
362
- ],
363
- "ʝ": [
364
- 115
365
- ],
366
- "ʟ": [
367
- 116
368
- ],
369
- "ʡ": [
370
- 117
371
- ],
372
- "ʢ": [
373
- 118
374
- ],
375
- "ʲ": [
376
- 119
377
- ],
378
- "ˈ": [
379
- 120
380
- ],
381
- "ˌ": [
382
- 121
383
- ],
384
- "ː": [
385
- 122
386
- ],
387
- "ˑ": [
388
- 123
389
- ],
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
446
- ],
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
- "00737": 0,
519
- "01232": 1,
520
- "02194": 2,
521
- "03042": 3,
522
- "00779": 4,
523
- "01701": 5,
524
- "0834": 6,
525
- "1010": 7,
526
- "3108": 8,
527
- "3713": 9,
528
- "3958": 10,
529
- "4046": 11,
530
- "4811": 12,
531
- "5958": 13,
532
- "9169": 14,
533
- "rm": 15
534
- },
535
- "hop_length": 256,
536
- "piper_version": "1.5.0",
537
- "language": {
538
- "code": "bn_BD",
539
- "family": "bn",
540
- "region": "BD",
541
- "name_native": "বাংলা",
542
- "name_english": "Bengali",
543
- "country_english": "Bangladesh"
544
- },
545
- "dataset": "google"
546
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac6eec2094c9286b60a2fb1b7f41c310d5315620c1f84a9a9f343f3300c367d
3
- size 276454
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_1.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15a8976115d50e56af8a1c346cbe437ceba268583fd02812dbf97f8ea958f83d
3
- size 301282
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_10.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4168fafe7a33ae992867131cd844581e36774dce0b6e1e5a7488657a00c60cf
3
- size 261238
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_11.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:02db7ee9a208a056a9b4d62bab5e93c44c140c0959ee60c0a9f022c48ed3828f
3
- size 332218
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_12.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:25069f9a52e7b1a08ed746b65453f7f256f46ed70e252f64d28056322ef0758d
3
- size 364938
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_13.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7b3d4c5ca0cff6dca70726411287da597a3905b7b2e475b18c3ac5c65531109
3
- size 369356
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_14.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cf69707d2c685b86209f3e32be55cf31a72570e4ffa2a75d05ddeddc317ac8f
3
- size 352038
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_15.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:757ff9b6633f44ecbabe31003b875a05ac6ceb8f1516db51eb4ff162aee70c70
3
- size 426621
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_2.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4556b26ae2283bbd7708b64158d7ed49b3cafda9dbac6dba7bdd7336a8ce5082
3
- size 320616
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_3.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f49f24988b2937044f0ad20d08bbcb09020d59da1a5ae775802693719d054be7
3
- size 351591
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_4.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc4bcf003942bfb60a4f1a6a089cf04371cad43352f8f62433b429d6b3fff825
3
- size 317130
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_5.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadc2197da358c5474464474f1d92c905071ad25dc167541ccd0c015ffa141f7
3
- size 321238
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_6.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b98ff7322e79893c033bb462a4de88dee700e02f504282dd4b44647a0ef3174
3
- size 321880
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_7.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f761df0962b6a66186ee74d159c48ff37a67040bb9d8879b842f021c01b3060
3
- size 283064
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_8.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:50cbc9b383bb308f93cf014c68ca7c15cde426be211afe09afe08bf4e7084cca
3
- size 315686
 
 
 
 
bn/bn_BD/google/medium/samples/speaker_9.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2280036b5f133d163ba27280c1fdede0d923fa4437ea3a11e00611e1785dbab3
3
- size 351962
 
 
 
 
cs/cs_CZ/jirka/low/MODEL_CARD CHANGED
@@ -2,7 +2,7 @@
2
 
3
  * Language: cs_CZ (Czech, Czech Republic)
4
  * Speakers: 1
5
- * Quality: low
6
  * Samplerate: 16,000Hz
7
 
8
  ## Dataset
 
2
 
3
  * Language: cs_CZ (Czech, Czech Republic)
4
  * Speakers: 1
5
+ * Quality: medium
6
  * Samplerate: 16,000Hz
7
 
8
  ## Dataset
cs/cs_CZ/kasandra/medium/MODEL_CARD DELETED
@@ -1,16 +0,0 @@
1
- # Model card for kasandra (medium)
2
-
3
- * Language: cs_CZ (Czech, Czech Republic)
4
- * Speakers: 1
5
- * Quality: medium
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- * Author: Ondřej Šimek
11
- * URL: https://huggingface.co/ondrazarici/Cassandra-Kasandra-piper-cz
12
- * License: Creative Commons Attribution 4.0 International (CC BY 4.0)
13
-
14
- ## Training
15
-
16
- The voice model was trained using my own original recordings, and I own the rights to the dataset.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cs/cs_CZ/kasandra/medium/cs_CZ-kasandra-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:09d08aa23691ed2d53fb3db242cfe82b189adf9c1812dd5fe928b5789ed76df7
3
- size 63511038
 
 
 
 
cs/cs_CZ/kasandra/medium/cs_CZ-kasandra-medium.onnx.json DELETED
@@ -1,195 +0,0 @@
1
- {
2
- "dataset": "kasandra",
3
- "audio": {
4
- "sample_rate": 22050,
5
- "quality": "medium"
6
- },
7
- "espeak": {
8
- "voice": "cs"
9
- },
10
- "language": {
11
- "code": "cs_CZ",
12
- "family": "cs",
13
- "region": "CZ",
14
- "name_native": "Čeština",
15
- "name_english": "Czech",
16
- "country_english": "Czech Republic"
17
- },
18
- "inference": {
19
- "noise_scale": 0.667,
20
- "length_scale": 1.2,
21
- "noise_w": 0.8
22
- },
23
- "phoneme_type": "espeak",
24
- "phoneme_map": {},
25
- "phoneme_id_map": {
26
- " ": [3],
27
- "!": [4],
28
- "\"": [150],
29
- "#": [149],
30
- "$": [2],
31
- "'": [5],
32
- "(": [6],
33
- ")": [7],
34
- ",": [8],
35
- "-": [9],
36
- ".": [10],
37
- "0": [130],
38
- "1": [131],
39
- "2": [132],
40
- "3": [133],
41
- "4": [134],
42
- "5": [135],
43
- "6": [136],
44
- "7": [137],
45
- "8": [138],
46
- "9": [139],
47
- ":": [11],
48
- ";": [12],
49
- "?": [13],
50
- "X": [156],
51
- "^": [1],
52
- "_": [0],
53
- "a": [14],
54
- "b": [15],
55
- "c": [16],
56
- "d": [17],
57
- "e": [18],
58
- "f": [19],
59
- "g": [154],
60
- "h": [20],
61
- "i": [21],
62
- "j": [22],
63
- "k": [23],
64
- "l": [24],
65
- "m": [25],
66
- "n": [26],
67
- "o": [27],
68
- "p": [28],
69
- "q": [29],
70
- "r": [30],
71
- "s": [31],
72
- "t": [32],
73
- "u": [33],
74
- "v": [34],
75
- "w": [35],
76
- "x": [36],
77
- "y": [37],
78
- "z": [38],
79
- "æ": [39],
80
- "ç": [40],
81
- "ð": [41],
82
- "ø": [42],
83
- "ħ": [43],
84
- "ŋ": [44],
85
- "œ": [45],
86
- "ǀ": [46],
87
- "ǁ": [47],
88
- "ǂ": [48],
89
- "ǃ": [49],
90
- "ɐ": [50],
91
- "ɑ": [51],
92
- "ɒ": [52],
93
- "ɓ": [53],
94
- "ɔ": [54],
95
- "ɕ": [55],
96
- "ɖ": [56],
97
- "ɗ": [57],
98
- "ɘ": [58],
99
- "ə": [59],
100
- "ɚ": [60],
101
- "ɛ": [61],
102
- "ɜ": [62],
103
- "ɞ": [63],
104
- "ɟ": [64],
105
- "ɠ": [65],
106
- "ɡ": [66],
107
- "ɢ": [67],
108
- "ɣ": [68],
109
- "ɤ": [69],
110
- "ɥ": [70],
111
- "ɦ": [71],
112
- "ɧ": [72],
113
- "ɨ": [73],
114
- "ɪ": [74],
115
- "ɫ": [75],
116
- "ɬ": [76],
117
- "ɭ": [77],
118
- "ɮ": [78],
119
- "ɯ": [79],
120
- "ɰ": [80],
121
- "ɱ": [81],
122
- "ɲ": [82],
123
- "ɳ": [83],
124
- "ɴ": [84],
125
- "ɵ": [85],
126
- "ɶ": [86],
127
- "ɸ": [87],
128
- "ɹ": [88],
129
- "ɺ": [89],
130
- "ɻ": [90],
131
- "ɽ": [91],
132
- "ɾ": [92],
133
- "ʀ": [93],
134
- "ʁ": [94],
135
- "ʂ": [95],
136
- "ʃ": [96],
137
- "ʄ": [97],
138
- "ʈ": [98],
139
- "ʉ": [99],
140
- "ʊ": [100],
141
- "ʋ": [101],
142
- "ʌ": [102],
143
- "ʍ": [103],
144
- "ʎ": [104],
145
- "ʏ": [105],
146
- "ʐ": [106],
147
- "ʑ": [107],
148
- "ʒ": [108],
149
- "ʔ": [109],
150
- "ʕ": [110],
151
- "ʘ": [111],
152
- "ʙ": [112],
153
- "ʛ": [113],
154
- "ʜ": [114],
155
- "ʝ": [115],
156
- "ʟ": [116],
157
- "ʡ": [117],
158
- "ʢ": [118],
159
- "ʦ": [155],
160
- "ʰ": [145],
161
- "ʲ": [119],
162
- "ˈ": [120],
163
- "ˌ": [121],
164
- "ː": [122],
165
- "ˑ": [123],
166
- "˞": [124],
167
- "ˤ": [146],
168
- "̃": [141],
169
- "̊": [158],
170
- "̝": [157],
171
- "̧": [140],
172
- "̩": [144],
173
- "̪": [142],
174
- "̯": [143],
175
- "̺": [152],
176
- "̻": [153],
177
- "β": [125],
178
- "ε": [147],
179
- "θ": [126],
180
- "χ": [127],
181
- "ᵻ": [128],
182
- "↑": [151],
183
- "↓": [148],
184
- "ⱱ": [129]
185
- },
186
- "num_symbols": 256,
187
- "num_speakers": 1,
188
- "speaker_id_map": {},
189
- "piper_version": "1.0.0",
190
- "metadata": {
191
- "author": "Ondřej Šimek",
192
- "project": "Kasandra",
193
- "version": "©2026 v2.0"
194
- }
195
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cs/cs_CZ/kasandra/medium/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9632f2f542f32835c412af3b6cb1bda1526eff8533cefd1f9de7d385a0148652
3
- size 106887
 
 
 
 
de/de_DE/thorsten/high/MODEL_CARD CHANGED
@@ -2,7 +2,7 @@
2
 
3
  * Language: de_DE (German, Germany)
4
  * Speakers: 1
5
- * Quality: high
6
  * Samplerate: 22,050Hz
7
 
8
  ## Dataset
 
2
 
3
  * Language: de_DE (German, Germany)
4
  * Speakers: 1
5
+ * Quality: medium
6
  * Samplerate: 22,050Hz
7
 
8
  ## Dataset
el/el_GR/joy/medium/MODEL_CARD DELETED
@@ -1,16 +0,0 @@
1
- # Model card for JOY (medium)
2
-
3
- * Language: el_GR (Greek, Greece)
4
- * Speakers: 1
5
- * Quality: medium
6
- * Samplerate: 22050 Hz
7
-
8
- ## Dataset
9
-
10
- * License: CC BY-NC 4.0
11
- * Speaker: Chara Kaltsou
12
-
13
- ## Training
14
-
15
- Trained with piper-train on 3,216 human voice recordings by a native Greek speaker.
16
- Base checkpoint: rhasspy/piper-checkpoints el_GR rapunzelina medium.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
el/el_GR/joy/medium/el_GR-joy-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:31b1d51dc72dd43a5429b67798e27599f8cdcfce8a80265bc6f50d932bf144bc
3
- size 63516050
 
 
 
 
el/el_GR/joy/medium/el_GR-joy-medium.onnx.json DELETED
@@ -1,509 +0,0 @@
1
- {
2
- "dataset": "joy",
3
- "audio": {
4
- "sample_rate": 22050,
5
- "quality": "medium"
6
- },
7
- "espeak": {
8
- "voice": "el"
9
- },
10
- "language": {
11
- "code": "el_GR",
12
- "family": "el",
13
- "region": "GR",
14
- "name_native": "Ελληνικά",
15
- "name_english": "Greek",
16
- "country_english": "Greece"
17
- },
18
- "inference": {
19
- "noise_scale": 0.667,
20
- "length_scale": 0.847,
21
- "noise_w": 0.8,
22
- "sentence_silence": 0.2
23
- },
24
- "phoneme_type": "espeak",
25
- "phoneme_map": {},
26
- "phoneme_id_map": {
27
- " ": [
28
- 3
29
- ],
30
- "!": [
31
- 4
32
- ],
33
- "\"": [
34
- 150
35
- ],
36
- "#": [
37
- 149
38
- ],
39
- "$": [
40
- 2
41
- ],
42
- "'": [
43
- 5
44
- ],
45
- "(": [
46
- 6
47
- ],
48
- ")": [
49
- 7
50
- ],
51
- ",": [
52
- 8
53
- ],
54
- "-": [
55
- 9
56
- ],
57
- ".": [
58
- 10
59
- ],
60
- "0": [
61
- 130
62
- ],
63
- "1": [
64
- 131
65
- ],
66
- "2": [
67
- 132
68
- ],
69
- "3": [
70
- 133
71
- ],
72
- "4": [
73
- 134
74
- ],
75
- "5": [
76
- 135
77
- ],
78
- "6": [
79
- 136
80
- ],
81
- "7": [
82
- 137
83
- ],
84
- "8": [
85
- 138
86
- ],
87
- "9": [
88
- 139
89
- ],
90
- ":": [
91
- 11
92
- ],
93
- ";": [
94
- 12
95
- ],
96
- "?": [
97
- 13
98
- ],
99
- "X": [
100
- 156
101
- ],
102
- "^": [
103
- 1
104
- ],
105
- "_": [
106
- 0
107
- ],
108
- "a": [
109
- 14
110
- ],
111
- "b": [
112
- 15
113
- ],
114
- "c": [
115
- 16
116
- ],
117
- "d": [
118
- 17
119
- ],
120
- "e": [
121
- 18
122
- ],
123
- "f": [
124
- 19
125
- ],
126
- "g": [
127
- 154
128
- ],
129
- "h": [
130
- 20
131
- ],
132
- "i": [
133
- 21
134
- ],
135
- "j": [
136
- 22
137
- ],
138
- "k": [
139
- 23
140
- ],
141
- "l": [
142
- 24
143
- ],
144
- "m": [
145
- 25
146
- ],
147
- "n": [
148
- 26
149
- ],
150
- "o": [
151
- 27
152
- ],
153
- "p": [
154
- 28
155
- ],
156
- "q": [
157
- 29
158
- ],
159
- "r": [
160
- 30
161
- ],
162
- "s": [
163
- 31
164
- ],
165
- "t": [
166
- 32
167
- ],
168
- "u": [
169
- 33
170
- ],
171
- "v": [
172
- 34
173
- ],
174
- "w": [
175
- 35
176
- ],
177
- "x": [
178
- 36
179
- ],
180
- "y": [
181
- 37
182
- ],
183
- "z": [
184
- 38
185
- ],
186
- "æ": [
187
- 39
188
- ],
189
- "ç": [
190
- 40
191
- ],
192
- "ð": [
193
- 41
194
- ],
195
- "ø": [
196
- 42
197
- ],
198
- "ħ": [
199
- 43
200
- ],
201
- "ŋ": [
202
- 44
203
- ],
204
- "œ": [
205
- 45
206
- ],
207
- "ǀ": [
208
- 46
209
- ],
210
- "ǁ": [
211
- 47
212
- ],
213
- "ǂ": [
214
- 48
215
- ],
216
- "ǃ": [
217
- 49
218
- ],
219
- "ɐ": [
220
- 50
221
- ],
222
- "ɑ": [
223
- 51
224
- ],
225
- "ɒ": [
226
- 52
227
- ],
228
- "ɓ": [
229
- 53
230
- ],
231
- "ɔ": [
232
- 54
233
- ],
234
- "ɕ": [
235
- 55
236
- ],
237
- "ɖ": [
238
- 56
239
- ],
240
- "ɗ": [
241
- 57
242
- ],
243
- "ɘ": [
244
- 58
245
- ],
246
- "ə": [
247
- 59
248
- ],
249
- "ɚ": [
250
- 60
251
- ],
252
- "ɛ": [
253
- 61
254
- ],
255
- "ɜ": [
256
- 62
257
- ],
258
- "ɞ": [
259
- 63
260
- ],
261
- "ɟ": [
262
- 64
263
- ],
264
- "ɠ": [
265
- 65
266
- ],
267
- "ɡ": [
268
- 66
269
- ],
270
- "ɢ": [
271
- 67
272
- ],
273
- "ɣ": [
274
- 68
275
- ],
276
- "ɤ": [
277
- 69
278
- ],
279
- "ɥ": [
280
- 70
281
- ],
282
- "ɦ": [
283
- 71
284
- ],
285
- "ɧ": [
286
- 72
287
- ],
288
- "ɨ": [
289
- 73
290
- ],
291
- "ɪ": [
292
- 74
293
- ],
294
- "ɫ": [
295
- 75
296
- ],
297
- "ɬ": [
298
- 76
299
- ],
300
- "ɭ": [
301
- 77
302
- ],
303
- "ɮ": [
304
- 78
305
- ],
306
- "ɯ": [
307
- 79
308
- ],
309
- "ɰ": [
310
- 80
311
- ],
312
- "ɱ": [
313
- 81
314
- ],
315
- "ɲ": [
316
- 82
317
- ],
318
- "ɳ": [
319
- 83
320
- ],
321
- "ɴ": [
322
- 84
323
- ],
324
- "ɵ": [
325
- 85
326
- ],
327
- "ɶ": [
328
- 86
329
- ],
330
- "ɸ": [
331
- 87
332
- ],
333
- "ɹ": [
334
- 88
335
- ],
336
- "ɺ": [
337
- 89
338
- ],
339
- "ɻ": [
340
- 90
341
- ],
342
- "ɽ": [
343
- 91
344
- ],
345
- "ɾ": [
346
- 92
347
- ],
348
- "ʀ": [
349
- 93
350
- ],
351
- "ʁ": [
352
- 94
353
- ],
354
- "ʂ": [
355
- 95
356
- ],
357
- "ʃ": [
358
- 96
359
- ],
360
- "ʄ": [
361
- 97
362
- ],
363
- "ʈ": [
364
- 98
365
- ],
366
- "ʉ": [
367
- 99
368
- ],
369
- "ʊ": [
370
- 100
371
- ],
372
- "ʋ": [
373
- 101
374
- ],
375
- "ʌ": [
376
- 102
377
- ],
378
- "ʍ": [
379
- 103
380
- ],
381
- "ʎ": [
382
- 104
383
- ],
384
- "ʏ": [
385
- 105
386
- ],
387
- "ʐ": [
388
- 106
389
- ],
390
- "ʑ": [
391
- 107
392
- ],
393
- "ʒ": [
394
- 108
395
- ],
396
- "ʔ": [
397
- 109
398
- ],
399
- "ʕ": [
400
- 110
401
- ],
402
- "ʘ": [
403
- 111
404
- ],
405
- "ʙ": [
406
- 112
407
- ],
408
- "ʛ": [
409
- 113
410
- ],
411
- "ʜ": [
412
- 114
413
- ],
414
- "ʝ": [
415
- 115
416
- ],
417
- "ʟ": [
418
- 116
419
- ],
420
- "ʡ": [
421
- 117
422
- ],
423
- "ʢ": [
424
- 118
425
- ],
426
- "ʦ": [
427
- 155
428
- ],
429
- "ʰ": [
430
- 145
431
- ],
432
- "ʲ": [
433
- 119
434
- ],
435
- "ˈ": [
436
- 120
437
- ],
438
- "ˌ": [
439
- 121
440
- ],
441
- "ː": [
442
- 122
443
- ],
444
- "ˑ": [
445
- 123
446
- ],
447
- "˞": [
448
- 124
449
- ],
450
- "ˤ": [
451
- 146
452
- ],
453
- "̃": [
454
- 141
455
- ],
456
- "̊": [
457
- 158
458
- ],
459
- "̝": [
460
- 157
461
- ],
462
- "̧": [
463
- 140
464
- ],
465
- "̩": [
466
- 144
467
- ],
468
- "̪": [
469
- 142
470
- ],
471
- "̯": [
472
- 143
473
- ],
474
- "̺": [
475
- 152
476
- ],
477
- "̻": [
478
- 153
479
- ],
480
- "β": [
481
- 125
482
- ],
483
- "ε": [
484
- 147
485
- ],
486
- "θ": [
487
- 126
488
- ],
489
- "χ": [
490
- 127
491
- ],
492
- "ᵻ": [
493
- 128
494
- ],
495
- "↑": [
496
- 151
497
- ],
498
- "↓": [
499
- 148
500
- ],
501
- "ⱱ": [
502
- 129
503
- ]
504
- },
505
- "num_symbols": 256,
506
- "num_speakers": 1,
507
- "speaker_id_map": {},
508
- "piper_version": "1.0.0"
509
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
el/el_GR/joy/medium/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:76c28f6158066ed39fde19ae5593853caea7c4123763abe4999c2ec99122917a
3
- size 34443
 
 
 
 
en/en_US/amy/medium/MODEL_CARD CHANGED
@@ -1,4 +1,4 @@
1
- # Model card for amy (medium)
2
 
3
  * Language: en_US (English, United States)
4
  * Speakers: 1
 
1
+ # Model card for amy (low)
2
 
3
  * Language: en_US (English, United States)
4
  * Speakers: 1
en/en_US/ljspeech/high/MODEL_CARD CHANGED
@@ -2,7 +2,7 @@
2
 
3
  * Language: en_US (English, United States)
4
  * Speakers: 1
5
- * Quality: high
6
  * Samplerate: 22,050Hz
7
 
8
  ## Dataset
 
2
 
3
  * Language: en_US (English, United States)
4
  * Speakers: 1
5
+ * Quality: medium
6
  * Samplerate: 22,050Hz
7
 
8
  ## Dataset
en/en_US/mike/medium/MODEL_CARD DELETED
@@ -1,15 +0,0 @@
1
- # Model card for mike (medium)
2
-
3
- * Language: en_US (English, United States)
4
- * Speakers: 1
5
- * Quality: medium
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- * URL: https://github.com/OHF-Voice/voice-datasets
11
- * License: CC0
12
-
13
- ## Training
14
-
15
- Finetuned from U.S. English lessac voice (medium quality).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
en/en_US/mike/medium/en_US-mike-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3157e69e2c580cab297483f4b301ee975a4590c17d35a9757e33347d0e90fae2
3
- size 63221984
 
 
 
 
en/en_US/mike/medium/en_US-mike-medium.onnx.json DELETED
@@ -1,551 +0,0 @@
1
- {
2
- "audio": {
3
- "sample_rate": 22050,
4
- "quality": "medium"
5
- },
6
- "espeak": {
7
- "voice": "en-us"
8
- },
9
- "dataset": "mike",
10
- "phoneme_type": "espeak",
11
- "num_symbols": 256,
12
- "num_speakers": 1,
13
- "inference": {
14
- "noise_scale": 0.667,
15
- "length_scale": 1.0,
16
- "noise_w": 0.8
17
- },
18
- "phoneme_id_map": {
19
- "_": [
20
- 0
21
- ],
22
- "^": [
23
- 1
24
- ],
25
- "$": [
26
- 2
27
- ],
28
- " ": [
29
- 3
30
- ],
31
- "!": [
32
- 4
33
- ],
34
- "'": [
35
- 5
36
- ],
37
- "(": [
38
- 6
39
- ],
40
- ")": [
41
- 7
42
- ],
43
- ",": [
44
- 8
45
- ],
46
- "-": [
47
- 9
48
- ],
49
- ".": [
50
- 10
51
- ],
52
- ":": [
53
- 11
54
- ],
55
- ";": [
56
- 12
57
- ],
58
- "?": [
59
- 13
60
- ],
61
- "a": [
62
- 14
63
- ],
64
- "b": [
65
- 15
66
- ],
67
- "c": [
68
- 16
69
- ],
70
- "d": [
71
- 17
72
- ],
73
- "e": [
74
- 18
75
- ],
76
- "f": [
77
- 19
78
- ],
79
- "h": [
80
- 20
81
- ],
82
- "i": [
83
- 21
84
- ],
85
- "j": [
86
- 22
87
- ],
88
- "k": [
89
- 23
90
- ],
91
- "l": [
92
- 24
93
- ],
94
- "m": [
95
- 25
96
- ],
97
- "n": [
98
- 26
99
- ],
100
- "o": [
101
- 27
102
- ],
103
- "p": [
104
- 28
105
- ],
106
- "q": [
107
- 29
108
- ],
109
- "r": [
110
- 30
111
- ],
112
- "s": [
113
- 31
114
- ],
115
- "t": [
116
- 32
117
- ],
118
- "u": [
119
- 33
120
- ],
121
- "v": [
122
- 34
123
- ],
124
- "w": [
125
- 35
126
- ],
127
- "x": [
128
- 36
129
- ],
130
- "y": [
131
- 37
132
- ],
133
- "z": [
134
- 38
135
- ],
136
- "æ": [
137
- 39
138
- ],
139
- "ç": [
140
- 40
141
- ],
142
- "ð": [
143
- 41
144
- ],
145
- "ø": [
146
- 42
147
- ],
148
- "ħ": [
149
- 43
150
- ],
151
- "ŋ": [
152
- 44
153
- ],
154
- "œ": [
155
- 45
156
- ],
157
- "ǀ": [
158
- 46
159
- ],
160
- "ǁ": [
161
- 47
162
- ],
163
- "ǂ": [
164
- 48
165
- ],
166
- "ǃ": [
167
- 49
168
- ],
169
- "ɐ": [
170
- 50
171
- ],
172
- "ɑ": [
173
- 51
174
- ],
175
- "ɒ": [
176
- 52
177
- ],
178
- "ɓ": [
179
- 53
180
- ],
181
- "ɔ": [
182
- 54
183
- ],
184
- "ɕ": [
185
- 55
186
- ],
187
- "ɖ": [
188
- 56
189
- ],
190
- "ɗ": [
191
- 57
192
- ],
193
- "ɘ": [
194
- 58
195
- ],
196
- "ə": [
197
- 59
198
- ],
199
- "ɚ": [
200
- 60
201
- ],
202
- "ɛ": [
203
- 61
204
- ],
205
- "ɜ": [
206
- 62
207
- ],
208
- "ɞ": [
209
- 63
210
- ],
211
- "ɟ": [
212
- 64
213
- ],
214
- "ɠ": [
215
- 65
216
- ],
217
- "ɡ": [
218
- 66
219
- ],
220
- "ɢ": [
221
- 67
222
- ],
223
- "ɣ": [
224
- 68
225
- ],
226
- "ɤ": [
227
- 69
228
- ],
229
- "ɥ": [
230
- 70
231
- ],
232
- "ɦ": [
233
- 71
234
- ],
235
- "ɧ": [
236
- 72
237
- ],
238
- "ɨ": [
239
- 73
240
- ],
241
- "ɪ": [
242
- 74
243
- ],
244
- "ɫ": [
245
- 75
246
- ],
247
- "ɬ": [
248
- 76
249
- ],
250
- "ɭ": [
251
- 77
252
- ],
253
- "ɮ": [
254
- 78
255
- ],
256
- "ɯ": [
257
- 79
258
- ],
259
- "ɰ": [
260
- 80
261
- ],
262
- "ɱ": [
263
- 81
264
- ],
265
- "ɲ": [
266
- 82
267
- ],
268
- "ɳ": [
269
- 83
270
- ],
271
- "ɴ": [
272
- 84
273
- ],
274
- "ɵ": [
275
- 85
276
- ],
277
- "ɶ": [
278
- 86
279
- ],
280
- "ɸ": [
281
- 87
282
- ],
283
- "ɹ": [
284
- 88
285
- ],
286
- "ɺ": [
287
- 89
288
- ],
289
- "ɻ": [
290
- 90
291
- ],
292
- "ɽ": [
293
- 91
294
- ],
295
- "ɾ": [
296
- 92
297
- ],
298
- "ʀ": [
299
- 93
300
- ],
301
- "ʁ": [
302
- 94
303
- ],
304
- "ʂ": [
305
- 95
306
- ],
307
- "ʃ": [
308
- 96
309
- ],
310
- "ʄ": [
311
- 97
312
- ],
313
- "ʈ": [
314
- 98
315
- ],
316
- "ʉ": [
317
- 99
318
- ],
319
- "ʊ": [
320
- 100
321
- ],
322
- "ʋ": [
323
- 101
324
- ],
325
- "ʌ": [
326
- 102
327
- ],
328
- "ʍ": [
329
- 103
330
- ],
331
- "ʎ": [
332
- 104
333
- ],
334
- "ʏ": [
335
- 105
336
- ],
337
- "ʐ": [
338
- 106
339
- ],
340
- "ʑ": [
341
- 107
342
- ],
343
- "ʒ": [
344
- 108
345
- ],
346
- "ʔ": [
347
- 109
348
- ],
349
- "ʕ": [
350
- 110
351
- ],
352
- "ʘ": [
353
- 111
354
- ],
355
- "ʙ": [
356
- 112
357
- ],
358
- "ʛ": [
359
- 113
360
- ],
361
- "ʜ": [
362
- 114
363
- ],
364
- "ʝ": [
365
- 115
366
- ],
367
- "ʟ": [
368
- 116
369
- ],
370
- "ʡ": [
371
- 117
372
- ],
373
- "ʢ": [
374
- 118
375
- ],
376
- "ʲ": [
377
- 119
378
- ],
379
- "ˈ": [
380
- 120
381
- ],
382
- "ˌ": [
383
- 121
384
- ],
385
- "ː": [
386
- 122
387
- ],
388
- "ˑ": [
389
- 123
390
- ],
391
- "˞": [
392
- 124
393
- ],
394
- "β": [
395
- 125
396
- ],
397
- "θ": [
398
- 126
399
- ],
400
- "χ": [
401
- 127
402
- ],
403
- "ᵻ": [
404
- 128
405
- ],
406
- "ⱱ": [
407
- 129
408
- ],
409
- "0": [
410
- 130
411
- ],
412
- "1": [
413
- 131
414
- ],
415
- "2": [
416
- 132
417
- ],
418
- "3": [
419
- 133
420
- ],
421
- "4": [
422
- 134
423
- ],
424
- "5": [
425
- 135
426
- ],
427
- "6": [
428
- 136
429
- ],
430
- "7": [
431
- 137
432
- ],
433
- "8": [
434
- 138
435
- ],
436
- "9": [
437
- 139
438
- ],
439
- "̧": [
440
- 140
441
- ],
442
- "̃": [
443
- 141
444
- ],
445
- "̪": [
446
- 142
447
- ],
448
- "̯": [
449
- 143
450
- ],
451
- "̩": [
452
- 144
453
- ],
454
- "ʰ": [
455
- 145
456
- ],
457
- "ˤ": [
458
- 146
459
- ],
460
- "ε": [
461
- 147
462
- ],
463
- "↓": [
464
- 148
465
- ],
466
- "#": [
467
- 149
468
- ],
469
- "\"": [
470
- 150
471
- ],
472
- "↑": [
473
- 151
474
- ],
475
- "̺": [
476
- 152
477
- ],
478
- "̻": [
479
- 153
480
- ],
481
- "g": [
482
- 154
483
- ],
484
- "ʦ": [
485
- 155
486
- ],
487
- "X": [
488
- 156
489
- ],
490
- "̝": [
491
- 157
492
- ],
493
- "̊": [
494
- 158
495
- ],
496
- "ɝ": [
497
- 159
498
- ],
499
- "ʷ": [
500
- 160
501
- ],
502
- "aɪ": [
503
- 161
504
- ],
505
- "aʊ": [
506
- 162
507
- ],
508
- "ɔɪ": [
509
- 163
510
- ],
511
- "eɪ": [
512
- 164
513
- ],
514
- "oʊ": [
515
- 165
516
- ]
517
- },
518
- "speaker_id_map": {},
519
- "hop_length": 256,
520
- "piper_version": "1.5.0",
521
- "vowel_clusters": [
522
- [
523
- "a",
524
- "ɪ"
525
- ],
526
- [
527
- "a",
528
- "ʊ"
529
- ],
530
- [
531
- "e",
532
- "ɪ"
533
- ],
534
- [
535
- "o",
536
- "ʊ"
537
- ],
538
- [
539
- "ɔ",
540
- "ɪ"
541
- ]
542
- ],
543
- "language": {
544
- "code": "en_US",
545
- "family": "en",
546
- "region": "US",
547
- "name_native": "English",
548
- "name_english": "English",
549
- "country_english": "United States"
550
- }
551
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
en/en_US/mike/medium/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b3befaceb606c9f88b86218c433b8a0bbb550e6183700985ba564197b033ccc
3
- size 80388
 
 
 
 
es/es_AR/daniela/high/MODEL_CARD CHANGED
@@ -1,6 +1,6 @@
1
  # Model card for daniela (high)
2
 
3
- * Language: es_AR (Spanish, Argentina)
4
  * Speakers: 1
5
  * Quality: high
6
  * Samplerate: 22,050Hz
 
1
  # Model card for daniela (high)
2
 
3
+ * Language: es_ES (Spanish, Argentina)
4
  * Speakers: 1
5
  * Quality: high
6
  * Samplerate: 22,050Hz
es/es_MX/ald/x_low/MODEL_CARD DELETED
@@ -1,19 +0,0 @@
1
- # Model card for ald (x-low)
2
-
3
- * Language: es_MX (Spanish, Mexico)
4
- * Speakers: 1
5
- * Quality: x-low
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- Synthetic speech dataset generated using the original es_MX-ald-medium Piper TTS model.
11
-
12
- The dataset contains approximately 8 hours of audio generated from Spanish sentences obtained from the Tatoeba Project:
13
- https://tatoeba.org/en/downloads
14
-
15
- ## Training
16
-
17
- This model was trained from scratch using the synthetic dataset generated with the es_MX-ald-medium voice.
18
-
19
- The goal of this model is to provide a smaller and faster alternative with fewer parameters.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
es/es_MX/ald/x_low/es_MX-ald-x_low.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8aae54aee9eafb37fb85d6da676facafca31c2d84d11acdca1a5b6dd82b1df6
3
- size 20986952
 
 
 
 
es/es_MX/ald/x_low/es_MX-ald-x_low.onnx.json DELETED
@@ -1,493 +0,0 @@
1
- {
2
- "audio": {
3
- "sample_rate": 22050,
4
- "quality": "x_low"
5
- },
6
- "espeak": {
7
- "voice": "es-419"
8
- },
9
- "inference": {
10
- "noise_scale": 0.667,
11
- "length_scale": 1,
12
- "noise_w": 0.8
13
- },
14
- "phoneme_type": "espeak",
15
- "phoneme_map": {},
16
- "phoneme_id_map": {
17
- "_": [
18
- 0
19
- ],
20
- "^": [
21
- 1
22
- ],
23
- "$": [
24
- 2
25
- ],
26
- " ": [
27
- 3
28
- ],
29
- "!": [
30
- 4
31
- ],
32
- "'": [
33
- 5
34
- ],
35
- "(": [
36
- 6
37
- ],
38
- ")": [
39
- 7
40
- ],
41
- ",": [
42
- 8
43
- ],
44
- "-": [
45
- 9
46
- ],
47
- ".": [
48
- 10
49
- ],
50
- ":": [
51
- 11
52
- ],
53
- ";": [
54
- 12
55
- ],
56
- "?": [
57
- 13
58
- ],
59
- "a": [
60
- 14
61
- ],
62
- "b": [
63
- 15
64
- ],
65
- "c": [
66
- 16
67
- ],
68
- "d": [
69
- 17
70
- ],
71
- "e": [
72
- 18
73
- ],
74
- "f": [
75
- 19
76
- ],
77
- "h": [
78
- 20
79
- ],
80
- "i": [
81
- 21
82
- ],
83
- "j": [
84
- 22
85
- ],
86
- "k": [
87
- 23
88
- ],
89
- "l": [
90
- 24
91
- ],
92
- "m": [
93
- 25
94
- ],
95
- "n": [
96
- 26
97
- ],
98
- "o": [
99
- 27
100
- ],
101
- "p": [
102
- 28
103
- ],
104
- "q": [
105
- 29
106
- ],
107
- "r": [
108
- 30
109
- ],
110
- "s": [
111
- 31
112
- ],
113
- "t": [
114
- 32
115
- ],
116
- "u": [
117
- 33
118
- ],
119
- "v": [
120
- 34
121
- ],
122
- "w": [
123
- 35
124
- ],
125
- "x": [
126
- 36
127
- ],
128
- "y": [
129
- 37
130
- ],
131
- "z": [
132
- 38
133
- ],
134
- "æ": [
135
- 39
136
- ],
137
- "ç": [
138
- 40
139
- ],
140
- "ð": [
141
- 41
142
- ],
143
- "ø": [
144
- 42
145
- ],
146
- "ħ": [
147
- 43
148
- ],
149
- "ŋ": [
150
- 44
151
- ],
152
- "œ": [
153
- 45
154
- ],
155
- "ǀ": [
156
- 46
157
- ],
158
- "ǁ": [
159
- 47
160
- ],
161
- "ǂ": [
162
- 48
163
- ],
164
- "ǃ": [
165
- 49
166
- ],
167
- "ɐ": [
168
- 50
169
- ],
170
- "ɑ": [
171
- 51
172
- ],
173
- "ɒ": [
174
- 52
175
- ],
176
- "ɓ": [
177
- 53
178
- ],
179
- "ɔ": [
180
- 54
181
- ],
182
- "ɕ": [
183
- 55
184
- ],
185
- "ɖ": [
186
- 56
187
- ],
188
- "ɗ": [
189
- 57
190
- ],
191
- "ɘ": [
192
- 58
193
- ],
194
- "ə": [
195
- 59
196
- ],
197
- "ɚ": [
198
- 60
199
- ],
200
- "ɛ": [
201
- 61
202
- ],
203
- "ɜ": [
204
- 62
205
- ],
206
- "ɞ": [
207
- 63
208
- ],
209
- "ɟ": [
210
- 64
211
- ],
212
- "ɠ": [
213
- 65
214
- ],
215
- "ɡ": [
216
- 66
217
- ],
218
- "ɢ": [
219
- 67
220
- ],
221
- "ɣ": [
222
- 68
223
- ],
224
- "ɤ": [
225
- 69
226
- ],
227
- "ɥ": [
228
- 70
229
- ],
230
- "ɦ": [
231
- 71
232
- ],
233
- "ɧ": [
234
- 72
235
- ],
236
- "ɨ": [
237
- 73
238
- ],
239
- "ɪ": [
240
- 74
241
- ],
242
- "ɫ": [
243
- 75
244
- ],
245
- "ɬ": [
246
- 76
247
- ],
248
- "ɭ": [
249
- 77
250
- ],
251
- "ɮ": [
252
- 78
253
- ],
254
- "ɯ": [
255
- 79
256
- ],
257
- "ɰ": [
258
- 80
259
- ],
260
- "ɱ": [
261
- 81
262
- ],
263
- "ɲ": [
264
- 82
265
- ],
266
- "ɳ": [
267
- 83
268
- ],
269
- "ɴ": [
270
- 84
271
- ],
272
- "ɵ": [
273
- 85
274
- ],
275
- "ɶ": [
276
- 86
277
- ],
278
- "ɸ": [
279
- 87
280
- ],
281
- "ɹ": [
282
- 88
283
- ],
284
- "ɺ": [
285
- 89
286
- ],
287
- "ɻ": [
288
- 90
289
- ],
290
- "ɽ": [
291
- 91
292
- ],
293
- "ɾ": [
294
- 92
295
- ],
296
- "ʀ": [
297
- 93
298
- ],
299
- "ʁ": [
300
- 94
301
- ],
302
- "ʂ": [
303
- 95
304
- ],
305
- "ʃ": [
306
- 96
307
- ],
308
- "ʄ": [
309
- 97
310
- ],
311
- "ʈ": [
312
- 98
313
- ],
314
- "ʉ": [
315
- 99
316
- ],
317
- "ʊ": [
318
- 100
319
- ],
320
- "ʋ": [
321
- 101
322
- ],
323
- "ʌ": [
324
- 102
325
- ],
326
- "ʍ": [
327
- 103
328
- ],
329
- "ʎ": [
330
- 104
331
- ],
332
- "ʏ": [
333
- 105
334
- ],
335
- "ʐ": [
336
- 106
337
- ],
338
- "ʑ": [
339
- 107
340
- ],
341
- "ʒ": [
342
- 108
343
- ],
344
- "ʔ": [
345
- 109
346
- ],
347
- "ʕ": [
348
- 110
349
- ],
350
- "ʘ": [
351
- 111
352
- ],
353
- "ʙ": [
354
- 112
355
- ],
356
- "ʛ": [
357
- 113
358
- ],
359
- "ʜ": [
360
- 114
361
- ],
362
- "ʝ": [
363
- 115
364
- ],
365
- "ʟ": [
366
- 116
367
- ],
368
- "ʡ": [
369
- 117
370
- ],
371
- "ʢ": [
372
- 118
373
- ],
374
- "ʲ": [
375
- 119
376
- ],
377
- "ˈ": [
378
- 120
379
- ],
380
- "ˌ": [
381
- 121
382
- ],
383
- "ː": [
384
- 122
385
- ],
386
- "ˑ": [
387
- 123
388
- ],
389
- "˞": [
390
- 124
391
- ],
392
- "β": [
393
- 125
394
- ],
395
- "θ": [
396
- 126
397
- ],
398
- "χ": [
399
- 127
400
- ],
401
- "ᵻ": [
402
- 128
403
- ],
404
- "ⱱ": [
405
- 129
406
- ],
407
- "0": [
408
- 130
409
- ],
410
- "1": [
411
- 131
412
- ],
413
- "2": [
414
- 132
415
- ],
416
- "3": [
417
- 133
418
- ],
419
- "4": [
420
- 134
421
- ],
422
- "5": [
423
- 135
424
- ],
425
- "6": [
426
- 136
427
- ],
428
- "7": [
429
- 137
430
- ],
431
- "8": [
432
- 138
433
- ],
434
- "9": [
435
- 139
436
- ],
437
- "̧": [
438
- 140
439
- ],
440
- "̃": [
441
- 141
442
- ],
443
- "̪": [
444
- 142
445
- ],
446
- "̯": [
447
- 143
448
- ],
449
- "̩": [
450
- 144
451
- ],
452
- "ʰ": [
453
- 145
454
- ],
455
- "ˤ": [
456
- 146
457
- ],
458
- "ε": [
459
- 147
460
- ],
461
- "↓": [
462
- 148
463
- ],
464
- "#": [
465
- 149
466
- ],
467
- "\"": [
468
- 150
469
- ],
470
- "↑": [
471
- 151
472
- ],
473
- "̺": [
474
- 152
475
- ],
476
- "̻": [
477
- 153
478
- ]
479
- },
480
- "num_symbols": 256,
481
- "num_speakers": 1,
482
- "speaker_id_map": {},
483
- "piper_version": "1.0.0",
484
- "language": {
485
- "code": "es_MX",
486
- "family": "es",
487
- "region": "MX",
488
- "name_native": "Español",
489
- "name_english": "Spanish",
490
- "country_english": "Mexico"
491
- },
492
- "dataset": "ald"
493
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
es/es_MX/ald/x_low/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:742ceeb5fec6fd163e74b30319e5bae547d602ea4c5668347c5f740d9df979a3
3
- size 176189
 
 
 
 
et/et_EE/news/medium/MODEL_CARD DELETED
@@ -1,16 +0,0 @@
1
- # Model card for news (medium)
2
-
3
- * Language: et_EE (Estonian, Estonia)
4
- * Speakers: 4
5
- * Quality: medium
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- * URL: https://metashare.ut.ee/repository/browse/speech-corpus-of-estonian-news-sentences/37b7c5d6a0d411eebb4773db10791bcfb0c0cf788d2d4030bfaf2f2e6e55dd8d/
11
- * License: CC-BY (META-SHARE "Available - Unrestricted Use")
12
- * Paper: https://arxiv.org/abs/2010.02636
13
-
14
- ## Training
15
-
16
- Finetuned from LibriTTS-R base model.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
et/et_EE/news/medium/et_EE-news-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd679e874e0f6ec4e8f76c99cef77d490341b001aa6e839415028be5d04f9bf
3
- size 76757937
 
 
 
 
et/et_EE/news/medium/et_EE-news-medium.onnx.json DELETED
@@ -1,535 +0,0 @@
1
- {
2
- "audio": {
3
- "sample_rate": 22050,
4
- "quality": "medium"
5
- },
6
- "espeak": {
7
- "voice": "et"
8
- },
9
- "language": {
10
- "code": "et_EE",
11
- "family": "et",
12
- "region": "EE",
13
- "name_native": "eesti",
14
- "name_english": "Estonian",
15
- "country_english": "Estonia"
16
- },
17
- "phoneme_type": "espeak",
18
- "num_symbols": 256,
19
- "num_speakers": 4,
20
- "inference": {
21
- "noise_scale": 0.667,
22
- "length_scale": 1.0,
23
- "noise_w": 0.8
24
- },
25
- "phoneme_id_map": {
26
- "_": [
27
- 0
28
- ],
29
- "^": [
30
- 1
31
- ],
32
- "$": [
33
- 2
34
- ],
35
- " ": [
36
- 3
37
- ],
38
- "!": [
39
- 4
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
- ":": [
60
- 11
61
- ],
62
- ";": [
63
- 12
64
- ],
65
- "?": [
66
- 13
67
- ],
68
- "a": [
69
- 14
70
- ],
71
- "b": [
72
- 15
73
- ],
74
- "c": [
75
- 16
76
- ],
77
- "d": [
78
- 17
79
- ],
80
- "e": [
81
- 18
82
- ],
83
- "f": [
84
- 19
85
- ],
86
- "h": [
87
- 20
88
- ],
89
- "i": [
90
- 21
91
- ],
92
- "j": [
93
- 22
94
- ],
95
- "k": [
96
- 23
97
- ],
98
- "l": [
99
- 24
100
- ],
101
- "m": [
102
- 25
103
- ],
104
- "n": [
105
- 26
106
- ],
107
- "o": [
108
- 27
109
- ],
110
- "p": [
111
- 28
112
- ],
113
- "q": [
114
- 29
115
- ],
116
- "r": [
117
- 30
118
- ],
119
- "s": [
120
- 31
121
- ],
122
- "t": [
123
- 32
124
- ],
125
- "u": [
126
- 33
127
- ],
128
- "v": [
129
- 34
130
- ],
131
- "w": [
132
- 35
133
- ],
134
- "x": [
135
- 36
136
- ],
137
- "y": [
138
- 37
139
- ],
140
- "z": [
141
- 38
142
- ],
143
- "æ": [
144
- 39
145
- ],
146
- "ç": [
147
- 40
148
- ],
149
- "ð": [
150
- 41
151
- ],
152
- "ø": [
153
- 42
154
- ],
155
- "ħ": [
156
- 43
157
- ],
158
- "ŋ": [
159
- 44
160
- ],
161
- "œ": [
162
- 45
163
- ],
164
- "ǀ": [
165
- 46
166
- ],
167
- "ǁ": [
168
- 47
169
- ],
170
- "ǂ": [
171
- 48
172
- ],
173
- "ǃ": [
174
- 49
175
- ],
176
- "ɐ": [
177
- 50
178
- ],
179
- "ɑ": [
180
- 51
181
- ],
182
- "ɒ": [
183
- 52
184
- ],
185
- "ɓ": [
186
- 53
187
- ],
188
- "ɔ": [
189
- 54
190
- ],
191
- "ɕ": [
192
- 55
193
- ],
194
- "ɖ": [
195
- 56
196
- ],
197
- "ɗ": [
198
- 57
199
- ],
200
- "ɘ": [
201
- 58
202
- ],
203
- "ə": [
204
- 59
205
- ],
206
- "ɚ": [
207
- 60
208
- ],
209
- "ɛ": [
210
- 61
211
- ],
212
- "ɜ": [
213
- 62
214
- ],
215
- "ɞ": [
216
- 63
217
- ],
218
- "ɟ": [
219
- 64
220
- ],
221
- "ɠ": [
222
- 65
223
- ],
224
- "ɡ": [
225
- 66
226
- ],
227
- "ɢ": [
228
- 67
229
- ],
230
- "ɣ": [
231
- 68
232
- ],
233
- "ɤ": [
234
- 69
235
- ],
236
- "ɥ": [
237
- 70
238
- ],
239
- "ɦ": [
240
- 71
241
- ],
242
- "ɧ": [
243
- 72
244
- ],
245
- "ɨ": [
246
- 73
247
- ],
248
- "ɪ": [
249
- 74
250
- ],
251
- "ɫ": [
252
- 75
253
- ],
254
- "ɬ": [
255
- 76
256
- ],
257
- "ɭ": [
258
- 77
259
- ],
260
- "ɮ": [
261
- 78
262
- ],
263
- "ɯ": [
264
- 79
265
- ],
266
- "ɰ": [
267
- 80
268
- ],
269
- "ɱ": [
270
- 81
271
- ],
272
- "ɲ": [
273
- 82
274
- ],
275
- "ɳ": [
276
- 83
277
- ],
278
- "ɴ": [
279
- 84
280
- ],
281
- "ɵ": [
282
- 85
283
- ],
284
- "ɶ": [
285
- 86
286
- ],
287
- "ɸ": [
288
- 87
289
- ],
290
- "ɹ": [
291
- 88
292
- ],
293
- "ɺ": [
294
- 89
295
- ],
296
- "ɻ": [
297
- 90
298
- ],
299
- "ɽ": [
300
- 91
301
- ],
302
- "ɾ": [
303
- 92
304
- ],
305
- "ʀ": [
306
- 93
307
- ],
308
- "ʁ": [
309
- 94
310
- ],
311
- "ʂ": [
312
- 95
313
- ],
314
- "ʃ": [
315
- 96
316
- ],
317
- "ʄ": [
318
- 97
319
- ],
320
- "ʈ": [
321
- 98
322
- ],
323
- "ʉ": [
324
- 99
325
- ],
326
- "ʊ": [
327
- 100
328
- ],
329
- "ʋ": [
330
- 101
331
- ],
332
- "ʌ": [
333
- 102
334
- ],
335
- "ʍ": [
336
- 103
337
- ],
338
- "ʎ": [
339
- 104
340
- ],
341
- "ʏ": [
342
- 105
343
- ],
344
- "ʐ": [
345
- 106
346
- ],
347
- "ʑ": [
348
- 107
349
- ],
350
- "ʒ": [
351
- 108
352
- ],
353
- "ʔ": [
354
- 109
355
- ],
356
- "ʕ": [
357
- 110
358
- ],
359
- "ʘ": [
360
- 111
361
- ],
362
- "ʙ": [
363
- 112
364
- ],
365
- "ʛ": [
366
- 113
367
- ],
368
- "ʜ": [
369
- 114
370
- ],
371
- "ʝ": [
372
- 115
373
- ],
374
- "ʟ": [
375
- 116
376
- ],
377
- "ʡ": [
378
- 117
379
- ],
380
- "ʢ": [
381
- 118
382
- ],
383
- "ʲ": [
384
- 119
385
- ],
386
- "ˈ": [
387
- 120
388
- ],
389
- "ˌ": [
390
- 121
391
- ],
392
- "ː": [
393
- 122
394
- ],
395
- "ˑ": [
396
- 123
397
- ],
398
- "˞": [
399
- 124
400
- ],
401
- "β": [
402
- 125
403
- ],
404
- "θ": [
405
- 126
406
- ],
407
- "χ": [
408
- 127
409
- ],
410
- "ᵻ": [
411
- 128
412
- ],
413
- "ⱱ": [
414
- 129
415
- ],
416
- "0": [
417
- 130
418
- ],
419
- "1": [
420
- 131
421
- ],
422
- "2": [
423
- 132
424
- ],
425
- "3": [
426
- 133
427
- ],
428
- "4": [
429
- 134
430
- ],
431
- "5": [
432
- 135
433
- ],
434
- "6": [
435
- 136
436
- ],
437
- "7": [
438
- 137
439
- ],
440
- "8": [
441
- 138
442
- ],
443
- "9": [
444
- 139
445
- ],
446
- "̧": [
447
- 140
448
- ],
449
- "̃": [
450
- 141
451
- ],
452
- "̪": [
453
- 142
454
- ],
455
- "̯": [
456
- 143
457
- ],
458
- "̩": [
459
- 144
460
- ],
461
- "ʰ": [
462
- 145
463
- ],
464
- "ˤ": [
465
- 146
466
- ],
467
- "ε": [
468
- 147
469
- ],
470
- "↓": [
471
- 148
472
- ],
473
- "#": [
474
- 149
475
- ],
476
- "\"": [
477
- 150
478
- ],
479
- "↑": [
480
- 151
481
- ],
482
- "̺": [
483
- 152
484
- ],
485
- "̻": [
486
- 153
487
- ],
488
- "g": [
489
- 154
490
- ],
491
- "ʦ": [
492
- 155
493
- ],
494
- "X": [
495
- 156
496
- ],
497
- "̝": [
498
- 157
499
- ],
500
- "̊": [
501
- 158
502
- ],
503
- "ɝ": [
504
- 159
505
- ],
506
- "ʷ": [
507
- 160
508
- ],
509
- "aɪ": [
510
- 161
511
- ],
512
- "aʊ": [
513
- 162
514
- ],
515
- "ɔɪ": [
516
- 163
517
- ],
518
- "eɪ": [
519
- 164
520
- ],
521
- "oʊ": [
522
- 165
523
- ]
524
- },
525
- "speaker_id_map": {
526
- "Albert": 0,
527
- "Kalev": 1,
528
- "Mari": 2,
529
- "Vesta": 3
530
- },
531
- "hop_length": 256,
532
- "default_speaker_id": 0,
533
- "piper_version": "1.5.0",
534
- "dataset": "news"
535
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
et/et_EE/news/medium/samples/speaker_0.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c977b65abbf5437aa9b62ecd6d79fd6a1c60b37325eabd4b5ded4b6f83ac7d2
3
- size 109812
 
 
 
 
et/et_EE/news/medium/samples/speaker_1.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b49921d345d137420e06f3e11fa649840b86bbdecc34e25954b5368496ebca
3
- size 125485
 
 
 
 
et/et_EE/news/medium/samples/speaker_2.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf9835b418f9b54f30badd50555548cf3af222d326ac4852eda653da1cfbb90f
3
- size 109713
 
 
 
 
et/et_EE/news/medium/samples/speaker_3.mp3 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0f7f7e1d3684e3f6823612fec9b65fd898154d481e5d7a79a356e0ade6a950f
3
- size 134716
 
 
 
 
he/he_IL/saspeech/medium/MODEL_CARD DELETED
@@ -1,15 +0,0 @@
1
- # Model card for saspeech (medium)
2
-
3
- * Language: he_IL (Hebrew, Israel)
4
- * Speakers: 1
5
- * Quality: medium
6
- * Samplerate: 22,050Hz
7
-
8
- ## Dataset
9
-
10
- * URL: https://www.openslr.org/134 (gold standard)
11
- * License: See dataset URL
12
-
13
- ## Training
14
-
15
- Finetuned from LibriTTS-R base model.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
he/he_IL/saspeech/medium/he_IL-saspeech-medium.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc067debc9e782a8a0d095dbb58786648743d406366dcc2aa81009660873b4d
3
- size 63221984