ONNX
Michael Hansen commited on
Commit
36915ed
·
1 Parent(s): aae8b0c

Add chitwan (ne)

Browse files
_script/voicefest.py CHANGED
@@ -34,6 +34,7 @@ _LANGUAGES = {
34
  "fr_FR": Language("Français", "French", "France"),
35
  "is_IS": Language("íslenska", "Icelandic", "Iceland"),
36
  "it_IT": Language("Italiano", "Italian", "Italy"),
 
37
  "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
38
  "ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
39
  "kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
 
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"),
39
  "ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
40
  "kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
ml/ml_IN/arjun/medium/samples/speaker_0.mp3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ecde975f20844339bdaafa77febac2437abc9861d90beb23b60a65b3999f95
3
+ size 87815
ml/ml_IN/meera/medium/samples/speaker_0.mp3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0968cfdbad943b882e5e724ccb10d251382b0506aacde156b7e68af95db85de9
3
+ size 73949
ne/ne_NP/chitwan/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for chitwan (medium)
2
+
3
+ * Language: ne_NP (Nepali, Nepal)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://github.com/NabuCasa/voice-datasets
11
+ * License: CC0
12
+
13
+ ## Training
14
+
15
+ Finetuned from U.S. English lessac voice (medium quality)
ne/ne_NP/chitwan/medium/ne_NP-chitwan-medium.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ba6b0927688f92717e93ca52bc06f5783ce8edc765d5f85365acef1d41822c
3
+ size 62950044
ne/ne_NP/chitwan/medium/ne_NP-chitwan-medium.onnx.json ADDED
@@ -0,0 +1,512 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050,
4
+ "quality": "medium"
5
+ },
6
+ "espeak": {
7
+ "voice": "ne"
8
+ },
9
+ "phoneme_type": "espeak",
10
+ "piper_version": "1.3.0",
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
+ },
503
+ "language": {
504
+ "code": "ne_NP",
505
+ "family": "ne",
506
+ "region": "NP",
507
+ "name_native": "नेपाली",
508
+ "name_english": "Nepali",
509
+ "country_english": "Nepal"
510
+ },
511
+ "dataset": "chitwan"
512
+ }
ne/ne_NP/chitwan/medium/samples/speaker_0.mp3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642fc6f43269f0bf4570ec80efd1a1d99f6f9fbc955e92113d1c14d12d6aa9a3
3
+ size 498941
voices.json CHANGED
@@ -4791,6 +4791,36 @@
4791
  },
4792
  "aliases": []
4793
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4794
  "hu_HU-anna-medium": {
4795
  "key": "hu_HU-anna-medium",
4796
  "name": "anna",
@@ -5324,6 +5354,36 @@
5324
  },
5325
  "aliases": []
5326
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5327
  "ne_NP-google-medium": {
5328
  "key": "ne_NP-google-medium",
5329
  "name": "google",
 
4791
  },
4792
  "aliases": []
4793
  },
4794
+ "he_IL-motek-medium": {
4795
+ "key": "he_IL-motek-medium",
4796
+ "name": "motek",
4797
+ "language": {
4798
+ "code": "he_IL",
4799
+ "family": "he",
4800
+ "region": "IL",
4801
+ "name_native": "עברית",
4802
+ "name_english": "Hebrew",
4803
+ "country_english": "Israel"
4804
+ },
4805
+ "quality": "medium",
4806
+ "num_speakers": 1,
4807
+ "speaker_id_map": {},
4808
+ "files": {
4809
+ "he/he_IL/motek/medium/he_IL-motek-medium.onnx": {
4810
+ "size_bytes": 62950044,
4811
+ "md5_digest": "a7462637b7e43bba0f28e1db93bc538e"
4812
+ },
4813
+ "he/he_IL/motek/medium/he_IL-motek-medium.onnx.json": {
4814
+ "size_bytes": 5034,
4815
+ "md5_digest": "3853c4e2a2e4b7beafac2525f385f226"
4816
+ },
4817
+ "he/he_IL/motek/medium/MODEL_CARD": {
4818
+ "size_bytes": 290,
4819
+ "md5_digest": "c2a5c0e238ae9d2a5aec7d212a44a4ce"
4820
+ }
4821
+ },
4822
+ "aliases": []
4823
+ },
4824
  "hu_HU-anna-medium": {
4825
  "key": "hu_HU-anna-medium",
4826
  "name": "anna",
 
5354
  },
5355
  "aliases": []
5356
  },
5357
+ "ne_NP-chitwan-medium": {
5358
+ "key": "ne_NP-chitwan-medium",
5359
+ "name": "chitwan",
5360
+ "language": {
5361
+ "code": "ne_NP",
5362
+ "family": "ne",
5363
+ "region": "NP",
5364
+ "name_native": "नेपाली",
5365
+ "name_english": "Nepali",
5366
+ "country_english": "Nepal"
5367
+ },
5368
+ "quality": "medium",
5369
+ "num_speakers": 1,
5370
+ "speaker_id_map": {},
5371
+ "files": {
5372
+ "ne/ne_NP/chitwan/medium/ne_NP-chitwan-medium.onnx": {
5373
+ "size_bytes": 62950044,
5374
+ "md5_digest": "74cdb5b32816c366af74b55ed7494e25"
5375
+ },
5376
+ "ne/ne_NP/chitwan/medium/ne_NP-chitwan-medium.onnx.json": {
5377
+ "size_bytes": 5043,
5378
+ "md5_digest": "7ddc520e24a862016f6d22cde4b70ac1"
5379
+ },
5380
+ "ne/ne_NP/chitwan/medium/MODEL_CARD": {
5381
+ "size_bytes": 275,
5382
+ "md5_digest": "dcd35df097f84ace498d7afeb5b1a29c"
5383
+ }
5384
+ },
5385
+ "aliases": []
5386
+ },
5387
  "ne_NP-google-medium": {
5388
  "key": "ne_NP-google-medium",
5389
  "name": "google",