ONNX
Michael Hansen commited on
Commit
2083514
1 Parent(s): de3dcfd

Add bryce, john, norman

Browse files
en/en_US/bryce/medium/MODEL_CARD ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for bryce (medium)
2
+
3
+ * Language: en_US (English, United States)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * License: public domain
11
+
12
+ ## Training
13
+
14
+ See: https://brycebeattie.com/files/tts/
15
+
16
+ US English male voice. Single Speaker. Finetuned for an additional 1000 epochs from an unreleased voice which had 2500 epochs. This is my voice, I only recorded about 750 samples.
en/en_US/bryce/medium/en_US-bryce-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9caa6c313199ffb5ac698b6e542fa6cba388aeaf2731e25262e33b9810aef1
3
+ size 63531379
en/en_US/bryce/medium/en_US-bryce-medium.onnx.json ADDED
@@ -0,0 +1,502 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "bryce",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "en"
9
+ },
10
+ "language": {
11
+ "code": "en_US",
12
+ "family": "en",
13
+ "region": "US",
14
+ "name_native": "English",
15
+ "name_english": "English",
16
+ "country_english": "United States"
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
+ "ⱱ": [
495
+ 129
496
+ ]
497
+ },
498
+ "num_symbols": 256,
499
+ "num_speakers": 1,
500
+ "speaker_id_map": {},
501
+ "piper_version": "1.0.0"
502
+ }
en/en_US/bryce/medium/samples/speaker_0.mp3 ADDED
Binary file (108 kB). View file
 
en/en_US/john/medium/MODEL_CARD ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for john (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://librivox.org
11
+ * License: public domain
12
+
13
+ ## Training
14
+
15
+ See: https://brycebeattie.com/files/tts/
16
+
17
+ US English male voice. Single Speaker. Finetuned from Kristin (above) on medium quality settings for an additional 600 epochs. I put together the dataset, which ended up with about 12.5 hours of recordings. All recordings came from LibriVox.org.
en/en_US/john/medium/en_US-john-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789c6c875726e627ddee93d51d8727859abe9c091c3d141591f4b83c2072e988
3
+ size 63531379
en/en_US/john/medium/en_US-john-medium.onnx.json ADDED
@@ -0,0 +1,502 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "john",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "en"
9
+ },
10
+ "language": {
11
+ "code": "en_US",
12
+ "family": "en",
13
+ "region": "US",
14
+ "name_native": "English",
15
+ "name_english": "English",
16
+ "country_english": "United States"
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
+ "ⱱ": [
495
+ 129
496
+ ]
497
+ },
498
+ "num_symbols": 256,
499
+ "num_speakers": 1,
500
+ "speaker_id_map": {},
501
+ "piper_version": "1.0.0"
502
+ }
en/en_US/john/medium/samples/speaker_0.mp3 ADDED
Binary file (97.1 kB). View file
 
en/en_US/norman/medium/MODEL_CARD ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for norman (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://librivox.org
11
+ * License: public domain
12
+
13
+ ## Training
14
+
15
+ See: https://brycebeattie.com/files/tts/
16
+
17
+ US English male voice. Single Speaker. Trained from scratch on medium quality settings for 1200 epochs. I put together the dataset, which ended up with about 15.5 hours of recordings. All recordings came from LibriVox.org. I forgot to save the ckpt file on this one, sorry.
en/en_US/norman/medium/en_US-norman-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9739443232a80a59c7d18810dd856899bf16a7964725f5ab81ea49b1351cb71
3
+ size 63531379
en/en_US/norman/medium/en_US-norman-medium.onnx.json ADDED
@@ -0,0 +1,502 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "norman",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "medium"
6
+ },
7
+ "espeak": {
8
+ "voice": "en"
9
+ },
10
+ "language": {
11
+ "code": "en_US",
12
+ "family": "en",
13
+ "region": "US",
14
+ "name_native": "English",
15
+ "name_english": "English",
16
+ "country_english": "United States"
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
+ "ⱱ": [
495
+ 129
496
+ ]
497
+ },
498
+ "num_symbols": 256,
499
+ "num_speakers": 1,
500
+ "speaker_id_map": {},
501
+ "piper_version": "1.0.0"
502
+ }
en/en_US/norman/medium/samples/speaker_0.mp3 ADDED
Binary file (91.3 kB). View file
 
voices.json CHANGED
@@ -1436,6 +1436,36 @@
1436
  },
1437
  "aliases": []
1438
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1439
  "en_US-danny-low": {
1440
  "key": "en_US-danny-low",
1441
  "name": "danny",
@@ -1556,6 +1586,36 @@
1556
  },
1557
  "aliases": []
1558
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1559
  "en_US-kathleen-low": {
1560
  "key": "en_US-kathleen-low",
1561
  "name": "kathleen",
@@ -3729,6 +3789,36 @@
3729
  },
3730
  "aliases": []
3731
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3732
  "en_US-ryan-high": {
3733
  "key": "en_US-ryan-high",
3734
  "name": "ryan",
@@ -4751,8 +4841,8 @@
4751
  "md5_digest": "3a44e73b12ca5d0c21a72e388b5847c8"
4752
  },
4753
  "it/it_IT/paola/medium/it_IT-paola-medium.onnx.json": {
4754
- "size_bytes": 7100,
4755
- "md5_digest": "3c983f7292518f042b4d137b2dfe65b3"
4756
  },
4757
  "it/it_IT/paola/medium/MODEL_CARD": {
4758
  "size_bytes": 303,
 
1436
  },
1437
  "aliases": []
1438
  },
1439
+ "en_US-bryce-medium": {
1440
+ "key": "en_US-bryce-medium",
1441
+ "name": "bryce",
1442
+ "language": {
1443
+ "code": "en_US",
1444
+ "family": "en",
1445
+ "region": "US",
1446
+ "name_native": "English",
1447
+ "name_english": "English",
1448
+ "country_english": "United States"
1449
+ },
1450
+ "quality": "medium",
1451
+ "num_speakers": 1,
1452
+ "speaker_id_map": {},
1453
+ "files": {
1454
+ "en/en_US/bryce/medium/en_US-bryce-medium.onnx": {
1455
+ "size_bytes": 63531379,
1456
+ "md5_digest": "a8482817c3bdc3d20121a0e31bfa9809"
1457
+ },
1458
+ "en/en_US/bryce/medium/en_US-bryce-medium.onnx.json": {
1459
+ "size_bytes": 4966,
1460
+ "md5_digest": "a548d1d4ce8579f5a16926bdec77c7bf"
1461
+ },
1462
+ "en/en_US/bryce/medium/MODEL_CARD": {
1463
+ "size_bytes": 405,
1464
+ "md5_digest": "79f21fcb165d0fcc4680222164bbb569"
1465
+ }
1466
+ },
1467
+ "aliases": []
1468
+ },
1469
  "en_US-danny-low": {
1470
  "key": "en_US-danny-low",
1471
  "name": "danny",
 
1586
  },
1587
  "aliases": []
1588
  },
1589
+ "en_US-john-medium": {
1590
+ "key": "en_US-john-medium",
1591
+ "name": "john",
1592
+ "language": {
1593
+ "code": "en_US",
1594
+ "family": "en",
1595
+ "region": "US",
1596
+ "name_native": "English",
1597
+ "name_english": "English",
1598
+ "country_english": "United States"
1599
+ },
1600
+ "quality": "medium",
1601
+ "num_speakers": 1,
1602
+ "speaker_id_map": {},
1603
+ "files": {
1604
+ "en/en_US/john/medium/en_US-john-medium.onnx": {
1605
+ "size_bytes": 63531379,
1606
+ "md5_digest": "70480857f21f2560f3a232722023b36d"
1607
+ },
1608
+ "en/en_US/john/medium/en_US-john-medium.onnx.json": {
1609
+ "size_bytes": 4965,
1610
+ "md5_digest": "f2d04611b498e14d394385d1ec8a2d2d"
1611
+ },
1612
+ "en/en_US/john/medium/MODEL_CARD": {
1613
+ "size_bytes": 498,
1614
+ "md5_digest": "4ef938585cf2cc8da4ada9b6d2c579ec"
1615
+ }
1616
+ },
1617
+ "aliases": []
1618
+ },
1619
  "en_US-kathleen-low": {
1620
  "key": "en_US-kathleen-low",
1621
  "name": "kathleen",
 
3789
  },
3790
  "aliases": []
3791
  },
3792
+ "en_US-norman-medium": {
3793
+ "key": "en_US-norman-medium",
3794
+ "name": "norman",
3795
+ "language": {
3796
+ "code": "en_US",
3797
+ "family": "en",
3798
+ "region": "US",
3799
+ "name_native": "English",
3800
+ "name_english": "English",
3801
+ "country_english": "United States"
3802
+ },
3803
+ "quality": "medium",
3804
+ "num_speakers": 1,
3805
+ "speaker_id_map": {},
3806
+ "files": {
3807
+ "en/en_US/norman/medium/en_US-norman-medium.onnx": {
3808
+ "size_bytes": 63531379,
3809
+ "md5_digest": "829cea515dc724d694b83b71e8083f9f"
3810
+ },
3811
+ "en/en_US/norman/medium/en_US-norman-medium.onnx.json": {
3812
+ "size_bytes": 4968,
3813
+ "md5_digest": "975830d6f230f6eccf657d265de99eba"
3814
+ },
3815
+ "en/en_US/norman/medium/MODEL_CARD": {
3816
+ "size_bytes": 528,
3817
+ "md5_digest": "c34f20bbc4918681ad7a070a8321f2fa"
3818
+ }
3819
+ },
3820
+ "aliases": []
3821
+ },
3822
  "en_US-ryan-high": {
3823
  "key": "en_US-ryan-high",
3824
  "name": "ryan",
 
4841
  "md5_digest": "3a44e73b12ca5d0c21a72e388b5847c8"
4842
  },
4843
  "it/it_IT/paola/medium/it_IT-paola-medium.onnx.json": {
4844
+ "size_bytes": 7099,
4845
+ "md5_digest": "cd471a3757c88a7a4baee6207248b5d5"
4846
  },
4847
  "it/it_IT/paola/medium/MODEL_CARD": {
4848
  "size_bytes": 303,