spybyscript commited on
Commit
37ee05c
·
verified ·
1 Parent(s): 9f7e3d1

Publish Scyllas Band v2 ONNX INT8 bundle

Browse files
Files changed (42) hide show
  1. onnx-int8/assets/emotions.json +391 -0
  2. onnx-int8/assets/g2p/export_config.json +29 -0
  3. onnx-int8/assets/g2p/language_map.json +47 -0
  4. onnx-int8/assets/g2p/normalization.json +46 -0
  5. onnx-int8/assets/g2p/phoneme_dict.json +9 -0
  6. onnx-int8/assets/g2p/pronunciation_overrides.json +4 -0
  7. onnx-int8/assets/g2p/tokenizer.json +517 -0
  8. onnx-int8/assets/languages.json +795 -0
  9. onnx-int8/assets/phone_vocab.json +111 -0
  10. onnx-int8/assets/voice_packs/ariadne.npz +3 -0
  11. onnx-int8/assets/voice_packs/felix.npz +3 -0
  12. onnx-int8/assets/voice_packs/gwen.npz +3 -0
  13. onnx-int8/assets/voice_packs/ink.npz +3 -0
  14. onnx-int8/assets/voice_packs/max.npz +3 -0
  15. onnx-int8/assets/voice_packs/orpheus.npz +3 -0
  16. onnx-int8/assets/voice_packs/reference_packs.json +916 -0
  17. onnx-int8/assets/voice_packs/rex.npz +3 -0
  18. onnx-int8/assets/voice_packs/scylla.npz +3 -0
  19. onnx-int8/assets/voice_packs/stone.npz +3 -0
  20. onnx-int8/assets/voice_packs/tuesday.npz +3 -0
  21. onnx-int8/assets/voices.json +972 -0
  22. onnx-int8/manifest.json +950 -0
  23. onnx-int8/onnx/components/duration_predictor.onnx +3 -0
  24. onnx-int8/onnx/components/shared_weights.bin +3 -0
  25. onnx-int8/onnx/components/shared_weights.json +0 -0
  26. onnx-int8/onnx/components/vector_context_encoder.onnx +3 -0
  27. onnx-int8/onnx/components/vector_estimator_b256.onnx +3 -0
  28. onnx-int8/onnx/components/vector_estimator_b384.onnx +3 -0
  29. onnx-int8/onnx/components/vector_estimator_b512.onnx +3 -0
  30. onnx-int8/onnx/components/vector_estimator_b640.onnx +3 -0
  31. onnx-int8/onnx/components/vocoder_adapter_b256.onnx +3 -0
  32. onnx-int8/onnx/components/vocoder_adapter_b384.onnx +3 -0
  33. onnx-int8/onnx/components/vocoder_adapter_b512.onnx +3 -0
  34. onnx-int8/onnx/components/vocoder_adapter_b640.onnx +3 -0
  35. onnx-int8/onnx/components/vocoder_b256.onnx +3 -0
  36. onnx-int8/onnx/components/vocoder_b384.onnx +3 -0
  37. onnx-int8/onnx/components/vocoder_b512.onnx +3 -0
  38. onnx-int8/onnx/components/vocoder_b640.onnx +3 -0
  39. onnx-int8/onnx/g2p/export_config.json +29 -0
  40. onnx-int8/onnx/g2p/model.onnx +3 -0
  41. onnx-int8/onnx/g2p/phoneme_dict.json +9 -0
  42. onnx-int8/onnx/g2p/tokenizer.json +517 -0
onnx-int8/assets/emotions.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "neutral",
4
+ "index": 0,
5
+ "samples": 44411,
6
+ "duration_seconds": 181320.9682500002,
7
+ "by_split": {
8
+ "train": 43460,
9
+ "val": 951
10
+ },
11
+ "by_voice": {
12
+ "ariadne": 4226,
13
+ "felix": 4504,
14
+ "gwen": 4444,
15
+ "ink": 4701,
16
+ "max": 4836,
17
+ "orpheus": 4792,
18
+ "rex": 4750,
19
+ "scylla": 4452,
20
+ "stone": 2848,
21
+ "tuesday": 4858
22
+ },
23
+ "by_language": {
24
+ "de": 430,
25
+ "en_gb": 9395,
26
+ "en_us": 19248,
27
+ "es": 6013,
28
+ "fr": 348,
29
+ "it": 8611,
30
+ "vi": 366
31
+ }
32
+ },
33
+ {
34
+ "id": "friendly",
35
+ "index": 1,
36
+ "samples": 26566,
37
+ "duration_seconds": 104009.00308333337,
38
+ "by_split": {
39
+ "train": 26566
40
+ },
41
+ "by_voice": {
42
+ "ariadne": 2801,
43
+ "felix": 2764,
44
+ "gwen": 2556,
45
+ "ink": 2939,
46
+ "max": 2683,
47
+ "orpheus": 2828,
48
+ "rex": 2636,
49
+ "scylla": 2544,
50
+ "stone": 2388,
51
+ "tuesday": 2427
52
+ },
53
+ "by_language": {
54
+ "en_gb": 4976,
55
+ "en_us": 10192,
56
+ "es": 4296,
57
+ "it": 7102
58
+ }
59
+ },
60
+ {
61
+ "id": "happy",
62
+ "index": 2,
63
+ "samples": 26934,
64
+ "duration_seconds": 107033.57025000086,
65
+ "by_split": {
66
+ "test": 6,
67
+ "train": 26928
68
+ },
69
+ "by_voice": {
70
+ "ariadne": 2957,
71
+ "felix": 2741,
72
+ "gwen": 2539,
73
+ "ink": 2850,
74
+ "max": 2746,
75
+ "orpheus": 2907,
76
+ "rex": 2757,
77
+ "scylla": 2670,
78
+ "stone": 2312,
79
+ "tuesday": 2455
80
+ },
81
+ "by_language": {
82
+ "de": 436,
83
+ "en_gb": 4611,
84
+ "en_us": 9702,
85
+ "es": 4608,
86
+ "fr": 336,
87
+ "it": 6887,
88
+ "vi": 354
89
+ }
90
+ },
91
+ {
92
+ "id": "excited",
93
+ "index": 3,
94
+ "samples": 27321,
95
+ "duration_seconds": 107528.56516666667,
96
+ "by_split": {
97
+ "train": 25344,
98
+ "val": 1977
99
+ },
100
+ "by_voice": {
101
+ "ariadne": 3022,
102
+ "felix": 2854,
103
+ "gwen": 2067,
104
+ "ink": 2952,
105
+ "max": 2814,
106
+ "orpheus": 2813,
107
+ "rex": 1998,
108
+ "scylla": 2689,
109
+ "stone": 3284,
110
+ "tuesday": 2828
111
+ },
112
+ "by_language": {
113
+ "en_gb": 4701,
114
+ "en_us": 10933,
115
+ "es": 4851,
116
+ "it": 6836
117
+ }
118
+ },
119
+ {
120
+ "id": "angry",
121
+ "index": 4,
122
+ "samples": 26969,
123
+ "duration_seconds": 107998.27783333347,
124
+ "by_split": {
125
+ "train": 26084,
126
+ "val": 885
127
+ },
128
+ "by_voice": {
129
+ "ariadne": 3081,
130
+ "felix": 2667,
131
+ "gwen": 2792,
132
+ "ink": 2199,
133
+ "max": 2821,
134
+ "orpheus": 2975,
135
+ "rex": 1897,
136
+ "scylla": 2932,
137
+ "stone": 2485,
138
+ "tuesday": 3120
139
+ },
140
+ "by_language": {
141
+ "de": 390,
142
+ "en_gb": 4979,
143
+ "en_us": 9900,
144
+ "es": 4734,
145
+ "fr": 361,
146
+ "it": 6284,
147
+ "vi": 321
148
+ }
149
+ },
150
+ {
151
+ "id": "frustrated",
152
+ "index": 5,
153
+ "samples": 21094,
154
+ "duration_seconds": 82796.8460416663,
155
+ "by_split": {
156
+ "train": 20410,
157
+ "val": 684
158
+ },
159
+ "by_voice": {
160
+ "ariadne": 2420,
161
+ "felix": 2081,
162
+ "gwen": 2113,
163
+ "ink": 1819,
164
+ "max": 2162,
165
+ "orpheus": 2441,
166
+ "rex": 1550,
167
+ "scylla": 2193,
168
+ "stone": 1806,
169
+ "tuesday": 2509
170
+ },
171
+ "by_language": {
172
+ "en_gb": 4458,
173
+ "en_us": 8686,
174
+ "es": 3305,
175
+ "it": 4645
176
+ }
177
+ },
178
+ {
179
+ "id": "sad",
180
+ "index": 6,
181
+ "samples": 22259,
182
+ "duration_seconds": 88170.71104166657,
183
+ "by_split": {
184
+ "test": 191,
185
+ "train": 22068
186
+ },
187
+ "by_voice": {
188
+ "ariadne": 2368,
189
+ "felix": 2044,
190
+ "gwen": 2020,
191
+ "ink": 2026,
192
+ "max": 2296,
193
+ "orpheus": 2328,
194
+ "rex": 2389,
195
+ "scylla": 2326,
196
+ "stone": 1952,
197
+ "tuesday": 2510
198
+ },
199
+ "by_language": {
200
+ "de": 454,
201
+ "en_gb": 4100,
202
+ "en_us": 8366,
203
+ "es": 3760,
204
+ "fr": 342,
205
+ "it": 4894,
206
+ "vi": 343
207
+ }
208
+ },
209
+ {
210
+ "id": "sarcastic",
211
+ "index": 7,
212
+ "samples": 24769,
213
+ "duration_seconds": 97825.94508333287,
214
+ "by_split": {
215
+ "train": 24769
216
+ },
217
+ "by_voice": {
218
+ "ariadne": 2771,
219
+ "felix": 2447,
220
+ "gwen": 2245,
221
+ "ink": 2691,
222
+ "max": 2625,
223
+ "orpheus": 2450,
224
+ "rex": 2445,
225
+ "scylla": 2243,
226
+ "stone": 2147,
227
+ "tuesday": 2705
228
+ },
229
+ "by_language": {
230
+ "en_gb": 4018,
231
+ "en_us": 8753,
232
+ "es": 5037,
233
+ "it": 6961
234
+ }
235
+ },
236
+ {
237
+ "id": "unsure",
238
+ "index": 8,
239
+ "samples": 18952,
240
+ "duration_seconds": 74308.31512500055,
241
+ "by_split": {
242
+ "train": 18952
243
+ },
244
+ "by_voice": {
245
+ "ariadne": 2095,
246
+ "felix": 2027,
247
+ "gwen": 1919,
248
+ "ink": 995,
249
+ "max": 2024,
250
+ "orpheus": 2168,
251
+ "rex": 1941,
252
+ "scylla": 1900,
253
+ "stone": 1805,
254
+ "tuesday": 2078
255
+ },
256
+ "by_language": {
257
+ "en_gb": 2282,
258
+ "en_us": 7363,
259
+ "es": 3743,
260
+ "it": 5564
261
+ }
262
+ },
263
+ {
264
+ "id": "anger",
265
+ "index": 9,
266
+ "samples": 1014161,
267
+ "duration_seconds": 4027756.9014583966,
268
+ "by_split": {
269
+ "test": 14399,
270
+ "train": 979373,
271
+ "val": 20389
272
+ },
273
+ "by_voice": {
274
+ "ariadne": 113699,
275
+ "felix": 97394,
276
+ "gwen": 96722,
277
+ "ink": 100018,
278
+ "max": 106674,
279
+ "orpheus": 104220,
280
+ "rex": 105673,
281
+ "scylla": 97926,
282
+ "stone": 84975,
283
+ "tuesday": 106860
284
+ },
285
+ "by_language": {
286
+ "de": 157088,
287
+ "en_gb": 85322,
288
+ "en_us": 179570,
289
+ "es": 165314,
290
+ "fr": 151353,
291
+ "it": 181826,
292
+ "vi": 93688
293
+ }
294
+ },
295
+ {
296
+ "id": "calm",
297
+ "index": 10,
298
+ "samples": 822328,
299
+ "duration_seconds": 3276813.5683750194,
300
+ "by_split": {
301
+ "test": 13959,
302
+ "train": 794831,
303
+ "val": 13538
304
+ },
305
+ "by_voice": {
306
+ "ariadne": 88083,
307
+ "felix": 78796,
308
+ "gwen": 74923,
309
+ "ink": 88019,
310
+ "max": 83256,
311
+ "orpheus": 86078,
312
+ "rex": 84890,
313
+ "scylla": 75811,
314
+ "stone": 74298,
315
+ "tuesday": 88174
316
+ },
317
+ "by_language": {
318
+ "de": 116192,
319
+ "en_gb": 48964,
320
+ "en_us": 103806,
321
+ "es": 162958,
322
+ "fr": 113339,
323
+ "it": 182696,
324
+ "vi": 94373
325
+ }
326
+ },
327
+ {
328
+ "id": "joy",
329
+ "index": 11,
330
+ "samples": 1004406,
331
+ "duration_seconds": 3944400.962499914,
332
+ "by_split": {
333
+ "test": 6530,
334
+ "train": 987181,
335
+ "val": 10695
336
+ },
337
+ "by_voice": {
338
+ "ariadne": 112961,
339
+ "felix": 101462,
340
+ "gwen": 98640,
341
+ "ink": 112067,
342
+ "max": 102374,
343
+ "orpheus": 95909,
344
+ "rex": 104647,
345
+ "scylla": 99116,
346
+ "stone": 74390,
347
+ "tuesday": 102840
348
+ },
349
+ "by_language": {
350
+ "de": 145774,
351
+ "en_gb": 79611,
352
+ "en_us": 175654,
353
+ "es": 180038,
354
+ "fr": 142231,
355
+ "it": 185312,
356
+ "vi": 95786
357
+ }
358
+ },
359
+ {
360
+ "id": "sadness",
361
+ "index": 12,
362
+ "samples": 1037987,
363
+ "duration_seconds": 4084567.352125135,
364
+ "by_split": {
365
+ "test": 13064,
366
+ "train": 1014587,
367
+ "val": 10336
368
+ },
369
+ "by_voice": {
370
+ "ariadne": 115408,
371
+ "felix": 102310,
372
+ "gwen": 104395,
373
+ "ink": 112271,
374
+ "max": 107074,
375
+ "orpheus": 103235,
376
+ "rex": 101840,
377
+ "scylla": 101403,
378
+ "stone": 84431,
379
+ "tuesday": 105620
380
+ },
381
+ "by_language": {
382
+ "de": 156159,
383
+ "en_gb": 92216,
384
+ "en_us": 182900,
385
+ "es": 174278,
386
+ "fr": 147561,
387
+ "it": 185577,
388
+ "vi": 99296
389
+ }
390
+ }
391
+ ]
onnx-int8/assets/g2p/export_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "scyllasband_g2p",
3
+ "source_checkpoint": "output/deepphonemizer_multilingual/model_v10_7lang/checkpoints/model_step_250k.pt",
4
+ "opset": 18,
5
+ "languages": [
6
+ "de",
7
+ "en_gb",
8
+ "en_us",
9
+ "es",
10
+ "fr",
11
+ "it",
12
+ "vi"
13
+ ],
14
+ "model_type": "transformer",
15
+ "input_granularity": "phrase",
16
+ "training_mix": "phrase_word_chunked_clean",
17
+ "phoneme_token_mode": "char",
18
+ "phrase_rows_per_language": 200000,
19
+ "word_rows_per_language": 200000,
20
+ "batch_dynamic": true,
21
+ "onnx_exporter": "dynamo",
22
+ "onnx_export_layout": "batch_first",
23
+ "onnx_padded_output": "ctc_blank",
24
+ "onnx_export_batch_size": 4,
25
+ "onnx_export_max_batch_size": 256,
26
+ "onnx_quantization": "dynamic_int8",
27
+ "onnx_fp32_model": "model.fp32.onnx",
28
+ "onnx_quantized_parity_tolerance": 3.0
29
+ }
onnx-int8/assets/g2p/language_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "american": "en_us",
3
+ "american_english": "en_us",
4
+ "british": "en_gb",
5
+ "british_english": "en_gb",
6
+ "de": "de",
7
+ "de_de": "de",
8
+ "deu": "de",
9
+ "en": "en_us",
10
+ "en-gb": "en_gb",
11
+ "en-uk": "en_gb",
12
+ "en-us": "en_us",
13
+ "en_gb": "en_gb",
14
+ "en_uk": "en_gb",
15
+ "en_us": "en_us",
16
+ "eng": "en_us",
17
+ "eng_gb": "en_gb",
18
+ "eng_us": "en_us",
19
+ "english": "en_us",
20
+ "english_gb": "en_gb",
21
+ "english_uk": "en_gb",
22
+ "english_us": "en_us",
23
+ "es": "es",
24
+ "es_es": "es",
25
+ "es_mx": "es",
26
+ "fr": "fr",
27
+ "fr_fr": "fr",
28
+ "fra": "fr",
29
+ "fre": "fr",
30
+ "french": "fr",
31
+ "gb": "en_gb",
32
+ "ger": "de",
33
+ "german": "de",
34
+ "it": "it",
35
+ "it_it": "it",
36
+ "ita": "it",
37
+ "italian": "it",
38
+ "spa": "es",
39
+ "spanish": "es",
40
+ "uk": "en_gb",
41
+ "us": "en_us",
42
+ "vi": "vi",
43
+ "vi_hn": "vi",
44
+ "vi_vn": "vi",
45
+ "vie": "vi",
46
+ "vietnamese": "vi"
47
+ }
onnx-int8/assets/g2p/normalization.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "normalizer": "SpokenTextNormalizer",
3
+ "languages": [
4
+ "en",
5
+ "en_us",
6
+ "en_gb",
7
+ "es",
8
+ "it",
9
+ "fr",
10
+ "de",
11
+ "vi"
12
+ ],
13
+ "expand_currency": true,
14
+ "expand_numbers": true,
15
+ "expand_ordinals": true,
16
+ "expand_percentages": true,
17
+ "expand_times": true,
18
+ "expand_dates": true,
19
+ "normalize_at_sign": true,
20
+ "normalize_punctuation": true,
21
+ "contract_version": "scyllasband_spoken_text_v2_2026_08_05",
22
+ "contract_sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
23
+ "contract": {
24
+ "version": "scyllasband_spoken_text_v2_2026_08_05",
25
+ "training_phone_source": "espeak",
26
+ "ok_spoken_form": "okay",
27
+ "mixed_question_exclamation": "leading_mark",
28
+ "homogeneous_terminal_runs": "single_mark",
29
+ "dot_runs_two_or_more": "ellipsis_three_dots",
30
+ "colon_semicolon_classes": "preserved",
31
+ "lexical_hyphen": "space_no_pause",
32
+ "syntactic_dash": "em_dash_pause",
33
+ "punctuation_silence_target": "explicit_silence",
34
+ "non_acoustic_modifiers": [
35
+ "stress",
36
+ "length",
37
+ "unicode_combining"
38
+ ]
39
+ },
40
+ "punctuation_token_remap": {
41
+ "<ellipsis>": "<sil>",
42
+ "<end_exclaim>": "<sil>",
43
+ "<end_question>": "<sil>"
44
+ },
45
+ "punctuation_token_remap_scope": "continuation_only"
46
+ }
onnx-int8/assets/g2p/phoneme_dict.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "de": {},
3
+ "en_gb": {},
4
+ "en_us": {},
5
+ "es": {},
6
+ "fr": {},
7
+ "it": {},
8
+ "vi": {}
9
+ }
onnx-int8/assets/g2p/pronunciation_overrides.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "format": "scyllasband_g2p_pronunciation_overrides_v1",
3
+ "languages": {}
4
+ }
onnx-int8/assets/g2p/tokenizer.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "deepphonemizer_forward_ctc",
3
+ "languages": [
4
+ "de",
5
+ "en_gb",
6
+ "en_us",
7
+ "es",
8
+ "fr",
9
+ "it",
10
+ "vi"
11
+ ],
12
+ "char_repeats": 4,
13
+ "lowercase": true,
14
+ "phoneme_token_mode": "char",
15
+ "text_symbols": {
16
+ "_": 0,
17
+ "<de>": 1,
18
+ "<en_gb>": 2,
19
+ "<en_us>": 3,
20
+ "<es>": 4,
21
+ "<fr>": 5,
22
+ "<it>": 6,
23
+ "<vi>": 7,
24
+ "<end>": 8,
25
+ "\b": 9,
26
+ " ": 10,
27
+ "!": 11,
28
+ "\"": 12,
29
+ "#": 13,
30
+ "$": 14,
31
+ "%": 15,
32
+ "&": 16,
33
+ "'": 17,
34
+ "(": 18,
35
+ ")": 19,
36
+ "*": 20,
37
+ "+": 21,
38
+ ",": 22,
39
+ "-": 23,
40
+ ".": 24,
41
+ "/": 25,
42
+ "0": 26,
43
+ "1": 27,
44
+ "2": 28,
45
+ "3": 29,
46
+ "4": 30,
47
+ "5": 31,
48
+ "6": 32,
49
+ "7": 33,
50
+ "8": 34,
51
+ "9": 35,
52
+ ":": 36,
53
+ ";": 37,
54
+ "<": 38,
55
+ "=": 39,
56
+ ">": 40,
57
+ "?": 41,
58
+ "@": 42,
59
+ "A": 43,
60
+ "B": 44,
61
+ "C": 45,
62
+ "D": 46,
63
+ "E": 47,
64
+ "F": 48,
65
+ "G": 49,
66
+ "H": 50,
67
+ "I": 51,
68
+ "J": 52,
69
+ "K": 53,
70
+ "L": 54,
71
+ "M": 55,
72
+ "N": 56,
73
+ "O": 57,
74
+ "P": 58,
75
+ "Q": 59,
76
+ "R": 60,
77
+ "S": 61,
78
+ "T": 62,
79
+ "U": 63,
80
+ "V": 64,
81
+ "W": 65,
82
+ "X": 66,
83
+ "Y": 67,
84
+ "Z": 68,
85
+ "[": 69,
86
+ "\\": 70,
87
+ "]": 71,
88
+ "^": 72,
89
+ "`": 73,
90
+ "a": 74,
91
+ "b": 75,
92
+ "c": 76,
93
+ "d": 77,
94
+ "e": 78,
95
+ "f": 79,
96
+ "g": 80,
97
+ "h": 81,
98
+ "i": 82,
99
+ "j": 83,
100
+ "k": 84,
101
+ "l": 85,
102
+ "m": 86,
103
+ "n": 87,
104
+ "o": 88,
105
+ "p": 89,
106
+ "q": 90,
107
+ "r": 91,
108
+ "s": 92,
109
+ "t": 93,
110
+ "u": 94,
111
+ "v": 95,
112
+ "w": 96,
113
+ "x": 97,
114
+ "y": 98,
115
+ "z": 99,
116
+ "{": 100,
117
+ "|": 101,
118
+ "}": 102,
119
+ "~": 103,
120
+ "¡": 104,
121
+ "¢": 105,
122
+ "£": 106,
123
+ "¥": 107,
124
+ "§": 108,
125
+ "ª": 109,
126
+ "«": 110,
127
+ "­": 111,
128
+ "®": 112,
129
+ "°": 113,
130
+ "±": 114,
131
+ "²": 115,
132
+ "³": 116,
133
+ "´": 117,
134
+ "¶": 118,
135
+ "·": 119,
136
+ "¹": 120,
137
+ "º": 121,
138
+ "»": 122,
139
+ "¼": 123,
140
+ "½": 124,
141
+ "¾": 125,
142
+ "¿": 126,
143
+ "À": 127,
144
+ "Á": 128,
145
+ "Â": 129,
146
+ "Ä": 130,
147
+ "Å": 131,
148
+ "Æ": 132,
149
+ "Ç": 133,
150
+ "È": 134,
151
+ "É": 135,
152
+ "Ê": 136,
153
+ "Í": 137,
154
+ "Ï": 138,
155
+ "Ñ": 139,
156
+ "Ó": 140,
157
+ "Ô": 141,
158
+ "Ö": 142,
159
+ "×": 143,
160
+ "Ù": 144,
161
+ "Ú": 145,
162
+ "Ü": 146,
163
+ "Ý": 147,
164
+ "Þ": 148,
165
+ "ß": 149,
166
+ "à": 150,
167
+ "á": 151,
168
+ "â": 152,
169
+ "ã": 153,
170
+ "ä": 154,
171
+ "å": 155,
172
+ "æ": 156,
173
+ "ç": 157,
174
+ "è": 158,
175
+ "é": 159,
176
+ "ê": 160,
177
+ "ë": 161,
178
+ "ì": 162,
179
+ "í": 163,
180
+ "î": 164,
181
+ "ï": 165,
182
+ "ð": 166,
183
+ "ñ": 167,
184
+ "ò": 168,
185
+ "ó": 169,
186
+ "ô": 170,
187
+ "õ": 171,
188
+ "ö": 172,
189
+ "ø": 173,
190
+ "ù": 174,
191
+ "ú": 175,
192
+ "û": 176,
193
+ "ü": 177,
194
+ "ý": 178,
195
+ "þ": 179,
196
+ "ÿ": 180,
197
+ "ā": 181,
198
+ "Ă": 182,
199
+ "ă": 183,
200
+ "ą": 184,
201
+ "ć": 185,
202
+ "č": 186,
203
+ "Đ": 187,
204
+ "đ": 188,
205
+ "ē": 189,
206
+ "ė": 190,
207
+ "ę": 191,
208
+ "ğ": 192,
209
+ "ġ": 193,
210
+ "ĩ": 194,
211
+ "ī": 195,
212
+ "ļ": 196,
213
+ "ł": 197,
214
+ "ń": 198,
215
+ "Ō": 199,
216
+ "ō": 200,
217
+ "Œ": 201,
218
+ "œ": 202,
219
+ "ŕ": 203,
220
+ "ś": 204,
221
+ "ş": 205,
222
+ "š": 206,
223
+ "ŧ": 207,
224
+ "ũ": 208,
225
+ "ū": 209,
226
+ "ŭ": 210,
227
+ "ů": 211,
228
+ "ű": 212,
229
+ "ż": 213,
230
+ "Ž": 214,
231
+ "ž": 215,
232
+ "ſ": 216,
233
+ "Ơ": 217,
234
+ "ơ": 218,
235
+ "Ư": 219,
236
+ "ư": 220,
237
+ "ǁ": 221,
238
+ "ǂ": 222,
239
+ "ǐ": 223,
240
+ "ǘ": 224,
241
+ "ǧ": 225,
242
+ "ș": 226,
243
+ "Ȝ": 227,
244
+ "ȝ": 228,
245
+ "ȟ": 229,
246
+ "ɛ": 230,
247
+ "ʰ": 231,
248
+ "ˆ": 232,
249
+ "ˈ": 233,
250
+ "ˢ": 234,
251
+ "̃": 235,
252
+ "̍": 236,
253
+ "̣": 237,
254
+ "̱": 238,
255
+ "͈": 239,
256
+ "α": 240,
257
+ "β": 241,
258
+ "γ": 242,
259
+ "δ": 243,
260
+ "ε": 244,
261
+ "η": 245,
262
+ "κ": 246,
263
+ "μ": 247,
264
+ "ξ": 248,
265
+ "π": 249,
266
+ "ς": 250,
267
+ "σ": 251,
268
+ "χ": 252,
269
+ "ψ": 253,
270
+ "а": 254,
271
+ "д": 255,
272
+ "е": 256,
273
+ "з": 257,
274
+ "и": 258,
275
+ "к": 259,
276
+ "л": 260,
277
+ "о": 261,
278
+ "п": 262,
279
+ "р": 263,
280
+ "с": 264,
281
+ "т": 265,
282
+ "ч": 266,
283
+ "ь": 267,
284
+ "ง": 268,
285
+ "ย": 269,
286
+ "า": 270,
287
+ "่": 271,
288
+ "ည": 272,
289
+ "လ": 273,
290
+ "း": 274,
291
+ "်": 275,
292
+ "ᵈ": 276,
293
+ "ᵗ": 277,
294
+ "ḅ": 278,
295
+ "ḍ": 279,
296
+ "ḳ": 280,
297
+ "ṅ": 281,
298
+ "Ṭ": 282,
299
+ "ẓ": 283,
300
+ "ạ": 284,
301
+ "Ả": 285,
302
+ "ả": 286,
303
+ "Ấ": 287,
304
+ "ấ": 288,
305
+ "ầ": 289,
306
+ "ẩ": 290,
307
+ "ẫ": 291,
308
+ "ậ": 292,
309
+ "ắ": 293,
310
+ "ằ": 294,
311
+ "ẳ": 295,
312
+ "ẵ": 296,
313
+ "ặ": 297,
314
+ "ẹ": 298,
315
+ "ẻ": 299,
316
+ "ẽ": 300,
317
+ "Ế": 301,
318
+ "ế": 302,
319
+ "Ề": 303,
320
+ "ề": 304,
321
+ "ể": 305,
322
+ "ễ": 306,
323
+ "ệ": 307,
324
+ "ỉ": 308,
325
+ "ị": 309,
326
+ "ọ": 310,
327
+ "ỏ": 311,
328
+ "Ố": 312,
329
+ "ố": 313,
330
+ "Ồ": 314,
331
+ "ồ": 315,
332
+ "Ổ": 316,
333
+ "ổ": 317,
334
+ "ỗ": 318,
335
+ "Ộ": 319,
336
+ "ộ": 320,
337
+ "ớ": 321,
338
+ "Ờ": 322,
339
+ "ờ": 323,
340
+ "Ở": 324,
341
+ "ở": 325,
342
+ "ỡ": 326,
343
+ "ợ": 327,
344
+ "ụ": 328,
345
+ "ủ": 329,
346
+ "Ứ": 330,
347
+ "ứ": 331,
348
+ "Ừ": 332,
349
+ "ừ": 333,
350
+ "ử": 334,
351
+ "ữ": 335,
352
+ "ự": 336,
353
+ "ỳ": 337,
354
+ "ỵ": 338,
355
+ "Ỷ": 339,
356
+ "ỷ": 340,
357
+ "ỹ": 341,
358
+ "ὖ": 342,
359
+ "ὼ": 343,
360
+ "ῆ": 344,
361
+ "​": 345,
362
+ "‐": 346,
363
+ "—": 347,
364
+ "―": 348,
365
+ "†": 349,
366
+ "•": 350,
367
+ "…": 351,
368
+ "‰": 352,
369
+ "′": 353,
370
+ "″": 354,
371
+ "⁄": 355,
372
+ "⁷": 356,
373
+ "⁻": 357,
374
+ "₀": 358,
375
+ "₁": 359,
376
+ "₂": 360,
377
+ "₃": 361,
378
+ "₄": 362,
379
+ "₅": 363,
380
+ "₆": 364,
381
+ "₇": 365,
382
+ "₈": 366,
383
+ "€": 367,
384
+ "₹": 368,
385
+ "⅓": 369,
386
+ "⅔": 370,
387
+ "⅖": 371,
388
+ "⅙": 372,
389
+ "⅛": 373,
390
+ "⅝": 374,
391
+ "√": 375,
392
+ "│": 376,
393
+ "♦": 377,
394
+ "⚓": 378,
395
+ "✈": 379,
396
+ "✠": 380,
397
+ "✨": 381,
398
+ "⟙": 382,
399
+ "⸺": 383,
400
+ "。": 384,
401
+ "〈": 385,
402
+ "な": 386,
403
+ "三": 387,
404
+ "次": 388,
405
+ "肿": 389,
406
+ "臃": 390,
407
+ "구": 391,
408
+ "로": 392,
409
+ "요": 393,
410
+ "ﷺ": 394,
411
+ "️": 395,
412
+ "𝑥": 396,
413
+ "𝑦": 397,
414
+ "🌊": 398,
415
+ "🌿": 399,
416
+ "💦": 400,
417
+ "💨": 401
418
+ },
419
+ "phoneme_symbols": {
420
+ "0": "_",
421
+ "1": "<de>",
422
+ "2": "<en_gb>",
423
+ "3": "<en_us>",
424
+ "4": "<es>",
425
+ "5": "<fr>",
426
+ "6": "<it>",
427
+ "7": "<vi>",
428
+ "8": "<end>",
429
+ "9": " ",
430
+ "10": "!",
431
+ "11": ",",
432
+ "12": "-",
433
+ "13": ".",
434
+ "14": "1",
435
+ "15": "2",
436
+ "16": "4",
437
+ "17": "5",
438
+ "18": "6",
439
+ "19": "7",
440
+ "20": ":",
441
+ "21": ";",
442
+ "22": "?",
443
+ "23": "a",
444
+ "24": "b",
445
+ "25": "c",
446
+ "26": "d",
447
+ "27": "e",
448
+ "28": "f",
449
+ "29": "h",
450
+ "30": "i",
451
+ "31": "j",
452
+ "32": "k",
453
+ "33": "l",
454
+ "34": "m",
455
+ "35": "n",
456
+ "36": "o",
457
+ "37": "p",
458
+ "38": "q",
459
+ "39": "r",
460
+ "40": "s",
461
+ "41": "t",
462
+ "42": "u",
463
+ "43": "v",
464
+ "44": "w",
465
+ "45": "x",
466
+ "46": "y",
467
+ "47": "z",
468
+ "48": "«",
469
+ "49": "»",
470
+ "50": "æ",
471
+ "51": "ç",
472
+ "52": "ð",
473
+ "53": "ø",
474
+ "54": "ŋ",
475
+ "55": "œ",
476
+ "56": "ɐ",
477
+ "57": "ɑ",
478
+ "58": "ɒ",
479
+ "59": "ɔ",
480
+ "60": "ɗ",
481
+ "61": "ə",
482
+ "62": "ɚ",
483
+ "63": "ɛ",
484
+ "64": "ɜ",
485
+ "65": "ɟ",
486
+ "66": "ɡ",
487
+ "67": "ɣ",
488
+ "68": "ɨ",
489
+ "69": "ɪ",
490
+ "70": "ɬ",
491
+ "71": "ɯ",
492
+ "72": "ɲ",
493
+ "73": "ɹ",
494
+ "74": "ɾ",
495
+ "75": "ʁ",
496
+ "76": "ʃ",
497
+ "77": "ʊ",
498
+ "78": "ʌ",
499
+ "79": "ʎ",
500
+ "80": "ʐ",
501
+ "81": "ʒ",
502
+ "82": "ʔ",
503
+ "83": "ʝ",
504
+ "84": "ʲ",
505
+ "85": "ˈ",
506
+ "86": "ˌ",
507
+ "87": "ː",
508
+ "88": "̃",
509
+ "89": "̩",
510
+ "90": "̪",
511
+ "91": "β",
512
+ "92": "θ",
513
+ "93": "ᵻ",
514
+ "94": "—",
515
+ "95": "…"
516
+ }
517
+ }
onnx-int8/assets/languages.json ADDED
@@ -0,0 +1,795 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "en_us",
4
+ "index": 0,
5
+ "samples": 735073,
6
+ "duration_seconds": 2901001.580458344,
7
+ "by_split": {
8
+ "test": 3,
9
+ "train": 725390,
10
+ "val": 9680
11
+ },
12
+ "by_emotion": {
13
+ "anger": 179570,
14
+ "angry": 9900,
15
+ "calm": 103806,
16
+ "excited": 10933,
17
+ "friendly": 10192,
18
+ "frustrated": 8686,
19
+ "happy": 9702,
20
+ "joy": 175654,
21
+ "neutral": 19248,
22
+ "sad": 8366,
23
+ "sadness": 182900,
24
+ "sarcastic": 8753,
25
+ "unsure": 7363
26
+ },
27
+ "by_voice_emotion": {
28
+ "ariadne|anger": 31666,
29
+ "ariadne|angry": 1578,
30
+ "ariadne|calm": 17091,
31
+ "ariadne|excited": 1692,
32
+ "ariadne|friendly": 1497,
33
+ "ariadne|frustrated": 1452,
34
+ "ariadne|happy": 1458,
35
+ "ariadne|joy": 27806,
36
+ "ariadne|neutral": 3142,
37
+ "ariadne|sad": 1251,
38
+ "ariadne|sadness": 28367,
39
+ "ariadne|sarcastic": 1545,
40
+ "ariadne|unsure": 1095,
41
+ "felix|anger": 25617,
42
+ "felix|angry": 1348,
43
+ "felix|calm": 15384,
44
+ "felix|excited": 1460,
45
+ "felix|friendly": 1526,
46
+ "felix|frustrated": 1243,
47
+ "felix|happy": 1389,
48
+ "felix|joy": 25798,
49
+ "felix|neutral": 2855,
50
+ "felix|sad": 1100,
51
+ "felix|sadness": 28783,
52
+ "felix|sarcastic": 1248,
53
+ "felix|unsure": 1111,
54
+ "gwen|anger": 25114,
55
+ "gwen|angry": 1451,
56
+ "gwen|calm": 14596,
57
+ "gwen|excited": 1358,
58
+ "gwen|friendly": 1463,
59
+ "gwen|frustrated": 1282,
60
+ "gwen|happy": 1325,
61
+ "gwen|joy": 24280,
62
+ "gwen|neutral": 2903,
63
+ "gwen|sad": 1092,
64
+ "gwen|sadness": 28975,
65
+ "gwen|sarcastic": 1168,
66
+ "gwen|unsure": 1087,
67
+ "max|anger": 27530,
68
+ "max|angry": 1334,
69
+ "max|calm": 13282,
70
+ "max|excited": 1529,
71
+ "max|friendly": 1591,
72
+ "max|frustrated": 1129,
73
+ "max|happy": 1547,
74
+ "max|joy": 26807,
75
+ "max|neutral": 2998,
76
+ "max|sad": 1235,
77
+ "max|sadness": 27896,
78
+ "max|sarcastic": 1325,
79
+ "max|unsure": 1082,
80
+ "rex|anger": 27386,
81
+ "rex|angry": 1437,
82
+ "rex|calm": 16009,
83
+ "rex|excited": 1434,
84
+ "rex|friendly": 1488,
85
+ "rex|frustrated": 1222,
86
+ "rex|happy": 1396,
87
+ "rex|joy": 31503,
88
+ "rex|neutral": 3106,
89
+ "rex|sad": 1281,
90
+ "rex|sadness": 25976,
91
+ "rex|sarcastic": 1250,
92
+ "rex|unsure": 1034,
93
+ "scylla|anger": 24960,
94
+ "scylla|angry": 1520,
95
+ "scylla|calm": 14722,
96
+ "scylla|excited": 1380,
97
+ "scylla|friendly": 1294,
98
+ "scylla|frustrated": 1294,
99
+ "scylla|happy": 1349,
100
+ "scylla|joy": 25405,
101
+ "scylla|neutral": 2892,
102
+ "scylla|sad": 1329,
103
+ "scylla|sadness": 25239,
104
+ "scylla|sarcastic": 1161,
105
+ "scylla|unsure": 994,
106
+ "stone|anger": 17297,
107
+ "stone|angry": 1232,
108
+ "stone|calm": 12722,
109
+ "stone|excited": 2080,
110
+ "stone|friendly": 1333,
111
+ "stone|frustrated": 1064,
112
+ "stone|happy": 1238,
113
+ "stone|joy": 14055,
114
+ "stone|neutral": 1352,
115
+ "stone|sad": 1078,
116
+ "stone|sadness": 17664,
117
+ "stone|sarcastic": 1056,
118
+ "stone|unsure": 960
119
+ }
120
+ },
121
+ {
122
+ "id": "en_gb",
123
+ "index": 1,
124
+ "samples": 349633,
125
+ "duration_seconds": 1411473.146166665,
126
+ "by_split": {
127
+ "test": 1,
128
+ "train": 348089,
129
+ "val": 1543
130
+ },
131
+ "by_emotion": {
132
+ "anger": 85322,
133
+ "angry": 4979,
134
+ "calm": 48964,
135
+ "excited": 4701,
136
+ "friendly": 4976,
137
+ "frustrated": 4458,
138
+ "happy": 4611,
139
+ "joy": 79611,
140
+ "neutral": 9395,
141
+ "sad": 4100,
142
+ "sadness": 92216,
143
+ "sarcastic": 4018,
144
+ "unsure": 2282
145
+ },
146
+ "by_voice_emotion": {
147
+ "ink|anger": 25411,
148
+ "ink|angry": 1614,
149
+ "ink|calm": 15361,
150
+ "ink|excited": 1647,
151
+ "ink|friendly": 1713,
152
+ "ink|frustrated": 1512,
153
+ "ink|happy": 1514,
154
+ "ink|joy": 27359,
155
+ "ink|neutral": 2986,
156
+ "ink|sad": 1368,
157
+ "ink|sadness": 32086,
158
+ "ink|sarcastic": 1397,
159
+ "orpheus|anger": 27769,
160
+ "orpheus|angry": 1608,
161
+ "orpheus|calm": 16678,
162
+ "orpheus|excited": 1568,
163
+ "orpheus|friendly": 1599,
164
+ "orpheus|frustrated": 1466,
165
+ "orpheus|happy": 1507,
166
+ "orpheus|joy": 24367,
167
+ "orpheus|neutral": 3210,
168
+ "orpheus|sad": 1287,
169
+ "orpheus|sadness": 29354,
170
+ "orpheus|sarcastic": 1282,
171
+ "orpheus|unsure": 1139,
172
+ "tuesday|anger": 32142,
173
+ "tuesday|angry": 1757,
174
+ "tuesday|calm": 16925,
175
+ "tuesday|excited": 1486,
176
+ "tuesday|friendly": 1664,
177
+ "tuesday|frustrated": 1480,
178
+ "tuesday|happy": 1590,
179
+ "tuesday|joy": 27885,
180
+ "tuesday|neutral": 3199,
181
+ "tuesday|sad": 1445,
182
+ "tuesday|sadness": 30776,
183
+ "tuesday|sarcastic": 1339,
184
+ "tuesday|unsure": 1143
185
+ }
186
+ },
187
+ {
188
+ "id": "es",
189
+ "index": 2,
190
+ "samples": 722935,
191
+ "duration_seconds": 2911555.221750007,
192
+ "by_split": {
193
+ "test": 19166,
194
+ "train": 692033,
195
+ "val": 11736
196
+ },
197
+ "by_emotion": {
198
+ "anger": 165314,
199
+ "angry": 4734,
200
+ "calm": 162958,
201
+ "excited": 4851,
202
+ "friendly": 4296,
203
+ "frustrated": 3305,
204
+ "happy": 4608,
205
+ "joy": 180038,
206
+ "neutral": 6013,
207
+ "sad": 3760,
208
+ "sadness": 174278,
209
+ "sarcastic": 5037,
210
+ "unsure": 3743
211
+ },
212
+ "by_voice_emotion": {
213
+ "ariadne|anger": 19064,
214
+ "ariadne|angry": 492,
215
+ "ariadne|calm": 15813,
216
+ "ariadne|excited": 547,
217
+ "ariadne|friendly": 504,
218
+ "ariadne|frustrated": 365,
219
+ "ariadne|happy": 568,
220
+ "ariadne|joy": 18815,
221
+ "ariadne|neutral": 59,
222
+ "ariadne|sad": 500,
223
+ "ariadne|sadness": 19508,
224
+ "ariadne|sarcastic": 549,
225
+ "ariadne|unsure": 427,
226
+ "felix|anger": 16850,
227
+ "felix|angry": 419,
228
+ "felix|calm": 16342,
229
+ "felix|excited": 571,
230
+ "felix|friendly": 509,
231
+ "felix|frustrated": 311,
232
+ "felix|happy": 593,
233
+ "felix|joy": 16887,
234
+ "felix|neutral": 645,
235
+ "felix|sad": 396,
236
+ "felix|sadness": 16392,
237
+ "felix|sarcastic": 514,
238
+ "felix|unsure": 363,
239
+ "gwen|anger": 15711,
240
+ "gwen|angry": 532,
241
+ "gwen|calm": 12529,
242
+ "gwen|friendly": 441,
243
+ "gwen|frustrated": 306,
244
+ "gwen|happy": 469,
245
+ "gwen|joy": 15912,
246
+ "gwen|neutral": 569,
247
+ "gwen|sad": 367,
248
+ "gwen|sadness": 20156,
249
+ "gwen|sarcastic": 456,
250
+ "gwen|unsure": 335,
251
+ "ink|anger": 11480,
252
+ "ink|angry": 470,
253
+ "ink|calm": 17615,
254
+ "ink|excited": 549,
255
+ "ink|friendly": 509,
256
+ "ink|frustrated": 307,
257
+ "ink|happy": 548,
258
+ "ink|joy": 23966,
259
+ "ink|neutral": 753,
260
+ "ink|sadness": 16581,
261
+ "ink|sarcastic": 547,
262
+ "ink|unsure": 396,
263
+ "max|anger": 16947,
264
+ "max|angry": 497,
265
+ "max|calm": 17674,
266
+ "max|excited": 491,
267
+ "max|friendly": 466,
268
+ "max|frustrated": 349,
269
+ "max|happy": 445,
270
+ "max|joy": 17471,
271
+ "max|neutral": 780,
272
+ "max|sad": 406,
273
+ "max|sadness": 17004,
274
+ "max|sarcastic": 569,
275
+ "max|unsure": 367,
276
+ "orpheus|anger": 16146,
277
+ "orpheus|angry": 492,
278
+ "orpheus|calm": 17293,
279
+ "orpheus|excited": 486,
280
+ "orpheus|friendly": 391,
281
+ "orpheus|frustrated": 347,
282
+ "orpheus|happy": 516,
283
+ "orpheus|joy": 16014,
284
+ "orpheus|neutral": 585,
285
+ "orpheus|sad": 437,
286
+ "orpheus|sadness": 17709,
287
+ "orpheus|sarcastic": 454,
288
+ "orpheus|unsure": 431,
289
+ "rex|anger": 17145,
290
+ "rex|angry": 437,
291
+ "rex|calm": 17234,
292
+ "rex|excited": 564,
293
+ "rex|friendly": 445,
294
+ "rex|frustrated": 328,
295
+ "rex|happy": 493,
296
+ "rex|joy": 17216,
297
+ "rex|neutral": 682,
298
+ "rex|sad": 443,
299
+ "rex|sadness": 17176,
300
+ "rex|sarcastic": 478,
301
+ "rex|unsure": 360,
302
+ "scylla|anger": 18884,
303
+ "scylla|angry": 490,
304
+ "scylla|calm": 14299,
305
+ "scylla|excited": 581,
306
+ "scylla|friendly": 545,
307
+ "scylla|frustrated": 364,
308
+ "scylla|happy": 523,
309
+ "scylla|joy": 21153,
310
+ "scylla|neutral": 605,
311
+ "scylla|sad": 438,
312
+ "scylla|sadness": 17745,
313
+ "scylla|sarcastic": 501,
314
+ "scylla|unsure": 354,
315
+ "stone|anger": 15474,
316
+ "stone|angry": 429,
317
+ "stone|calm": 15760,
318
+ "stone|excited": 502,
319
+ "stone|friendly": 486,
320
+ "stone|frustrated": 262,
321
+ "stone|happy": 453,
322
+ "stone|joy": 14345,
323
+ "stone|neutral": 607,
324
+ "stone|sad": 365,
325
+ "stone|sadness": 14923,
326
+ "stone|sarcastic": 444,
327
+ "stone|unsure": 338,
328
+ "tuesday|anger": 17613,
329
+ "tuesday|angry": 476,
330
+ "tuesday|calm": 18399,
331
+ "tuesday|excited": 560,
332
+ "tuesday|frustrated": 366,
333
+ "tuesday|joy": 18259,
334
+ "tuesday|neutral": 728,
335
+ "tuesday|sad": 408,
336
+ "tuesday|sadness": 17084,
337
+ "tuesday|sarcastic": 525,
338
+ "tuesday|unsure": 372
339
+ }
340
+ },
341
+ {
342
+ "id": "it",
343
+ "index": 3,
344
+ "samples": 793195,
345
+ "duration_seconds": 3343548.095916678,
346
+ "by_split": {
347
+ "test": 4948,
348
+ "train": 762867,
349
+ "val": 25380
350
+ },
351
+ "by_emotion": {
352
+ "anger": 181826,
353
+ "angry": 6284,
354
+ "calm": 182696,
355
+ "excited": 6836,
356
+ "friendly": 7102,
357
+ "frustrated": 4645,
358
+ "happy": 6887,
359
+ "joy": 185312,
360
+ "neutral": 8611,
361
+ "sad": 4894,
362
+ "sadness": 185577,
363
+ "sarcastic": 6961,
364
+ "unsure": 5564
365
+ },
366
+ "by_voice_emotion": {
367
+ "ariadne|anger": 17708,
368
+ "ariadne|angry": 857,
369
+ "ariadne|calm": 18525,
370
+ "ariadne|excited": 783,
371
+ "ariadne|friendly": 800,
372
+ "ariadne|frustrated": 603,
373
+ "ariadne|happy": 833,
374
+ "ariadne|joy": 19256,
375
+ "ariadne|neutral": 844,
376
+ "ariadne|sad": 555,
377
+ "ariadne|sadness": 19510,
378
+ "ariadne|sarcastic": 677,
379
+ "ariadne|unsure": 573,
380
+ "felix|anger": 18281,
381
+ "felix|angry": 779,
382
+ "felix|calm": 17884,
383
+ "felix|excited": 823,
384
+ "felix|friendly": 729,
385
+ "felix|frustrated": 527,
386
+ "felix|happy": 653,
387
+ "felix|joy": 18293,
388
+ "felix|neutral": 918,
389
+ "felix|sad": 461,
390
+ "felix|sadness": 18379,
391
+ "felix|sarcastic": 685,
392
+ "felix|unsure": 553,
393
+ "gwen|anger": 16984,
394
+ "gwen|angry": 701,
395
+ "gwen|calm": 17615,
396
+ "gwen|excited": 709,
397
+ "gwen|friendly": 652,
398
+ "gwen|frustrated": 525,
399
+ "gwen|happy": 625,
400
+ "gwen|joy": 17628,
401
+ "gwen|neutral": 888,
402
+ "gwen|sad": 423,
403
+ "gwen|sadness": 17438,
404
+ "gwen|sarcastic": 621,
405
+ "gwen|unsure": 497,
406
+ "ink|anger": 21226,
407
+ "ink|calm": 19311,
408
+ "ink|excited": 756,
409
+ "ink|friendly": 717,
410
+ "ink|happy": 672,
411
+ "ink|joy": 18118,
412
+ "ink|neutral": 880,
413
+ "ink|sad": 495,
414
+ "ink|sadness": 20142,
415
+ "ink|sarcastic": 747,
416
+ "ink|unsure": 599,
417
+ "max|anger": 18857,
418
+ "max|angry": 885,
419
+ "max|calm": 18002,
420
+ "max|excited": 794,
421
+ "max|friendly": 626,
422
+ "max|frustrated": 684,
423
+ "max|happy": 645,
424
+ "max|joy": 18472,
425
+ "max|neutral": 930,
426
+ "max|sad": 520,
427
+ "max|sadness": 18512,
428
+ "max|sarcastic": 731,
429
+ "max|unsure": 575,
430
+ "orpheus|anger": 18468,
431
+ "orpheus|angry": 775,
432
+ "orpheus|calm": 19120,
433
+ "orpheus|excited": 759,
434
+ "orpheus|friendly": 838,
435
+ "orpheus|frustrated": 628,
436
+ "orpheus|happy": 755,
437
+ "orpheus|joy": 19799,
438
+ "orpheus|neutral": 874,
439
+ "orpheus|sad": 507,
440
+ "orpheus|sadness": 19310,
441
+ "orpheus|sarcastic": 714,
442
+ "orpheus|unsure": 598,
443
+ "rex|anger": 18055,
444
+ "rex|calm": 18476,
445
+ "rex|friendly": 703,
446
+ "rex|happy": 780,
447
+ "rex|joy": 20885,
448
+ "rex|neutral": 834,
449
+ "rex|sad": 557,
450
+ "rex|sadness": 19262,
451
+ "rex|sarcastic": 717,
452
+ "rex|unsure": 547,
453
+ "scylla|anger": 17442,
454
+ "scylla|angry": 762,
455
+ "scylla|calm": 17654,
456
+ "scylla|excited": 728,
457
+ "scylla|friendly": 705,
458
+ "scylla|frustrated": 535,
459
+ "scylla|happy": 712,
460
+ "scylla|joy": 17835,
461
+ "scylla|neutral": 808,
462
+ "scylla|sad": 491,
463
+ "scylla|sadness": 17908,
464
+ "scylla|sarcastic": 581,
465
+ "scylla|unsure": 552,
466
+ "stone|anger": 16507,
467
+ "stone|angry": 715,
468
+ "stone|calm": 17167,
469
+ "stone|excited": 702,
470
+ "stone|friendly": 569,
471
+ "stone|frustrated": 480,
472
+ "stone|happy": 512,
473
+ "stone|joy": 16477,
474
+ "stone|neutral": 789,
475
+ "stone|sad": 396,
476
+ "stone|sadness": 16592,
477
+ "stone|sarcastic": 647,
478
+ "stone|unsure": 507,
479
+ "tuesday|anger": 18298,
480
+ "tuesday|angry": 810,
481
+ "tuesday|calm": 18942,
482
+ "tuesday|excited": 782,
483
+ "tuesday|friendly": 763,
484
+ "tuesday|frustrated": 663,
485
+ "tuesday|happy": 700,
486
+ "tuesday|joy": 18549,
487
+ "tuesday|neutral": 846,
488
+ "tuesday|sad": 489,
489
+ "tuesday|sadness": 18524,
490
+ "tuesday|sarcastic": 841,
491
+ "tuesday|unsure": 563
492
+ }
493
+ },
494
+ {
495
+ "id": "fr",
496
+ "index": 4,
497
+ "samples": 555871,
498
+ "duration_seconds": 2100927.66266675,
499
+ "by_split": {
500
+ "test": 11797,
501
+ "train": 542199,
502
+ "val": 1875
503
+ },
504
+ "by_emotion": {
505
+ "anger": 151353,
506
+ "angry": 361,
507
+ "calm": 113339,
508
+ "happy": 336,
509
+ "joy": 142231,
510
+ "neutral": 348,
511
+ "sad": 342,
512
+ "sadness": 147561
513
+ },
514
+ "by_voice_emotion": {
515
+ "ariadne|anger": 18503,
516
+ "ariadne|angry": 52,
517
+ "ariadne|calm": 13218,
518
+ "ariadne|happy": 33,
519
+ "ariadne|joy": 16447,
520
+ "ariadne|neutral": 66,
521
+ "ariadne|sadness": 19999,
522
+ "felix|anger": 16184,
523
+ "felix|angry": 40,
524
+ "felix|calm": 9303,
525
+ "felix|happy": 34,
526
+ "felix|joy": 17208,
527
+ "felix|sadness": 14388,
528
+ "gwen|anger": 14959,
529
+ "gwen|angry": 29,
530
+ "gwen|calm": 11436,
531
+ "gwen|happy": 41,
532
+ "gwen|joy": 16868,
533
+ "gwen|neutral": 24,
534
+ "gwen|sad": 51,
535
+ "gwen|sadness": 14069,
536
+ "ink|anger": 15344,
537
+ "ink|angry": 39,
538
+ "ink|calm": 11026,
539
+ "ink|happy": 37,
540
+ "ink|joy": 15526,
541
+ "ink|sad": 53,
542
+ "ink|sadness": 14133,
543
+ "max|anger": 16001,
544
+ "max|angry": 45,
545
+ "max|calm": 12547,
546
+ "max|happy": 24,
547
+ "max|joy": 14315,
548
+ "max|neutral": 60,
549
+ "max|sad": 35,
550
+ "max|sadness": 15977,
551
+ "orpheus|anger": 14508,
552
+ "orpheus|angry": 24,
553
+ "orpheus|calm": 11697,
554
+ "orpheus|happy": 56,
555
+ "orpheus|joy": 12792,
556
+ "orpheus|neutral": 26,
557
+ "orpheus|sad": 56,
558
+ "orpheus|sadness": 13828,
559
+ "rex|anger": 16731,
560
+ "rex|calm": 11048,
561
+ "rex|joy": 11580,
562
+ "rex|neutral": 60,
563
+ "rex|sad": 24,
564
+ "rex|sadness": 11145,
565
+ "scylla|anger": 12966,
566
+ "scylla|angry": 66,
567
+ "scylla|calm": 10733,
568
+ "scylla|happy": 23,
569
+ "scylla|joy": 13662,
570
+ "scylla|neutral": 57,
571
+ "scylla|sad": 20,
572
+ "scylla|sadness": 15278,
573
+ "stone|anger": 12668,
574
+ "stone|angry": 36,
575
+ "stone|calm": 10122,
576
+ "stone|happy": 44,
577
+ "stone|joy": 9556,
578
+ "stone|neutral": 25,
579
+ "stone|sad": 44,
580
+ "stone|sadness": 13083,
581
+ "tuesday|anger": 13489,
582
+ "tuesday|angry": 30,
583
+ "tuesday|calm": 12209,
584
+ "tuesday|happy": 44,
585
+ "tuesday|joy": 14277,
586
+ "tuesday|neutral": 30,
587
+ "tuesday|sad": 59,
588
+ "tuesday|sadness": 15661
589
+ }
590
+ },
591
+ {
592
+ "id": "de",
593
+ "index": 5,
594
+ "samples": 576923,
595
+ "duration_seconds": 2195474.76420833,
596
+ "by_split": {
597
+ "test": 8249,
598
+ "train": 568674
599
+ },
600
+ "by_emotion": {
601
+ "anger": 157088,
602
+ "angry": 390,
603
+ "calm": 116192,
604
+ "happy": 436,
605
+ "joy": 145774,
606
+ "neutral": 430,
607
+ "sad": 454,
608
+ "sadness": 156159
609
+ },
610
+ "by_voice_emotion": {
611
+ "ariadne|anger": 16121,
612
+ "ariadne|angry": 67,
613
+ "ariadne|calm": 13457,
614
+ "ariadne|happy": 27,
615
+ "ariadne|joy": 19071,
616
+ "ariadne|neutral": 67,
617
+ "ariadne|sad": 32,
618
+ "ariadne|sadness": 17796,
619
+ "felix|anger": 11767,
620
+ "felix|angry": 59,
621
+ "felix|calm": 11353,
622
+ "felix|happy": 27,
623
+ "felix|joy": 13488,
624
+ "felix|neutral": 67,
625
+ "felix|sad": 30,
626
+ "felix|sadness": 14451,
627
+ "gwen|anger": 15657,
628
+ "gwen|angry": 59,
629
+ "gwen|calm": 11078,
630
+ "gwen|happy": 34,
631
+ "gwen|joy": 15899,
632
+ "gwen|neutral": 42,
633
+ "gwen|sad": 40,
634
+ "gwen|sadness": 15884,
635
+ "ink|anger": 15888,
636
+ "ink|angry": 29,
637
+ "ink|calm": 11926,
638
+ "ink|happy": 53,
639
+ "ink|joy": 15329,
640
+ "ink|neutral": 33,
641
+ "ink|sad": 73,
642
+ "ink|sadness": 15916,
643
+ "max|anger": 16881,
644
+ "max|angry": 22,
645
+ "max|calm": 12514,
646
+ "max|happy": 65,
647
+ "max|joy": 16109,
648
+ "max|neutral": 24,
649
+ "max|sad": 68,
650
+ "max|sadness": 16720,
651
+ "orpheus|anger": 17423,
652
+ "orpheus|angry": 55,
653
+ "orpheus|calm": 11973,
654
+ "orpheus|happy": 41,
655
+ "orpheus|joy": 13727,
656
+ "orpheus|neutral": 53,
657
+ "orpheus|sad": 26,
658
+ "orpheus|sadness": 12845,
659
+ "rex|anger": 16470,
660
+ "rex|calm": 11935,
661
+ "rex|happy": 36,
662
+ "rex|joy": 13429,
663
+ "rex|neutral": 39,
664
+ "rex|sad": 39,
665
+ "rex|sadness": 17995,
666
+ "scylla|anger": 15430,
667
+ "scylla|angry": 47,
668
+ "scylla|calm": 9641,
669
+ "scylla|happy": 39,
670
+ "scylla|joy": 11987,
671
+ "scylla|neutral": 47,
672
+ "scylla|sad": 26,
673
+ "scylla|sadness": 15870,
674
+ "stone|anger": 14909,
675
+ "stone|angry": 27,
676
+ "stone|calm": 9922,
677
+ "stone|happy": 44,
678
+ "stone|joy": 11813,
679
+ "stone|neutral": 28,
680
+ "stone|sad": 52,
681
+ "stone|sadness": 13762,
682
+ "tuesday|anger": 16542,
683
+ "tuesday|angry": 25,
684
+ "tuesday|calm": 12393,
685
+ "tuesday|happy": 70,
686
+ "tuesday|joy": 14922,
687
+ "tuesday|neutral": 30,
688
+ "tuesday|sad": 68,
689
+ "tuesday|sadness": 14920
690
+ }
691
+ },
692
+ {
693
+ "id": "vi",
694
+ "index": 6,
695
+ "samples": 384527,
696
+ "duration_seconds": 1420550.5151666757,
697
+ "by_split": {
698
+ "test": 3985,
699
+ "train": 371301,
700
+ "val": 9241
701
+ },
702
+ "by_emotion": {
703
+ "anger": 93688,
704
+ "angry": 321,
705
+ "calm": 94373,
706
+ "happy": 354,
707
+ "joy": 95786,
708
+ "neutral": 366,
709
+ "sad": 343,
710
+ "sadness": 99296
711
+ },
712
+ "by_voice_emotion": {
713
+ "ariadne|anger": 10637,
714
+ "ariadne|angry": 35,
715
+ "ariadne|calm": 9979,
716
+ "ariadne|happy": 38,
717
+ "ariadne|joy": 11566,
718
+ "ariadne|neutral": 48,
719
+ "ariadne|sad": 30,
720
+ "ariadne|sadness": 10228,
721
+ "felix|anger": 8695,
722
+ "felix|angry": 22,
723
+ "felix|calm": 8530,
724
+ "felix|happy": 45,
725
+ "felix|joy": 9788,
726
+ "felix|neutral": 19,
727
+ "felix|sad": 57,
728
+ "felix|sadness": 9917,
729
+ "gwen|anger": 8297,
730
+ "gwen|angry": 20,
731
+ "gwen|calm": 7669,
732
+ "gwen|happy": 45,
733
+ "gwen|joy": 8053,
734
+ "gwen|neutral": 18,
735
+ "gwen|sad": 47,
736
+ "gwen|sadness": 7873,
737
+ "ink|anger": 10669,
738
+ "ink|angry": 47,
739
+ "ink|calm": 12780,
740
+ "ink|happy": 26,
741
+ "ink|joy": 11769,
742
+ "ink|neutral": 49,
743
+ "ink|sad": 37,
744
+ "ink|sadness": 13413,
745
+ "max|anger": 10458,
746
+ "max|angry": 38,
747
+ "max|calm": 9237,
748
+ "max|happy": 20,
749
+ "max|joy": 9200,
750
+ "max|neutral": 44,
751
+ "max|sad": 32,
752
+ "max|sadness": 10965,
753
+ "orpheus|anger": 9906,
754
+ "orpheus|angry": 21,
755
+ "orpheus|calm": 9317,
756
+ "orpheus|happy": 32,
757
+ "orpheus|joy": 9210,
758
+ "orpheus|neutral": 44,
759
+ "orpheus|sad": 15,
760
+ "orpheus|sadness": 10189,
761
+ "rex|anger": 9886,
762
+ "rex|angry": 23,
763
+ "rex|calm": 10188,
764
+ "rex|happy": 52,
765
+ "rex|joy": 10034,
766
+ "rex|neutral": 29,
767
+ "rex|sad": 45,
768
+ "rex|sadness": 10286,
769
+ "scylla|anger": 8244,
770
+ "scylla|angry": 47,
771
+ "scylla|calm": 8762,
772
+ "scylla|happy": 24,
773
+ "scylla|joy": 9074,
774
+ "scylla|neutral": 43,
775
+ "scylla|sad": 22,
776
+ "scylla|sadness": 9363,
777
+ "stone|anger": 8120,
778
+ "stone|angry": 46,
779
+ "stone|calm": 8605,
780
+ "stone|happy": 21,
781
+ "stone|joy": 8144,
782
+ "stone|neutral": 47,
783
+ "stone|sad": 17,
784
+ "stone|sadness": 8407,
785
+ "tuesday|anger": 8776,
786
+ "tuesday|angry": 22,
787
+ "tuesday|calm": 9306,
788
+ "tuesday|happy": 51,
789
+ "tuesday|joy": 8948,
790
+ "tuesday|neutral": 25,
791
+ "tuesday|sad": 41,
792
+ "tuesday|sadness": 8655
793
+ }
794
+ }
795
+ ]
onnx-int8/assets/phone_vocab.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema_version": 1,
3
+ "mode": "scyllasband_ipa_phone_symbols",
4
+ "special_tokens": [
5
+ "<pad>",
6
+ "<unk>",
7
+ "<sil>",
8
+ "<pause_comma>",
9
+ "<pause_semicolon>",
10
+ "<pause_colon>",
11
+ "<pause_dash>",
12
+ "<ellipsis>",
13
+ "<end_stmt>",
14
+ "<end_question>",
15
+ "<end_exclaim>",
16
+ "<ctx_sentence_start>",
17
+ "<ctx_continuation>",
18
+ "<ctx_sentence_end>",
19
+ "<ctx_chunk_continue>"
20
+ ],
21
+ "vocab_size": 87,
22
+ "token_to_id": {
23
+ "<pad>": 0,
24
+ "<unk>": 1,
25
+ "<sil>": 2,
26
+ "<pause_comma>": 3,
27
+ "<pause_semicolon>": 4,
28
+ "<pause_colon>": 5,
29
+ "<pause_dash>": 6,
30
+ "<ellipsis>": 7,
31
+ "<end_stmt>": 8,
32
+ "<end_question>": 9,
33
+ "<end_exclaim>": 10,
34
+ "<ctx_sentence_start>": 11,
35
+ "<ctx_continuation>": 12,
36
+ "<ctx_sentence_end>": 13,
37
+ "<ctx_chunk_continue>": 14,
38
+ "1": 15,
39
+ "2": 16,
40
+ "4": 17,
41
+ "5": 18,
42
+ "6": 19,
43
+ "7": 20,
44
+ "a": 21,
45
+ "b": 22,
46
+ "c": 23,
47
+ "d": 24,
48
+ "e": 25,
49
+ "f": 26,
50
+ "h": 27,
51
+ "i": 28,
52
+ "j": 29,
53
+ "k": 30,
54
+ "l": 31,
55
+ "m": 32,
56
+ "n": 33,
57
+ "o": 34,
58
+ "p": 35,
59
+ "r": 36,
60
+ "s": 37,
61
+ "t": 38,
62
+ "u": 39,
63
+ "v": 40,
64
+ "w": 41,
65
+ "x": 42,
66
+ "y": 43,
67
+ "z": 44,
68
+ "æ": 45,
69
+ "ç": 46,
70
+ "ð": 47,
71
+ "ø": 48,
72
+ "ŋ": 49,
73
+ "œ": 50,
74
+ "ɐ": 51,
75
+ "ɑ": 52,
76
+ "ɒ": 53,
77
+ "ɔ": 54,
78
+ "ɗ": 55,
79
+ "ə": 56,
80
+ "ɚ": 57,
81
+ "ɛ": 58,
82
+ "ɜ": 59,
83
+ "ɟ": 60,
84
+ "ɡ": 61,
85
+ "ɣ": 62,
86
+ "ɪ": 63,
87
+ "ɯ": 64,
88
+ "ɲ": 65,
89
+ "ɹ": 66,
90
+ "ɾ": 67,
91
+ "ʁ": 68,
92
+ "ʃ": 69,
93
+ "ʊ": 70,
94
+ "ʌ": 71,
95
+ "ʎ": 72,
96
+ "ʐ": 73,
97
+ "ʒ": 74,
98
+ "ʔ": 75,
99
+ "ʝ": 76,
100
+ "ʲ": 77,
101
+ "ˈ": 78,
102
+ "ˌ": 79,
103
+ "ː": 80,
104
+ "̃": 81,
105
+ "̩": 82,
106
+ "̪": 83,
107
+ "β": 84,
108
+ "θ": 85,
109
+ "ᵻ": 86
110
+ }
111
+ }
onnx-int8/assets/voice_packs/ariadne.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fa680e7338121eb517d90fb52bef000259b0882cb2ff523bef160f9a6ad7e0
3
+ size 256110
onnx-int8/assets/voice_packs/felix.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fe52012afd583abfea1ecdd45a6f381add43bed668cb61a5df6fa9913d5823
3
+ size 255046
onnx-int8/assets/voice_packs/gwen.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99375b97a65ce117300b99aec9c6299084cdbcf1d87084b73923aac7fa26ece3
3
+ size 256021
onnx-int8/assets/voice_packs/ink.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793eca609ae0765db20fa678f8591594e64400967555c74607bc71218e112230
3
+ size 260271
onnx-int8/assets/voice_packs/max.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8a830c4bfc912b6a04dc674ecce3946515d7f5bfdef16267b8e4a51f5a40d9
3
+ size 260997
onnx-int8/assets/voice_packs/orpheus.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8782dd27c7581a6fa0909dad5c247e55bb3220d0ee42225921907723205cbe50
3
+ size 250919
onnx-int8/assets/voice_packs/reference_packs.json ADDED
@@ -0,0 +1,916 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "affect_axis_order": [
3
+ "calm",
4
+ "joy",
5
+ "anger",
6
+ "sadness",
7
+ "whisper"
8
+ ],
9
+ "compiled_affect_index": {
10
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/input/compiled_affect/index.json",
11
+ "sha256": "816d33335eaca6921e9ac0ff0fd7a6d065faf25c9081053fd0574e3e7be474bd",
12
+ "size_bytes": 1346
13
+ },
14
+ "identity_encoder": {
15
+ "config_sha256": "c6ac8c0ce55b18d4612677931036fe5ce78093e87361c552a173f00a0bb07514",
16
+ "implementation_path": "/home/sean/aiTools/datasetGen/venv/lib/python3.11/site-packages/transformers/models/wavlm/modeling_wavlm.py",
17
+ "implementation_sha256": "2d876ea90e1df2e049149a248b47c9f8ab496dbf5a95ee5da9222ed439b62cdf",
18
+ "implementation_version": "transformers==4.57.3",
19
+ "model_path": "/home/sean/.cache/huggingface/hub/models--microsoft--wavlm-base-plus-sv/snapshots/feb593a6c23c1cc3d9510425c29b0a14d2b07b1e",
20
+ "preprocessor_sha256": "99272fe8ccfab114b68b478681ea47ee3a1ce62bb788cb92dd6e4f69fb1f1da2",
21
+ "weights_sha256": "e906bce2fa42fb497a1d1a9ecf81548adb7e03b12a5644e32d2f42f0d6500fad"
22
+ },
23
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
24
+ "identity_window_spec": {
25
+ "edge_padding_ms": 100.0,
26
+ "frame_ms": 30.0,
27
+ "hop_ms": 10.0,
28
+ "maximum_clipping_fraction": 0.001,
29
+ "maximum_window_seconds": 12.0,
30
+ "minimum_active_ratio": 0.5,
31
+ "minimum_active_speech_seconds": 2.0,
32
+ "minimum_window_seconds": 2.0,
33
+ "sample_rate": 16000,
34
+ "selection": "maximum_active_frames_then_earliest_v1",
35
+ "threshold_below_p90_db": 35.0,
36
+ "threshold_dbfs_floor": -55.0
37
+ },
38
+ "pack_kind": "archival_training",
39
+ "pack_schema_version": "scyllasband_reference_pack_v4",
40
+ "prosody_extractor_spec": {
41
+ "channels": "mono_mean",
42
+ "confidence": "support_times_source_diversity_times_feature_coverage",
43
+ "contract": "scyllasband_prosody_32_v3_relative",
44
+ "cpp": "real_cepstrum_peak_2p5_to_16ms_minus_local_median_v1",
45
+ "energy_floor_dbfs": -100.0,
46
+ "f0_estimator": "torchaudio_detect_pitch_frequency",
47
+ "f0_max_hz": 900.0,
48
+ "f0_min_hz": 45.0,
49
+ "f0_min_voiced_frames": 10,
50
+ "f0_min_voiced_ratio": 0.08,
51
+ "f0_reference_hz": 55.0,
52
+ "frame_ms": 40.0,
53
+ "global_location": "masked_median",
54
+ "global_scale": "masked_iqr_over_1p349_with_feature_floor",
55
+ "hnr": "normalized_autocorrelation_peak_2p5_to_16ms_v1",
56
+ "hop_ms": 10.0,
57
+ "identity_window_quality": "duration_x_active_speech_x_clipping_v1",
58
+ "mfa_silence": [
59
+ "",
60
+ "<sil>",
61
+ "sil",
62
+ "sp",
63
+ "spn"
64
+ ],
65
+ "mfa_tiers": [
66
+ "phones",
67
+ "words"
68
+ ],
69
+ "octave_handling": "mask_outside_fixed_range_no_posthoc_correction",
70
+ "sample_rate": 24000,
71
+ "spectral_log_base": "natural_except_tilt_db_per_octave",
72
+ "spectral_range_hz": [
73
+ 100.0,
74
+ 8000.0
75
+ ],
76
+ "vad_rule": "frame_rms_db_above_max_minus_55_or_p90_minus_35"
77
+ },
78
+ "prosody_feature_contract": "scyllasband_prosody_32_v3_relative",
79
+ "prosody_global_locations": [
80
+ -23.03205108642578,
81
+ -7.371561050415039,
82
+ 15.812406539916992,
83
+ -60.721412658691406,
84
+ -37.18050765991211,
85
+ -26.05147933959961,
86
+ -21.280845642089844,
87
+ -18.83296012878418,
88
+ 0.0,
89
+ 0.0,
90
+ 0.0,
91
+ 0.0,
92
+ 0.0,
93
+ 0.0,
94
+ 0.0,
95
+ 0.8792452812194824,
96
+ 20.119674682617188,
97
+ 14.531656265258789,
98
+ 17.919153213500977,
99
+ 23.237964630126953,
100
+ 26.577579498291016,
101
+ 4.303144454956055,
102
+ 9.918582916259766,
103
+ 2.0197482109069824,
104
+ 18.624141693115234,
105
+ -3.781693935394287,
106
+ -7.069836616516113,
107
+ 6.445383548736572,
108
+ 6.363071441650391,
109
+ 0.2435217797756195,
110
+ 0.06537781655788422,
111
+ 0.012853986583650112
112
+ ],
113
+ "prosody_global_scales": [
114
+ 1.0,
115
+ 2.027599334716797,
116
+ 2.1430840492248535,
117
+ 35.65044021606445,
118
+ 8.346331596374512,
119
+ 2.799455404281616,
120
+ 1.0578213930130005,
121
+ 1.0,
122
+ 0.10000000149011612,
123
+ 0.10000000149011612,
124
+ 0.019999999552965164,
125
+ 0.019999999552965164,
126
+ 0.009999999776482582,
127
+ 0.009999999776482582,
128
+ 0.009999999776482582,
129
+ 0.10578638315200806,
130
+ 5.736739158630371,
131
+ 5.03354024887085,
132
+ 5.791416168212891,
133
+ 5.937447547912598,
134
+ 6.5922746658325195,
135
+ 2.4209775924682617,
136
+ 6.081151485443115,
137
+ 1.0395649671554565,
138
+ 5.723820209503174,
139
+ 3.30536150932312,
140
+ 1.5370782613754272,
141
+ 0.31072285771369934,
142
+ 0.3059537708759308,
143
+ 0.07528027147054672,
144
+ 0.011799979954957962,
145
+ 0.011431285180151463
146
+ ],
147
+ "reports": {
148
+ "ariadne": {
149
+ "baselines": {
150
+ "de": {
151
+ "confidence": 0.78125,
152
+ "distinct_sources": 7,
153
+ "kind": "ordinary_low_activation",
154
+ "support": 7
155
+ },
156
+ "en_us": {
157
+ "confidence": 0.78125,
158
+ "distinct_sources": 12,
159
+ "kind": "ordinary_low_activation",
160
+ "support": 12
161
+ },
162
+ "es": {
163
+ "confidence": 0.5859375,
164
+ "distinct_sources": 3,
165
+ "kind": "ordinary_low_activation",
166
+ "support": 3
167
+ },
168
+ "fr": {
169
+ "confidence": 0.78125,
170
+ "distinct_sources": 9,
171
+ "kind": "ordinary_low_activation",
172
+ "support": 9
173
+ },
174
+ "it": {
175
+ "confidence": 0.78125,
176
+ "distinct_sources": 8,
177
+ "kind": "ordinary_low_activation",
178
+ "support": 8
179
+ },
180
+ "vi": {
181
+ "confidence": 0.78125,
182
+ "distinct_sources": 12,
183
+ "kind": "ordinary_low_activation",
184
+ "support": 12
185
+ }
186
+ },
187
+ "identity_active_ratios": {
188
+ "maximum": 0.9394387001477105,
189
+ "median": 0.8167842812649064,
190
+ "minimum": 0.5548172757475083
191
+ },
192
+ "identity_active_speech_seconds": {
193
+ "maximum": 10.46,
194
+ "median": 6.734999999999999,
195
+ "minimum": 2.65
196
+ },
197
+ "identity_dispersion": 0.03384660929441452,
198
+ "identity_distinct_source_groups": 90,
199
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
200
+ "identity_rejected_sources": 0,
201
+ "identity_rejections": [],
202
+ "identity_windows": 90,
203
+ "prototype_counts_by_language": {
204
+ "de": 18,
205
+ "en_us": 24,
206
+ "es": 12,
207
+ "fr": 15,
208
+ "it": 9,
209
+ "vi": 11
210
+ },
211
+ "prototypes": 89,
212
+ "references": 216
213
+ },
214
+ "felix": {
215
+ "baselines": {
216
+ "de": {
217
+ "confidence": 0.78125,
218
+ "distinct_sources": 7,
219
+ "kind": "ordinary_low_activation",
220
+ "support": 7
221
+ },
222
+ "en_us": {
223
+ "confidence": 0.78125,
224
+ "distinct_sources": 9,
225
+ "kind": "ordinary_low_activation",
226
+ "support": 9
227
+ },
228
+ "es": {
229
+ "confidence": 0.78125,
230
+ "distinct_sources": 4,
231
+ "kind": "ordinary_low_activation",
232
+ "support": 4
233
+ },
234
+ "fr": {
235
+ "confidence": 0.78125,
236
+ "distinct_sources": 12,
237
+ "kind": "ordinary_low_activation",
238
+ "support": 12
239
+ },
240
+ "it": {
241
+ "confidence": 0.78125,
242
+ "distinct_sources": 11,
243
+ "kind": "ordinary_low_activation",
244
+ "support": 11
245
+ },
246
+ "vi": {
247
+ "confidence": 0.78125,
248
+ "distinct_sources": 9,
249
+ "kind": "ordinary_low_activation",
250
+ "support": 9
251
+ }
252
+ },
253
+ "identity_active_ratios": {
254
+ "maximum": 0.903485254691689,
255
+ "median": 0.779891304347826,
256
+ "minimum": 0.5620689655172414
257
+ },
258
+ "identity_active_speech_seconds": {
259
+ "maximum": 10.11,
260
+ "median": 6.14,
261
+ "minimum": 2.8
262
+ },
263
+ "identity_dispersion": 0.06031669303774834,
264
+ "identity_distinct_source_groups": 89,
265
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
266
+ "identity_rejected_sources": 0,
267
+ "identity_rejections": [],
268
+ "identity_windows": 89,
269
+ "prototype_counts_by_language": {
270
+ "de": 20,
271
+ "en_us": 23,
272
+ "es": 10,
273
+ "fr": 18,
274
+ "it": 14,
275
+ "vi": 12
276
+ },
277
+ "prototypes": 97,
278
+ "references": 215
279
+ },
280
+ "gwen": {
281
+ "baselines": {
282
+ "de": {
283
+ "confidence": 0.78125,
284
+ "distinct_sources": 5,
285
+ "kind": "ordinary_low_activation",
286
+ "support": 5
287
+ },
288
+ "en_us": {
289
+ "confidence": 0.78125,
290
+ "distinct_sources": 12,
291
+ "kind": "ordinary_low_activation",
292
+ "support": 12
293
+ },
294
+ "es": {
295
+ "confidence": 0.78125,
296
+ "distinct_sources": 8,
297
+ "kind": "ordinary_low_activation",
298
+ "support": 8
299
+ },
300
+ "fr": {
301
+ "confidence": 0.5859375,
302
+ "distinct_sources": 3,
303
+ "kind": "ordinary_low_activation",
304
+ "support": 3
305
+ },
306
+ "it": {
307
+ "confidence": 0.78125,
308
+ "distinct_sources": 12,
309
+ "kind": "ordinary_low_activation",
310
+ "support": 12
311
+ },
312
+ "vi": {
313
+ "confidence": 0.78125,
314
+ "distinct_sources": 9,
315
+ "kind": "ordinary_low_activation",
316
+ "support": 9
317
+ }
318
+ },
319
+ "identity_active_ratios": {
320
+ "maximum": 0.8748663101604278,
321
+ "median": 0.78125,
322
+ "minimum": 0.5931899641577061
323
+ },
324
+ "identity_active_speech_seconds": {
325
+ "maximum": 9.94,
326
+ "median": 5.96,
327
+ "minimum": 2.59
328
+ },
329
+ "identity_dispersion": 0.061493881046772,
330
+ "identity_distinct_source_groups": 89,
331
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
332
+ "identity_rejected_sources": 0,
333
+ "identity_rejections": [],
334
+ "identity_windows": 89,
335
+ "prototype_counts_by_language": {
336
+ "de": 15,
337
+ "en_us": 26,
338
+ "es": 12,
339
+ "fr": 16,
340
+ "it": 15,
341
+ "vi": 14
342
+ },
343
+ "prototypes": 98,
344
+ "references": 221
345
+ },
346
+ "ink": {
347
+ "baselines": {
348
+ "de": {
349
+ "confidence": 0.5859375,
350
+ "distinct_sources": 3,
351
+ "kind": "ordinary_low_activation",
352
+ "support": 3
353
+ },
354
+ "en_gb": {
355
+ "confidence": 0.78125,
356
+ "distinct_sources": 11,
357
+ "kind": "ordinary_low_activation",
358
+ "support": 11
359
+ },
360
+ "es": {
361
+ "confidence": 0.78125,
362
+ "distinct_sources": 10,
363
+ "kind": "ordinary_low_activation",
364
+ "support": 10
365
+ },
366
+ "fr": {
367
+ "confidence": 0.5859375,
368
+ "distinct_sources": 3,
369
+ "kind": "ordinary_low_activation",
370
+ "support": 3
371
+ },
372
+ "it": {
373
+ "confidence": 0.78125,
374
+ "distinct_sources": 6,
375
+ "kind": "ordinary_low_activation",
376
+ "support": 6
377
+ },
378
+ "vi": {
379
+ "confidence": 0.78125,
380
+ "distinct_sources": 9,
381
+ "kind": "ordinary_low_activation",
382
+ "support": 9
383
+ }
384
+ },
385
+ "identity_active_ratios": {
386
+ "maximum": 0.9158050221565731,
387
+ "median": 0.7556890452341203,
388
+ "minimum": 0.5262345679012346
389
+ },
390
+ "identity_active_speech_seconds": {
391
+ "maximum": 9.66,
392
+ "median": 6.32,
393
+ "minimum": 2.97
394
+ },
395
+ "identity_dispersion": 0.05147593840956688,
396
+ "identity_distinct_source_groups": 90,
397
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
398
+ "identity_rejected_sources": 0,
399
+ "identity_rejections": [],
400
+ "identity_windows": 90,
401
+ "prototype_counts_by_language": {
402
+ "de": 12,
403
+ "en_gb": 34,
404
+ "es": 14,
405
+ "fr": 14,
406
+ "it": 10,
407
+ "vi": 18
408
+ },
409
+ "prototypes": 102,
410
+ "references": 227
411
+ },
412
+ "max": {
413
+ "baselines": {
414
+ "de": {
415
+ "confidence": 0.78125,
416
+ "distinct_sources": 4,
417
+ "kind": "ordinary_low_activation",
418
+ "support": 4
419
+ },
420
+ "en_us": {
421
+ "confidence": 0.78125,
422
+ "distinct_sources": 12,
423
+ "kind": "ordinary_low_activation",
424
+ "support": 12
425
+ },
426
+ "es": {
427
+ "confidence": 0.26041666666666663,
428
+ "distinct_sources": 2,
429
+ "kind": "ordinary_low_activation",
430
+ "support": 2
431
+ },
432
+ "fr": {
433
+ "confidence": 0.78125,
434
+ "distinct_sources": 8,
435
+ "kind": "ordinary_low_activation",
436
+ "support": 8
437
+ },
438
+ "it": {
439
+ "confidence": 0.78125,
440
+ "distinct_sources": 5,
441
+ "kind": "ordinary_low_activation",
442
+ "support": 5
443
+ },
444
+ "vi": {
445
+ "confidence": 0.78125,
446
+ "distinct_sources": 10,
447
+ "kind": "ordinary_low_activation",
448
+ "support": 10
449
+ }
450
+ },
451
+ "identity_active_ratios": {
452
+ "maximum": 0.9382716049382716,
453
+ "median": 0.7963778917243024,
454
+ "minimum": 0.5475792988313857
455
+ },
456
+ "identity_active_speech_seconds": {
457
+ "maximum": 11.07,
458
+ "median": 6.885,
459
+ "minimum": 3.09
460
+ },
461
+ "identity_dispersion": 0.04625476151704788,
462
+ "identity_distinct_source_groups": 90,
463
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
464
+ "identity_rejected_sources": 0,
465
+ "identity_rejections": [],
466
+ "identity_windows": 90,
467
+ "prototype_counts_by_language": {
468
+ "de": 19,
469
+ "en_us": 35,
470
+ "es": 12,
471
+ "fr": 11,
472
+ "it": 10,
473
+ "vi": 17
474
+ },
475
+ "prototypes": 104,
476
+ "references": 230
477
+ },
478
+ "orpheus": {
479
+ "baselines": {
480
+ "de": {
481
+ "confidence": 0.78125,
482
+ "distinct_sources": 4,
483
+ "kind": "ordinary_low_activation",
484
+ "support": 4
485
+ },
486
+ "en_gb": {
487
+ "confidence": 0.78125,
488
+ "distinct_sources": 12,
489
+ "kind": "ordinary_low_activation",
490
+ "support": 12
491
+ },
492
+ "es": {
493
+ "confidence": 0.78125,
494
+ "distinct_sources": 4,
495
+ "kind": "ordinary_low_activation",
496
+ "support": 4
497
+ },
498
+ "fr": {
499
+ "confidence": 0.78125,
500
+ "distinct_sources": 10,
501
+ "kind": "ordinary_low_activation",
502
+ "support": 10
503
+ },
504
+ "it": {
505
+ "confidence": 0.78125,
506
+ "distinct_sources": 5,
507
+ "kind": "ordinary_low_activation",
508
+ "support": 5
509
+ },
510
+ "vi": {
511
+ "confidence": 0.78125,
512
+ "distinct_sources": 9,
513
+ "kind": "ordinary_low_activation",
514
+ "support": 9
515
+ }
516
+ },
517
+ "identity_active_ratios": {
518
+ "maximum": 0.9351432880844646,
519
+ "median": 0.7728739347305791,
520
+ "minimum": 0.5242070116861436
521
+ },
522
+ "identity_active_speech_seconds": {
523
+ "maximum": 9.66,
524
+ "median": 6.135,
525
+ "minimum": 2.53
526
+ },
527
+ "identity_dispersion": 0.05940033495426178,
528
+ "identity_distinct_source_groups": 88,
529
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
530
+ "identity_rejected_sources": 1,
531
+ "identity_rejections": [
532
+ {
533
+ "reason": "identity source failed VAD qualification: active_ratio",
534
+ "reference_id": "orpheus:en:sadness:base_overlay_fill__11labs_sadness_whisper_01"
535
+ }
536
+ ],
537
+ "identity_windows": 88,
538
+ "prototype_counts_by_language": {
539
+ "de": 10,
540
+ "en_gb": 24,
541
+ "es": 13,
542
+ "fr": 12,
543
+ "it": 8,
544
+ "vi": 17
545
+ },
546
+ "prototypes": 84,
547
+ "references": 209
548
+ },
549
+ "rex": {
550
+ "baselines": {
551
+ "de": {
552
+ "confidence": 0.78125,
553
+ "distinct_sources": 6,
554
+ "kind": "ordinary_low_activation",
555
+ "support": 6
556
+ },
557
+ "en_us": {
558
+ "confidence": 0.78125,
559
+ "distinct_sources": 8,
560
+ "kind": "ordinary_low_activation",
561
+ "support": 8
562
+ },
563
+ "es": {
564
+ "confidence": 0.78125,
565
+ "distinct_sources": 7,
566
+ "kind": "ordinary_low_activation",
567
+ "support": 7
568
+ },
569
+ "fr": {
570
+ "confidence": 0.78125,
571
+ "distinct_sources": 4,
572
+ "kind": "ordinary_low_activation",
573
+ "support": 4
574
+ },
575
+ "it": {
576
+ "confidence": 0.78125,
577
+ "distinct_sources": 5,
578
+ "kind": "ordinary_low_activation",
579
+ "support": 5
580
+ },
581
+ "vi": {
582
+ "confidence": 0.78125,
583
+ "distinct_sources": 9,
584
+ "kind": "ordinary_low_activation",
585
+ "support": 9
586
+ }
587
+ },
588
+ "identity_active_ratios": {
589
+ "maximum": 0.9013452914798207,
590
+ "median": 0.8139931740614335,
591
+ "minimum": 0.5089285714285714
592
+ },
593
+ "identity_active_speech_seconds": {
594
+ "maximum": 10.62,
595
+ "median": 6.55,
596
+ "minimum": 2.79
597
+ },
598
+ "identity_dispersion": 0.028971850872039795,
599
+ "identity_distinct_source_groups": 89,
600
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
601
+ "identity_rejected_sources": 0,
602
+ "identity_rejections": [],
603
+ "identity_windows": 89,
604
+ "prototype_counts_by_language": {
605
+ "de": 15,
606
+ "en_us": 20,
607
+ "es": 10,
608
+ "fr": 10,
609
+ "it": 7,
610
+ "vi": 13
611
+ },
612
+ "prototypes": 75,
613
+ "references": 196
614
+ },
615
+ "scylla": {
616
+ "baselines": {
617
+ "de": {
618
+ "confidence": 0.78125,
619
+ "distinct_sources": 11,
620
+ "kind": "ordinary_low_activation",
621
+ "support": 11
622
+ },
623
+ "en_us": {
624
+ "confidence": 0.78125,
625
+ "distinct_sources": 12,
626
+ "kind": "ordinary_low_activation",
627
+ "support": 12
628
+ },
629
+ "es": {
630
+ "confidence": 0.06510416666666666,
631
+ "distinct_sources": 1,
632
+ "kind": "ordinary_low_activation",
633
+ "support": 1
634
+ },
635
+ "fr": {
636
+ "confidence": 0.5859375,
637
+ "distinct_sources": 3,
638
+ "kind": "ordinary_low_activation",
639
+ "support": 3
640
+ },
641
+ "it": {
642
+ "confidence": 0.5859375,
643
+ "distinct_sources": 3,
644
+ "kind": "ordinary_low_activation",
645
+ "support": 3
646
+ },
647
+ "vi": {
648
+ "confidence": 0.78125,
649
+ "distinct_sources": 9,
650
+ "kind": "ordinary_low_activation",
651
+ "support": 9
652
+ }
653
+ },
654
+ "identity_active_ratios": {
655
+ "maximum": 0.8613861386138614,
656
+ "median": 0.7674025282572805,
657
+ "minimum": 0.5846325167037862
658
+ },
659
+ "identity_active_speech_seconds": {
660
+ "maximum": 9.61,
661
+ "median": 5.835,
662
+ "minimum": 2.26
663
+ },
664
+ "identity_dispersion": 0.038124531507492065,
665
+ "identity_distinct_source_groups": 90,
666
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
667
+ "identity_rejected_sources": 0,
668
+ "identity_rejections": [],
669
+ "identity_windows": 90,
670
+ "prototype_counts_by_language": {
671
+ "de": 20,
672
+ "en_us": 27,
673
+ "es": 9,
674
+ "fr": 12,
675
+ "it": 6,
676
+ "vi": 13
677
+ },
678
+ "prototypes": 87,
679
+ "references": 208
680
+ },
681
+ "stone": {
682
+ "baselines": {
683
+ "de": {
684
+ "confidence": 0.78125,
685
+ "distinct_sources": 5,
686
+ "kind": "ordinary_low_activation",
687
+ "support": 5
688
+ },
689
+ "en_us": {
690
+ "confidence": 0.78125,
691
+ "distinct_sources": 10,
692
+ "kind": "ordinary_low_activation",
693
+ "support": 10
694
+ },
695
+ "es": {
696
+ "confidence": 0.78125,
697
+ "distinct_sources": 7,
698
+ "kind": "ordinary_low_activation",
699
+ "support": 7
700
+ },
701
+ "fr": {
702
+ "confidence": 0.78125,
703
+ "distinct_sources": 7,
704
+ "kind": "ordinary_low_activation",
705
+ "support": 7
706
+ },
707
+ "it": {
708
+ "confidence": 0.78125,
709
+ "distinct_sources": 10,
710
+ "kind": "ordinary_low_activation",
711
+ "support": 10
712
+ },
713
+ "vi": {
714
+ "confidence": 0.78125,
715
+ "distinct_sources": 12,
716
+ "kind": "ordinary_low_activation",
717
+ "support": 12
718
+ }
719
+ },
720
+ "identity_active_ratios": {
721
+ "maximum": 0.9298831385642737,
722
+ "median": 0.8104118238906429,
723
+ "minimum": 0.5950819672131148
724
+ },
725
+ "identity_active_speech_seconds": {
726
+ "maximum": 11.14,
727
+ "median": 6.8100000000000005,
728
+ "minimum": 2.41
729
+ },
730
+ "identity_dispersion": 0.05702367424964905,
731
+ "identity_distinct_source_groups": 90,
732
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
733
+ "identity_rejected_sources": 0,
734
+ "identity_rejections": [],
735
+ "identity_windows": 90,
736
+ "prototype_counts_by_language": {
737
+ "de": 17,
738
+ "en_us": 20,
739
+ "es": 9,
740
+ "fr": 11,
741
+ "it": 8,
742
+ "vi": 18
743
+ },
744
+ "prototypes": 83,
745
+ "references": 203
746
+ },
747
+ "tuesday": {
748
+ "baselines": {
749
+ "de": {
750
+ "confidence": 0.78125,
751
+ "distinct_sources": 5,
752
+ "kind": "ordinary_low_activation",
753
+ "support": 5
754
+ },
755
+ "en_gb": {
756
+ "confidence": 0.78125,
757
+ "distinct_sources": 10,
758
+ "kind": "ordinary_low_activation",
759
+ "support": 10
760
+ },
761
+ "es": {
762
+ "confidence": 0.78125,
763
+ "distinct_sources": 5,
764
+ "kind": "ordinary_low_activation",
765
+ "support": 5
766
+ },
767
+ "fr": {
768
+ "confidence": 0.78125,
769
+ "distinct_sources": 9,
770
+ "kind": "ordinary_low_activation",
771
+ "support": 9
772
+ },
773
+ "it": {
774
+ "confidence": 0.78125,
775
+ "distinct_sources": 9,
776
+ "kind": "ordinary_low_activation",
777
+ "support": 9
778
+ },
779
+ "vi": {
780
+ "confidence": 0.78125,
781
+ "distinct_sources": 7,
782
+ "kind": "ordinary_low_activation",
783
+ "support": 7
784
+ }
785
+ },
786
+ "identity_active_ratios": {
787
+ "maximum": 0.8780918727915195,
788
+ "median": 0.7484227443206477,
789
+ "minimum": 0.5039872408293461
790
+ },
791
+ "identity_active_speech_seconds": {
792
+ "maximum": 10.24,
793
+ "median": 6.165,
794
+ "minimum": 2.63
795
+ },
796
+ "identity_dispersion": 0.043402332812547684,
797
+ "identity_distinct_source_groups": 90,
798
+ "identity_preprocess_contract": "mono_16k_energy_vad_best_window_2s_12s_speech2s_ratio0p50_clip0p001_wavlm_feature_extractor_v2",
799
+ "identity_rejected_sources": 0,
800
+ "identity_rejections": [],
801
+ "identity_windows": 90,
802
+ "prototype_counts_by_language": {
803
+ "de": 10,
804
+ "en_gb": 22,
805
+ "es": 7,
806
+ "fr": 16,
807
+ "it": 13,
808
+ "vi": 15
809
+ },
810
+ "prototypes": 83,
811
+ "references": 194
812
+ }
813
+ },
814
+ "schema_version": "scyllasband_reference_pack_index_v4",
815
+ "v3_membership_audit_source": {
816
+ "path": "/media/sean/data/aiwork/output/emotional_multilingual_v3/voices/reference_packs.json",
817
+ "sha256": "4f456704c4d0d62156f0f9a44a33c8c6cdbbd71fa17f51a9cb7473cb7f53cb7b",
818
+ "size_bytes": 11579
819
+ },
820
+ "voices": {
821
+ "ariadne": {
822
+ "baselines": 6,
823
+ "identity_windows": 90,
824
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/ariadne.npz",
825
+ "prototypes": 89,
826
+ "references": 216,
827
+ "sha256": "28fa680e7338121eb517d90fb52bef000259b0882cb2ff523bef160f9a6ad7e0",
828
+ "size_bytes": 256110
829
+ },
830
+ "felix": {
831
+ "baselines": 6,
832
+ "identity_windows": 89,
833
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/felix.npz",
834
+ "prototypes": 97,
835
+ "references": 215,
836
+ "sha256": "44fe52012afd583abfea1ecdd45a6f381add43bed668cb61a5df6fa9913d5823",
837
+ "size_bytes": 255046
838
+ },
839
+ "gwen": {
840
+ "baselines": 6,
841
+ "identity_windows": 89,
842
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/gwen.npz",
843
+ "prototypes": 98,
844
+ "references": 221,
845
+ "sha256": "99375b97a65ce117300b99aec9c6299084cdbcf1d87084b73923aac7fa26ece3",
846
+ "size_bytes": 256021
847
+ },
848
+ "ink": {
849
+ "baselines": 6,
850
+ "identity_windows": 90,
851
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/ink.npz",
852
+ "prototypes": 102,
853
+ "references": 227,
854
+ "sha256": "793eca609ae0765db20fa678f8591594e64400967555c74607bc71218e112230",
855
+ "size_bytes": 260271
856
+ },
857
+ "max": {
858
+ "baselines": 6,
859
+ "identity_windows": 90,
860
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/max.npz",
861
+ "prototypes": 104,
862
+ "references": 230,
863
+ "sha256": "2e8a830c4bfc912b6a04dc674ecce3946515d7f5bfdef16267b8e4a51f5a40d9",
864
+ "size_bytes": 260997
865
+ },
866
+ "orpheus": {
867
+ "baselines": 6,
868
+ "identity_windows": 88,
869
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/orpheus.npz",
870
+ "prototypes": 84,
871
+ "references": 209,
872
+ "sha256": "8782dd27c7581a6fa0909dad5c247e55bb3220d0ee42225921907723205cbe50",
873
+ "size_bytes": 250919
874
+ },
875
+ "rex": {
876
+ "baselines": 6,
877
+ "identity_windows": 89,
878
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/rex.npz",
879
+ "prototypes": 75,
880
+ "references": 196,
881
+ "sha256": "c79017c09774734216caf0ba2a40bde0fa5f4c86e5baca214c191ee739b95f05",
882
+ "size_bytes": 248214
883
+ },
884
+ "scylla": {
885
+ "baselines": 6,
886
+ "identity_windows": 90,
887
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/scylla.npz",
888
+ "prototypes": 87,
889
+ "references": 208,
890
+ "sha256": "b1e2d4a8289b3a10653f99413591e8ab539aa2717fef1b04612b2926e92aeaf4",
891
+ "size_bytes": 254240
892
+ },
893
+ "stone": {
894
+ "baselines": 6,
895
+ "identity_windows": 90,
896
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/stone.npz",
897
+ "prototypes": 83,
898
+ "references": 203,
899
+ "sha256": "d9edccaaceff333b65a70408aec2561980716ad00bb0e040c499d05938cb093b",
900
+ "size_bytes": 253184
901
+ },
902
+ "tuesday": {
903
+ "baselines": 6,
904
+ "identity_windows": 90,
905
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/prepared/reference_packs/npz/tuesday.npz",
906
+ "prototypes": 83,
907
+ "references": 194,
908
+ "sha256": "e34924f14b47138a56447857c0c504c186d0fbb421c20ca0884a41430c20f63b",
909
+ "size_bytes": 249532
910
+ }
911
+ },
912
+ "staged_from": {
913
+ "path": "/home/sean/aiTools/datasetGen/output/scyllasband/scyllasband_v2_clean_202608/input/reference_packs_v4/reference_packs.json",
914
+ "sha256": "35c3643bfce06ed0a08badd0f68d899ac9f27205edd928668caf43a1e8039a60"
915
+ }
916
+ }
onnx-int8/assets/voice_packs/rex.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79017c09774734216caf0ba2a40bde0fa5f4c86e5baca214c191ee739b95f05
3
+ size 248214
onnx-int8/assets/voice_packs/scylla.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e2d4a8289b3a10653f99413591e8ab539aa2717fef1b04612b2926e92aeaf4
3
+ size 254240
onnx-int8/assets/voice_packs/stone.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9edccaaceff333b65a70408aec2561980716ad00bb0e040c499d05938cb093b
3
+ size 253184
onnx-int8/assets/voice_packs/tuesday.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e34924f14b47138a56447857c0c504c186d0fbb421c20ca0884a41430c20f63b
3
+ size 249532
onnx-int8/assets/voices.json ADDED
@@ -0,0 +1,972 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": "ariadne",
4
+ "index": 0,
5
+ "samples": 455892,
6
+ "duration_seconds": 1840551.9077083508,
7
+ "by_language": {
8
+ "de": 66638,
9
+ "en_us": 119640,
10
+ "es": 77211,
11
+ "fr": 68318,
12
+ "it": 81524,
13
+ "vi": 42561
14
+ },
15
+ "by_emotion": {
16
+ "anger": 113699,
17
+ "angry": 3081,
18
+ "calm": 88083,
19
+ "excited": 3022,
20
+ "friendly": 2801,
21
+ "frustrated": 2420,
22
+ "happy": 2957,
23
+ "joy": 112961,
24
+ "neutral": 4226,
25
+ "sad": 2368,
26
+ "sadness": 115408,
27
+ "sarcastic": 2771,
28
+ "unsure": 2095
29
+ },
30
+ "by_language_emotion": {
31
+ "de|anger": 16121,
32
+ "de|angry": 67,
33
+ "de|calm": 13457,
34
+ "de|happy": 27,
35
+ "de|joy": 19071,
36
+ "de|neutral": 67,
37
+ "de|sad": 32,
38
+ "de|sadness": 17796,
39
+ "en_us|anger": 31666,
40
+ "en_us|angry": 1578,
41
+ "en_us|calm": 17091,
42
+ "en_us|excited": 1692,
43
+ "en_us|friendly": 1497,
44
+ "en_us|frustrated": 1452,
45
+ "en_us|happy": 1458,
46
+ "en_us|joy": 27806,
47
+ "en_us|neutral": 3142,
48
+ "en_us|sad": 1251,
49
+ "en_us|sadness": 28367,
50
+ "en_us|sarcastic": 1545,
51
+ "en_us|unsure": 1095,
52
+ "es|anger": 19064,
53
+ "es|angry": 492,
54
+ "es|calm": 15813,
55
+ "es|excited": 547,
56
+ "es|friendly": 504,
57
+ "es|frustrated": 365,
58
+ "es|happy": 568,
59
+ "es|joy": 18815,
60
+ "es|neutral": 59,
61
+ "es|sad": 500,
62
+ "es|sadness": 19508,
63
+ "es|sarcastic": 549,
64
+ "es|unsure": 427,
65
+ "fr|anger": 18503,
66
+ "fr|angry": 52,
67
+ "fr|calm": 13218,
68
+ "fr|happy": 33,
69
+ "fr|joy": 16447,
70
+ "fr|neutral": 66,
71
+ "fr|sadness": 19999,
72
+ "it|anger": 17708,
73
+ "it|angry": 857,
74
+ "it|calm": 18525,
75
+ "it|excited": 783,
76
+ "it|friendly": 800,
77
+ "it|frustrated": 603,
78
+ "it|happy": 833,
79
+ "it|joy": 19256,
80
+ "it|neutral": 844,
81
+ "it|sad": 555,
82
+ "it|sadness": 19510,
83
+ "it|sarcastic": 677,
84
+ "it|unsure": 573,
85
+ "vi|anger": 10637,
86
+ "vi|angry": 35,
87
+ "vi|calm": 9979,
88
+ "vi|happy": 38,
89
+ "vi|joy": 11566,
90
+ "vi|neutral": 48,
91
+ "vi|sad": 30,
92
+ "vi|sadness": 10228
93
+ },
94
+ "by_split": {
95
+ "test": 917,
96
+ "train": 449680,
97
+ "val": 5295
98
+ }
99
+ },
100
+ {
101
+ "id": "felix",
102
+ "index": 1,
103
+ "samples": 404091,
104
+ "duration_seconds": 1594860.1030832995,
105
+ "by_language": {
106
+ "de": 51242,
107
+ "en_us": 108862,
108
+ "es": 70792,
109
+ "fr": 57157,
110
+ "it": 78965,
111
+ "vi": 37073
112
+ },
113
+ "by_emotion": {
114
+ "anger": 97394,
115
+ "angry": 2667,
116
+ "calm": 78796,
117
+ "excited": 2854,
118
+ "friendly": 2764,
119
+ "frustrated": 2081,
120
+ "happy": 2741,
121
+ "joy": 101462,
122
+ "neutral": 4504,
123
+ "sad": 2044,
124
+ "sadness": 102310,
125
+ "sarcastic": 2447,
126
+ "unsure": 2027
127
+ },
128
+ "by_language_emotion": {
129
+ "de|anger": 11767,
130
+ "de|angry": 59,
131
+ "de|calm": 11353,
132
+ "de|happy": 27,
133
+ "de|joy": 13488,
134
+ "de|neutral": 67,
135
+ "de|sad": 30,
136
+ "de|sadness": 14451,
137
+ "en_us|anger": 25617,
138
+ "en_us|angry": 1348,
139
+ "en_us|calm": 15384,
140
+ "en_us|excited": 1460,
141
+ "en_us|friendly": 1526,
142
+ "en_us|frustrated": 1243,
143
+ "en_us|happy": 1389,
144
+ "en_us|joy": 25798,
145
+ "en_us|neutral": 2855,
146
+ "en_us|sad": 1100,
147
+ "en_us|sadness": 28783,
148
+ "en_us|sarcastic": 1248,
149
+ "en_us|unsure": 1111,
150
+ "es|anger": 16850,
151
+ "es|angry": 419,
152
+ "es|calm": 16342,
153
+ "es|excited": 571,
154
+ "es|friendly": 509,
155
+ "es|frustrated": 311,
156
+ "es|happy": 593,
157
+ "es|joy": 16887,
158
+ "es|neutral": 645,
159
+ "es|sad": 396,
160
+ "es|sadness": 16392,
161
+ "es|sarcastic": 514,
162
+ "es|unsure": 363,
163
+ "fr|anger": 16184,
164
+ "fr|angry": 40,
165
+ "fr|calm": 9303,
166
+ "fr|happy": 34,
167
+ "fr|joy": 17208,
168
+ "fr|sadness": 14388,
169
+ "it|anger": 18281,
170
+ "it|angry": 779,
171
+ "it|calm": 17884,
172
+ "it|excited": 823,
173
+ "it|friendly": 729,
174
+ "it|frustrated": 527,
175
+ "it|happy": 653,
176
+ "it|joy": 18293,
177
+ "it|neutral": 918,
178
+ "it|sad": 461,
179
+ "it|sadness": 18379,
180
+ "it|sarcastic": 685,
181
+ "it|unsure": 553,
182
+ "vi|anger": 8695,
183
+ "vi|angry": 22,
184
+ "vi|calm": 8530,
185
+ "vi|happy": 45,
186
+ "vi|joy": 9788,
187
+ "vi|neutral": 19,
188
+ "vi|sad": 57,
189
+ "vi|sadness": 9917
190
+ },
191
+ "by_split": {
192
+ "test": 6509,
193
+ "train": 397582
194
+ }
195
+ },
196
+ {
197
+ "id": "gwen",
198
+ "index": 2,
199
+ "samples": 397375,
200
+ "duration_seconds": 1538322.4992083265,
201
+ "by_language": {
202
+ "de": 58693,
203
+ "en_us": 106094,
204
+ "es": 67783,
205
+ "fr": 57477,
206
+ "it": 75306,
207
+ "vi": 32022
208
+ },
209
+ "by_emotion": {
210
+ "anger": 96722,
211
+ "angry": 2792,
212
+ "calm": 74923,
213
+ "excited": 2067,
214
+ "friendly": 2556,
215
+ "frustrated": 2113,
216
+ "happy": 2539,
217
+ "joy": 98640,
218
+ "neutral": 4444,
219
+ "sad": 2020,
220
+ "sadness": 104395,
221
+ "sarcastic": 2245,
222
+ "unsure": 1919
223
+ },
224
+ "by_language_emotion": {
225
+ "de|anger": 15657,
226
+ "de|angry": 59,
227
+ "de|calm": 11078,
228
+ "de|happy": 34,
229
+ "de|joy": 15899,
230
+ "de|neutral": 42,
231
+ "de|sad": 40,
232
+ "de|sadness": 15884,
233
+ "en_us|anger": 25114,
234
+ "en_us|angry": 1451,
235
+ "en_us|calm": 14596,
236
+ "en_us|excited": 1358,
237
+ "en_us|friendly": 1463,
238
+ "en_us|frustrated": 1282,
239
+ "en_us|happy": 1325,
240
+ "en_us|joy": 24280,
241
+ "en_us|neutral": 2903,
242
+ "en_us|sad": 1092,
243
+ "en_us|sadness": 28975,
244
+ "en_us|sarcastic": 1168,
245
+ "en_us|unsure": 1087,
246
+ "es|anger": 15711,
247
+ "es|angry": 532,
248
+ "es|calm": 12529,
249
+ "es|friendly": 441,
250
+ "es|frustrated": 306,
251
+ "es|happy": 469,
252
+ "es|joy": 15912,
253
+ "es|neutral": 569,
254
+ "es|sad": 367,
255
+ "es|sadness": 20156,
256
+ "es|sarcastic": 456,
257
+ "es|unsure": 335,
258
+ "fr|anger": 14959,
259
+ "fr|angry": 29,
260
+ "fr|calm": 11436,
261
+ "fr|happy": 41,
262
+ "fr|joy": 16868,
263
+ "fr|neutral": 24,
264
+ "fr|sad": 51,
265
+ "fr|sadness": 14069,
266
+ "it|anger": 16984,
267
+ "it|angry": 701,
268
+ "it|calm": 17615,
269
+ "it|excited": 709,
270
+ "it|friendly": 652,
271
+ "it|frustrated": 525,
272
+ "it|happy": 625,
273
+ "it|joy": 17628,
274
+ "it|neutral": 888,
275
+ "it|sad": 423,
276
+ "it|sadness": 17438,
277
+ "it|sarcastic": 621,
278
+ "it|unsure": 497,
279
+ "vi|anger": 8297,
280
+ "vi|angry": 20,
281
+ "vi|calm": 7669,
282
+ "vi|happy": 45,
283
+ "vi|joy": 8053,
284
+ "vi|neutral": 18,
285
+ "vi|sad": 47,
286
+ "vi|sadness": 7873
287
+ },
288
+ "by_split": {
289
+ "test": 5129,
290
+ "train": 392021,
291
+ "val": 225
292
+ }
293
+ },
294
+ {
295
+ "id": "ink",
296
+ "index": 3,
297
+ "samples": 435547,
298
+ "duration_seconds": 1732036.888458335,
299
+ "by_language": {
300
+ "de": 59247,
301
+ "en_gb": 113968,
302
+ "es": 73721,
303
+ "fr": 56158,
304
+ "it": 83663,
305
+ "vi": 48790
306
+ },
307
+ "by_emotion": {
308
+ "anger": 100018,
309
+ "angry": 2199,
310
+ "calm": 88019,
311
+ "excited": 2952,
312
+ "friendly": 2939,
313
+ "frustrated": 1819,
314
+ "happy": 2850,
315
+ "joy": 112067,
316
+ "neutral": 4701,
317
+ "sad": 2026,
318
+ "sadness": 112271,
319
+ "sarcastic": 2691,
320
+ "unsure": 995
321
+ },
322
+ "by_language_emotion": {
323
+ "de|anger": 15888,
324
+ "de|angry": 29,
325
+ "de|calm": 11926,
326
+ "de|happy": 53,
327
+ "de|joy": 15329,
328
+ "de|neutral": 33,
329
+ "de|sad": 73,
330
+ "de|sadness": 15916,
331
+ "en_gb|anger": 25411,
332
+ "en_gb|angry": 1614,
333
+ "en_gb|calm": 15361,
334
+ "en_gb|excited": 1647,
335
+ "en_gb|friendly": 1713,
336
+ "en_gb|frustrated": 1512,
337
+ "en_gb|happy": 1514,
338
+ "en_gb|joy": 27359,
339
+ "en_gb|neutral": 2986,
340
+ "en_gb|sad": 1368,
341
+ "en_gb|sadness": 32086,
342
+ "en_gb|sarcastic": 1397,
343
+ "es|anger": 11480,
344
+ "es|angry": 470,
345
+ "es|calm": 17615,
346
+ "es|excited": 549,
347
+ "es|friendly": 509,
348
+ "es|frustrated": 307,
349
+ "es|happy": 548,
350
+ "es|joy": 23966,
351
+ "es|neutral": 753,
352
+ "es|sadness": 16581,
353
+ "es|sarcastic": 547,
354
+ "es|unsure": 396,
355
+ "fr|anger": 15344,
356
+ "fr|angry": 39,
357
+ "fr|calm": 11026,
358
+ "fr|happy": 37,
359
+ "fr|joy": 15526,
360
+ "fr|sad": 53,
361
+ "fr|sadness": 14133,
362
+ "it|anger": 21226,
363
+ "it|calm": 19311,
364
+ "it|excited": 756,
365
+ "it|friendly": 717,
366
+ "it|happy": 672,
367
+ "it|joy": 18118,
368
+ "it|neutral": 880,
369
+ "it|sad": 495,
370
+ "it|sadness": 20142,
371
+ "it|sarcastic": 747,
372
+ "it|unsure": 599,
373
+ "vi|anger": 10669,
374
+ "vi|angry": 47,
375
+ "vi|calm": 12780,
376
+ "vi|happy": 26,
377
+ "vi|joy": 11769,
378
+ "vi|neutral": 49,
379
+ "vi|sad": 37,
380
+ "vi|sadness": 13413
381
+ },
382
+ "by_split": {
383
+ "test": 8461,
384
+ "train": 421246,
385
+ "val": 5840
386
+ }
387
+ },
388
+ {
389
+ "id": "max",
390
+ "index": 4,
391
+ "samples": 424385,
392
+ "duration_seconds": 1687073.5253750135,
393
+ "by_language": {
394
+ "de": 62403,
395
+ "en_us": 109285,
396
+ "es": 73466,
397
+ "fr": 59004,
398
+ "it": 80233,
399
+ "vi": 39994
400
+ },
401
+ "by_emotion": {
402
+ "anger": 106674,
403
+ "angry": 2821,
404
+ "calm": 83256,
405
+ "excited": 2814,
406
+ "friendly": 2683,
407
+ "frustrated": 2162,
408
+ "happy": 2746,
409
+ "joy": 102374,
410
+ "neutral": 4836,
411
+ "sad": 2296,
412
+ "sadness": 107074,
413
+ "sarcastic": 2625,
414
+ "unsure": 2024
415
+ },
416
+ "by_language_emotion": {
417
+ "de|anger": 16881,
418
+ "de|angry": 22,
419
+ "de|calm": 12514,
420
+ "de|happy": 65,
421
+ "de|joy": 16109,
422
+ "de|neutral": 24,
423
+ "de|sad": 68,
424
+ "de|sadness": 16720,
425
+ "en_us|anger": 27530,
426
+ "en_us|angry": 1334,
427
+ "en_us|calm": 13282,
428
+ "en_us|excited": 1529,
429
+ "en_us|friendly": 1591,
430
+ "en_us|frustrated": 1129,
431
+ "en_us|happy": 1547,
432
+ "en_us|joy": 26807,
433
+ "en_us|neutral": 2998,
434
+ "en_us|sad": 1235,
435
+ "en_us|sadness": 27896,
436
+ "en_us|sarcastic": 1325,
437
+ "en_us|unsure": 1082,
438
+ "es|anger": 16947,
439
+ "es|angry": 497,
440
+ "es|calm": 17674,
441
+ "es|excited": 491,
442
+ "es|friendly": 466,
443
+ "es|frustrated": 349,
444
+ "es|happy": 445,
445
+ "es|joy": 17471,
446
+ "es|neutral": 780,
447
+ "es|sad": 406,
448
+ "es|sadness": 17004,
449
+ "es|sarcastic": 569,
450
+ "es|unsure": 367,
451
+ "fr|anger": 16001,
452
+ "fr|angry": 45,
453
+ "fr|calm": 12547,
454
+ "fr|happy": 24,
455
+ "fr|joy": 14315,
456
+ "fr|neutral": 60,
457
+ "fr|sad": 35,
458
+ "fr|sadness": 15977,
459
+ "it|anger": 18857,
460
+ "it|angry": 885,
461
+ "it|calm": 18002,
462
+ "it|excited": 794,
463
+ "it|friendly": 626,
464
+ "it|frustrated": 684,
465
+ "it|happy": 645,
466
+ "it|joy": 18472,
467
+ "it|neutral": 930,
468
+ "it|sad": 520,
469
+ "it|sadness": 18512,
470
+ "it|sarcastic": 731,
471
+ "it|unsure": 575,
472
+ "vi|anger": 10458,
473
+ "vi|angry": 38,
474
+ "vi|calm": 9237,
475
+ "vi|happy": 20,
476
+ "vi|joy": 9200,
477
+ "vi|neutral": 44,
478
+ "vi|sad": 32,
479
+ "vi|sadness": 10965
480
+ },
481
+ "by_split": {
482
+ "test": 5855,
483
+ "train": 403815,
484
+ "val": 14715
485
+ }
486
+ },
487
+ {
488
+ "id": "orpheus",
489
+ "index": 5,
490
+ "samples": 415144,
491
+ "duration_seconds": 1664056.8369166418,
492
+ "by_language": {
493
+ "de": 56143,
494
+ "en_gb": 112834,
495
+ "es": 71301,
496
+ "fr": 52987,
497
+ "it": 83145,
498
+ "vi": 38734
499
+ },
500
+ "by_emotion": {
501
+ "anger": 104220,
502
+ "angry": 2975,
503
+ "calm": 86078,
504
+ "excited": 2813,
505
+ "friendly": 2828,
506
+ "frustrated": 2441,
507
+ "happy": 2907,
508
+ "joy": 95909,
509
+ "neutral": 4792,
510
+ "sad": 2328,
511
+ "sadness": 103235,
512
+ "sarcastic": 2450,
513
+ "unsure": 2168
514
+ },
515
+ "by_language_emotion": {
516
+ "de|anger": 17423,
517
+ "de|angry": 55,
518
+ "de|calm": 11973,
519
+ "de|happy": 41,
520
+ "de|joy": 13727,
521
+ "de|neutral": 53,
522
+ "de|sad": 26,
523
+ "de|sadness": 12845,
524
+ "en_gb|anger": 27769,
525
+ "en_gb|angry": 1608,
526
+ "en_gb|calm": 16678,
527
+ "en_gb|excited": 1568,
528
+ "en_gb|friendly": 1599,
529
+ "en_gb|frustrated": 1466,
530
+ "en_gb|happy": 1507,
531
+ "en_gb|joy": 24367,
532
+ "en_gb|neutral": 3210,
533
+ "en_gb|sad": 1287,
534
+ "en_gb|sadness": 29354,
535
+ "en_gb|sarcastic": 1282,
536
+ "en_gb|unsure": 1139,
537
+ "es|anger": 16146,
538
+ "es|angry": 492,
539
+ "es|calm": 17293,
540
+ "es|excited": 486,
541
+ "es|friendly": 391,
542
+ "es|frustrated": 347,
543
+ "es|happy": 516,
544
+ "es|joy": 16014,
545
+ "es|neutral": 585,
546
+ "es|sad": 437,
547
+ "es|sadness": 17709,
548
+ "es|sarcastic": 454,
549
+ "es|unsure": 431,
550
+ "fr|anger": 14508,
551
+ "fr|angry": 24,
552
+ "fr|calm": 11697,
553
+ "fr|happy": 56,
554
+ "fr|joy": 12792,
555
+ "fr|neutral": 26,
556
+ "fr|sad": 56,
557
+ "fr|sadness": 13828,
558
+ "it|anger": 18468,
559
+ "it|angry": 775,
560
+ "it|calm": 19120,
561
+ "it|excited": 759,
562
+ "it|friendly": 838,
563
+ "it|frustrated": 628,
564
+ "it|happy": 755,
565
+ "it|joy": 19799,
566
+ "it|neutral": 874,
567
+ "it|sad": 507,
568
+ "it|sadness": 19310,
569
+ "it|sarcastic": 714,
570
+ "it|unsure": 598,
571
+ "vi|anger": 9906,
572
+ "vi|angry": 21,
573
+ "vi|calm": 9317,
574
+ "vi|happy": 32,
575
+ "vi|joy": 9210,
576
+ "vi|neutral": 44,
577
+ "vi|sad": 15,
578
+ "vi|sadness": 10189
579
+ },
580
+ "by_split": {
581
+ "test": 1,
582
+ "train": 415130,
583
+ "val": 13
584
+ }
585
+ },
586
+ {
587
+ "id": "rex",
588
+ "index": 6,
589
+ "samples": 419413,
590
+ "duration_seconds": 1668331.6962083348,
591
+ "by_language": {
592
+ "de": 59943,
593
+ "en_us": 114522,
594
+ "es": 73001,
595
+ "fr": 50588,
596
+ "it": 80816,
597
+ "vi": 40543
598
+ },
599
+ "by_emotion": {
600
+ "anger": 105673,
601
+ "angry": 1897,
602
+ "calm": 84890,
603
+ "excited": 1998,
604
+ "friendly": 2636,
605
+ "frustrated": 1550,
606
+ "happy": 2757,
607
+ "joy": 104647,
608
+ "neutral": 4750,
609
+ "sad": 2389,
610
+ "sadness": 101840,
611
+ "sarcastic": 2445,
612
+ "unsure": 1941
613
+ },
614
+ "by_language_emotion": {
615
+ "de|anger": 16470,
616
+ "de|calm": 11935,
617
+ "de|happy": 36,
618
+ "de|joy": 13429,
619
+ "de|neutral": 39,
620
+ "de|sad": 39,
621
+ "de|sadness": 17995,
622
+ "en_us|anger": 27386,
623
+ "en_us|angry": 1437,
624
+ "en_us|calm": 16009,
625
+ "en_us|excited": 1434,
626
+ "en_us|friendly": 1488,
627
+ "en_us|frustrated": 1222,
628
+ "en_us|happy": 1396,
629
+ "en_us|joy": 31503,
630
+ "en_us|neutral": 3106,
631
+ "en_us|sad": 1281,
632
+ "en_us|sadness": 25976,
633
+ "en_us|sarcastic": 1250,
634
+ "en_us|unsure": 1034,
635
+ "es|anger": 17145,
636
+ "es|angry": 437,
637
+ "es|calm": 17234,
638
+ "es|excited": 564,
639
+ "es|friendly": 445,
640
+ "es|frustrated": 328,
641
+ "es|happy": 493,
642
+ "es|joy": 17216,
643
+ "es|neutral": 682,
644
+ "es|sad": 443,
645
+ "es|sadness": 17176,
646
+ "es|sarcastic": 478,
647
+ "es|unsure": 360,
648
+ "fr|anger": 16731,
649
+ "fr|calm": 11048,
650
+ "fr|joy": 11580,
651
+ "fr|neutral": 60,
652
+ "fr|sad": 24,
653
+ "fr|sadness": 11145,
654
+ "it|anger": 18055,
655
+ "it|calm": 18476,
656
+ "it|friendly": 703,
657
+ "it|happy": 780,
658
+ "it|joy": 20885,
659
+ "it|neutral": 834,
660
+ "it|sad": 557,
661
+ "it|sadness": 19262,
662
+ "it|sarcastic": 717,
663
+ "it|unsure": 547,
664
+ "vi|anger": 9886,
665
+ "vi|angry": 23,
666
+ "vi|calm": 10188,
667
+ "vi|happy": 52,
668
+ "vi|joy": 10034,
669
+ "vi|neutral": 29,
670
+ "vi|sad": 45,
671
+ "vi|sadness": 10286
672
+ },
673
+ "by_split": {
674
+ "test": 14063,
675
+ "train": 396062,
676
+ "val": 9288
677
+ }
678
+ },
679
+ {
680
+ "id": "scylla",
681
+ "index": 7,
682
+ "samples": 398205,
683
+ "duration_seconds": 1555860.8998749473,
684
+ "by_language": {
685
+ "de": 53087,
686
+ "en_us": 103539,
687
+ "es": 76482,
688
+ "fr": 52805,
689
+ "it": 76713,
690
+ "vi": 35579
691
+ },
692
+ "by_emotion": {
693
+ "anger": 97926,
694
+ "angry": 2932,
695
+ "calm": 75811,
696
+ "excited": 2689,
697
+ "friendly": 2544,
698
+ "frustrated": 2193,
699
+ "happy": 2670,
700
+ "joy": 99116,
701
+ "neutral": 4452,
702
+ "sad": 2326,
703
+ "sadness": 101403,
704
+ "sarcastic": 2243,
705
+ "unsure": 1900
706
+ },
707
+ "by_language_emotion": {
708
+ "de|anger": 15430,
709
+ "de|angry": 47,
710
+ "de|calm": 9641,
711
+ "de|happy": 39,
712
+ "de|joy": 11987,
713
+ "de|neutral": 47,
714
+ "de|sad": 26,
715
+ "de|sadness": 15870,
716
+ "en_us|anger": 24960,
717
+ "en_us|angry": 1520,
718
+ "en_us|calm": 14722,
719
+ "en_us|excited": 1380,
720
+ "en_us|friendly": 1294,
721
+ "en_us|frustrated": 1294,
722
+ "en_us|happy": 1349,
723
+ "en_us|joy": 25405,
724
+ "en_us|neutral": 2892,
725
+ "en_us|sad": 1329,
726
+ "en_us|sadness": 25239,
727
+ "en_us|sarcastic": 1161,
728
+ "en_us|unsure": 994,
729
+ "es|anger": 18884,
730
+ "es|angry": 490,
731
+ "es|calm": 14299,
732
+ "es|excited": 581,
733
+ "es|friendly": 545,
734
+ "es|frustrated": 364,
735
+ "es|happy": 523,
736
+ "es|joy": 21153,
737
+ "es|neutral": 605,
738
+ "es|sad": 438,
739
+ "es|sadness": 17745,
740
+ "es|sarcastic": 501,
741
+ "es|unsure": 354,
742
+ "fr|anger": 12966,
743
+ "fr|angry": 66,
744
+ "fr|calm": 10733,
745
+ "fr|happy": 23,
746
+ "fr|joy": 13662,
747
+ "fr|neutral": 57,
748
+ "fr|sad": 20,
749
+ "fr|sadness": 15278,
750
+ "it|anger": 17442,
751
+ "it|angry": 762,
752
+ "it|calm": 17654,
753
+ "it|excited": 728,
754
+ "it|friendly": 705,
755
+ "it|frustrated": 535,
756
+ "it|happy": 712,
757
+ "it|joy": 17835,
758
+ "it|neutral": 808,
759
+ "it|sad": 491,
760
+ "it|sadness": 17908,
761
+ "it|sarcastic": 581,
762
+ "it|unsure": 552,
763
+ "vi|anger": 8244,
764
+ "vi|angry": 47,
765
+ "vi|calm": 8762,
766
+ "vi|happy": 24,
767
+ "vi|joy": 9074,
768
+ "vi|neutral": 43,
769
+ "vi|sad": 22,
770
+ "vi|sadness": 9363
771
+ },
772
+ "by_split": {
773
+ "train": 381435,
774
+ "val": 16770
775
+ }
776
+ },
777
+ {
778
+ "id": "stone",
779
+ "index": 8,
780
+ "samples": 339121,
781
+ "duration_seconds": 1293407.0055833745,
782
+ "by_language": {
783
+ "de": 50557,
784
+ "en_us": 73131,
785
+ "es": 64388,
786
+ "fr": 45578,
787
+ "it": 72060,
788
+ "vi": 33407
789
+ },
790
+ "by_emotion": {
791
+ "anger": 84975,
792
+ "angry": 2485,
793
+ "calm": 74298,
794
+ "excited": 3284,
795
+ "friendly": 2388,
796
+ "frustrated": 1806,
797
+ "happy": 2312,
798
+ "joy": 74390,
799
+ "neutral": 2848,
800
+ "sad": 1952,
801
+ "sadness": 84431,
802
+ "sarcastic": 2147,
803
+ "unsure": 1805
804
+ },
805
+ "by_language_emotion": {
806
+ "de|anger": 14909,
807
+ "de|angry": 27,
808
+ "de|calm": 9922,
809
+ "de|happy": 44,
810
+ "de|joy": 11813,
811
+ "de|neutral": 28,
812
+ "de|sad": 52,
813
+ "de|sadness": 13762,
814
+ "en_us|anger": 17297,
815
+ "en_us|angry": 1232,
816
+ "en_us|calm": 12722,
817
+ "en_us|excited": 2080,
818
+ "en_us|friendly": 1333,
819
+ "en_us|frustrated": 1064,
820
+ "en_us|happy": 1238,
821
+ "en_us|joy": 14055,
822
+ "en_us|neutral": 1352,
823
+ "en_us|sad": 1078,
824
+ "en_us|sadness": 17664,
825
+ "en_us|sarcastic": 1056,
826
+ "en_us|unsure": 960,
827
+ "es|anger": 15474,
828
+ "es|angry": 429,
829
+ "es|calm": 15760,
830
+ "es|excited": 502,
831
+ "es|friendly": 486,
832
+ "es|frustrated": 262,
833
+ "es|happy": 453,
834
+ "es|joy": 14345,
835
+ "es|neutral": 607,
836
+ "es|sad": 365,
837
+ "es|sadness": 14923,
838
+ "es|sarcastic": 444,
839
+ "es|unsure": 338,
840
+ "fr|anger": 12668,
841
+ "fr|angry": 36,
842
+ "fr|calm": 10122,
843
+ "fr|happy": 44,
844
+ "fr|joy": 9556,
845
+ "fr|neutral": 25,
846
+ "fr|sad": 44,
847
+ "fr|sadness": 13083,
848
+ "it|anger": 16507,
849
+ "it|angry": 715,
850
+ "it|calm": 17167,
851
+ "it|excited": 702,
852
+ "it|friendly": 569,
853
+ "it|frustrated": 480,
854
+ "it|happy": 512,
855
+ "it|joy": 16477,
856
+ "it|neutral": 789,
857
+ "it|sad": 396,
858
+ "it|sadness": 16592,
859
+ "it|sarcastic": 647,
860
+ "it|unsure": 507,
861
+ "vi|anger": 8120,
862
+ "vi|angry": 46,
863
+ "vi|calm": 8605,
864
+ "vi|happy": 21,
865
+ "vi|joy": 8144,
866
+ "vi|neutral": 47,
867
+ "vi|sad": 17,
868
+ "vi|sadness": 8407
869
+ },
870
+ "by_split": {
871
+ "test": 7024,
872
+ "train": 332097
873
+ }
874
+ },
875
+ {
876
+ "id": "tuesday",
877
+ "index": 9,
878
+ "samples": 428984,
879
+ "duration_seconds": 1710029.623916695,
880
+ "by_language": {
881
+ "de": 58970,
882
+ "en_gb": 122831,
883
+ "es": 74790,
884
+ "fr": 55799,
885
+ "it": 80770,
886
+ "vi": 35824
887
+ },
888
+ "by_emotion": {
889
+ "anger": 106860,
890
+ "angry": 3120,
891
+ "calm": 88174,
892
+ "excited": 2828,
893
+ "friendly": 2427,
894
+ "frustrated": 2509,
895
+ "happy": 2455,
896
+ "joy": 102840,
897
+ "neutral": 4858,
898
+ "sad": 2510,
899
+ "sadness": 105620,
900
+ "sarcastic": 2705,
901
+ "unsure": 2078
902
+ },
903
+ "by_language_emotion": {
904
+ "de|anger": 16542,
905
+ "de|angry": 25,
906
+ "de|calm": 12393,
907
+ "de|happy": 70,
908
+ "de|joy": 14922,
909
+ "de|neutral": 30,
910
+ "de|sad": 68,
911
+ "de|sadness": 14920,
912
+ "en_gb|anger": 32142,
913
+ "en_gb|angry": 1757,
914
+ "en_gb|calm": 16925,
915
+ "en_gb|excited": 1486,
916
+ "en_gb|friendly": 1664,
917
+ "en_gb|frustrated": 1480,
918
+ "en_gb|happy": 1590,
919
+ "en_gb|joy": 27885,
920
+ "en_gb|neutral": 3199,
921
+ "en_gb|sad": 1445,
922
+ "en_gb|sadness": 30776,
923
+ "en_gb|sarcastic": 1339,
924
+ "en_gb|unsure": 1143,
925
+ "es|anger": 17613,
926
+ "es|angry": 476,
927
+ "es|calm": 18399,
928
+ "es|excited": 560,
929
+ "es|frustrated": 366,
930
+ "es|joy": 18259,
931
+ "es|neutral": 728,
932
+ "es|sad": 408,
933
+ "es|sadness": 17084,
934
+ "es|sarcastic": 525,
935
+ "es|unsure": 372,
936
+ "fr|anger": 13489,
937
+ "fr|angry": 30,
938
+ "fr|calm": 12209,
939
+ "fr|happy": 44,
940
+ "fr|joy": 14277,
941
+ "fr|neutral": 30,
942
+ "fr|sad": 59,
943
+ "fr|sadness": 15661,
944
+ "it|anger": 18298,
945
+ "it|angry": 810,
946
+ "it|calm": 18942,
947
+ "it|excited": 782,
948
+ "it|friendly": 763,
949
+ "it|frustrated": 663,
950
+ "it|happy": 700,
951
+ "it|joy": 18549,
952
+ "it|neutral": 846,
953
+ "it|sad": 489,
954
+ "it|sadness": 18524,
955
+ "it|sarcastic": 841,
956
+ "it|unsure": 563,
957
+ "vi|anger": 8776,
958
+ "vi|angry": 22,
959
+ "vi|calm": 9306,
960
+ "vi|happy": 51,
961
+ "vi|joy": 8948,
962
+ "vi|neutral": 25,
963
+ "vi|sad": 41,
964
+ "vi|sadness": 8655
965
+ },
966
+ "by_split": {
967
+ "test": 190,
968
+ "train": 421485,
969
+ "val": 7309
970
+ }
971
+ }
972
+ ]
onnx-int8/manifest.json ADDED
@@ -0,0 +1,950 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "scyllasband-duration-flow",
3
+ "assets": {
4
+ "emotion_index": "assets/emotions.json",
5
+ "g2p_config": "assets/g2p/export_config.json",
6
+ "g2p_language_map": "assets/g2p/language_map.json",
7
+ "g2p_normalization": "assets/g2p/normalization.json",
8
+ "g2p_phoneme_dict": "assets/g2p/phoneme_dict.json",
9
+ "g2p_pronunciation_overrides": "assets/g2p/pronunciation_overrides.json",
10
+ "g2p_tokenizer": "assets/g2p/tokenizer.json",
11
+ "language_index": "assets/languages.json",
12
+ "phone_vocab": "assets/phone_vocab.json",
13
+ "voice_index": "assets/voices.json",
14
+ "voice_pack_manifest": "assets/voice_packs/reference_packs.json",
15
+ "voice_packs": "assets/voice_packs"
16
+ },
17
+ "audio": {
18
+ "hop_length": 256,
19
+ "latent_dim": 24,
20
+ "latent_hop_length": 512,
21
+ "n_mels": 100,
22
+ "sample_rate": 24000
23
+ },
24
+ "components": {
25
+ "duration_predictor": {
26
+ "artifacts": {
27
+ "onnx": {
28
+ "format": "onnx",
29
+ "path": "onnx/components/duration_predictor.onnx"
30
+ }
31
+ },
32
+ "inputs": [
33
+ "phone_ids",
34
+ "voice_id",
35
+ "language_id",
36
+ "affect_values",
37
+ "boundary_before_id",
38
+ "boundary_after_id",
39
+ "phone_mask",
40
+ "affect_condition_mask",
41
+ "identity_reference",
42
+ "identity_reference_mask",
43
+ "prosody_baseline",
44
+ "prosody_delta",
45
+ "prosody_feature_mask",
46
+ "prosody_confidence"
47
+ ],
48
+ "outputs": [
49
+ "durations"
50
+ ],
51
+ "required": true
52
+ },
53
+ "g2p": {
54
+ "artifacts": {
55
+ "onnx": {
56
+ "format": "onnx",
57
+ "path": "onnx/g2p/model.onnx"
58
+ }
59
+ },
60
+ "inputs": [
61
+ "text"
62
+ ],
63
+ "outputs": [
64
+ "logits"
65
+ ],
66
+ "required": true
67
+ },
68
+ "vector_context_encoder": {
69
+ "artifacts": {
70
+ "onnx": {
71
+ "format": "onnx",
72
+ "path": "onnx/components/vector_context_encoder.onnx"
73
+ }
74
+ },
75
+ "inputs": [
76
+ "span_context_phone_ids",
77
+ "span_context_segment_ids",
78
+ "span_context_mask"
79
+ ],
80
+ "outputs": [
81
+ "span_context_hidden"
82
+ ],
83
+ "required": true
84
+ },
85
+ "vector_estimator": {
86
+ "artifacts": {
87
+ "onnx": {
88
+ "format": "onnx",
89
+ "path": "onnx/components/vector_estimator_b640.onnx"
90
+ }
91
+ },
92
+ "inputs": [
93
+ "noise",
94
+ "time",
95
+ "expanded_phone_ids",
96
+ "voice_id",
97
+ "language_id",
98
+ "affect_values",
99
+ "boundary_before_id",
100
+ "boundary_after_id",
101
+ "latent_mask",
102
+ "affect_condition_mask",
103
+ "identity_reference",
104
+ "identity_reference_mask",
105
+ "prosody_baseline",
106
+ "prosody_delta",
107
+ "prosody_feature_mask",
108
+ "prosody_confidence",
109
+ "prefix_latents",
110
+ "prefix_mask",
111
+ "span_context_hidden"
112
+ ],
113
+ "outputs": [
114
+ "velocity"
115
+ ],
116
+ "required": true
117
+ },
118
+ "vector_estimator_256": {
119
+ "artifacts": {
120
+ "onnx": {
121
+ "format": "onnx",
122
+ "path": "onnx/components/vector_estimator_b256.onnx"
123
+ }
124
+ },
125
+ "inputs": [
126
+ "noise",
127
+ "time",
128
+ "expanded_phone_ids",
129
+ "voice_id",
130
+ "language_id",
131
+ "affect_values",
132
+ "boundary_before_id",
133
+ "boundary_after_id",
134
+ "latent_mask",
135
+ "affect_condition_mask",
136
+ "identity_reference",
137
+ "identity_reference_mask",
138
+ "prosody_baseline",
139
+ "prosody_delta",
140
+ "prosody_feature_mask",
141
+ "prosody_confidence",
142
+ "prefix_latents",
143
+ "prefix_mask",
144
+ "span_context_hidden"
145
+ ],
146
+ "outputs": [
147
+ "velocity"
148
+ ],
149
+ "required": false
150
+ },
151
+ "vector_estimator_384": {
152
+ "artifacts": {
153
+ "onnx": {
154
+ "format": "onnx",
155
+ "path": "onnx/components/vector_estimator_b384.onnx"
156
+ }
157
+ },
158
+ "inputs": [
159
+ "noise",
160
+ "time",
161
+ "expanded_phone_ids",
162
+ "voice_id",
163
+ "language_id",
164
+ "affect_values",
165
+ "boundary_before_id",
166
+ "boundary_after_id",
167
+ "latent_mask",
168
+ "affect_condition_mask",
169
+ "identity_reference",
170
+ "identity_reference_mask",
171
+ "prosody_baseline",
172
+ "prosody_delta",
173
+ "prosody_feature_mask",
174
+ "prosody_confidence",
175
+ "prefix_latents",
176
+ "prefix_mask",
177
+ "span_context_hidden"
178
+ ],
179
+ "outputs": [
180
+ "velocity"
181
+ ],
182
+ "required": false
183
+ },
184
+ "vector_estimator_512": {
185
+ "artifacts": {
186
+ "onnx": {
187
+ "format": "onnx",
188
+ "path": "onnx/components/vector_estimator_b512.onnx"
189
+ }
190
+ },
191
+ "inputs": [
192
+ "noise",
193
+ "time",
194
+ "expanded_phone_ids",
195
+ "voice_id",
196
+ "language_id",
197
+ "affect_values",
198
+ "boundary_before_id",
199
+ "boundary_after_id",
200
+ "latent_mask",
201
+ "affect_condition_mask",
202
+ "identity_reference",
203
+ "identity_reference_mask",
204
+ "prosody_baseline",
205
+ "prosody_delta",
206
+ "prosody_feature_mask",
207
+ "prosody_confidence",
208
+ "prefix_latents",
209
+ "prefix_mask",
210
+ "span_context_hidden"
211
+ ],
212
+ "outputs": [
213
+ "velocity"
214
+ ],
215
+ "required": false
216
+ },
217
+ "vocoder": {
218
+ "artifacts": {
219
+ "onnx": {
220
+ "format": "onnx",
221
+ "path": "onnx/components/vocoder_b640.onnx"
222
+ }
223
+ },
224
+ "inputs": [
225
+ "latents",
226
+ "latent_mask",
227
+ "voice_id",
228
+ "language_id",
229
+ "emotion_id"
230
+ ],
231
+ "outputs": [
232
+ "audio"
233
+ ],
234
+ "required": true
235
+ },
236
+ "vocoder_256": {
237
+ "artifacts": {
238
+ "onnx": {
239
+ "format": "onnx",
240
+ "path": "onnx/components/vocoder_b256.onnx"
241
+ }
242
+ },
243
+ "inputs": [
244
+ "latents",
245
+ "latent_mask",
246
+ "voice_id",
247
+ "language_id",
248
+ "emotion_id"
249
+ ],
250
+ "outputs": [
251
+ "audio"
252
+ ],
253
+ "required": false
254
+ },
255
+ "vocoder_384": {
256
+ "artifacts": {
257
+ "onnx": {
258
+ "format": "onnx",
259
+ "path": "onnx/components/vocoder_b384.onnx"
260
+ }
261
+ },
262
+ "inputs": [
263
+ "latents",
264
+ "latent_mask",
265
+ "voice_id",
266
+ "language_id",
267
+ "emotion_id"
268
+ ],
269
+ "outputs": [
270
+ "audio"
271
+ ],
272
+ "required": false
273
+ },
274
+ "vocoder_512": {
275
+ "artifacts": {
276
+ "onnx": {
277
+ "format": "onnx",
278
+ "path": "onnx/components/vocoder_b512.onnx"
279
+ }
280
+ },
281
+ "inputs": [
282
+ "latents",
283
+ "latent_mask",
284
+ "voice_id",
285
+ "language_id",
286
+ "emotion_id"
287
+ ],
288
+ "outputs": [
289
+ "audio"
290
+ ],
291
+ "required": false
292
+ },
293
+ "vocoder_adapter": {
294
+ "artifacts": {
295
+ "onnx": {
296
+ "format": "onnx",
297
+ "path": "onnx/components/vocoder_adapter_b640.onnx"
298
+ }
299
+ },
300
+ "inputs": [
301
+ "latents",
302
+ "latent_mask",
303
+ "voice_id",
304
+ "language_id",
305
+ "emotion_id"
306
+ ],
307
+ "outputs": [
308
+ "vocos_features"
309
+ ],
310
+ "required": false
311
+ },
312
+ "vocoder_adapter_256": {
313
+ "artifacts": {
314
+ "onnx": {
315
+ "format": "onnx",
316
+ "path": "onnx/components/vocoder_adapter_b256.onnx"
317
+ }
318
+ },
319
+ "inputs": [
320
+ "latents",
321
+ "latent_mask",
322
+ "voice_id",
323
+ "language_id",
324
+ "emotion_id"
325
+ ],
326
+ "outputs": [
327
+ "vocos_features"
328
+ ],
329
+ "required": false
330
+ },
331
+ "vocoder_adapter_384": {
332
+ "artifacts": {
333
+ "onnx": {
334
+ "format": "onnx",
335
+ "path": "onnx/components/vocoder_adapter_b384.onnx"
336
+ }
337
+ },
338
+ "inputs": [
339
+ "latents",
340
+ "latent_mask",
341
+ "voice_id",
342
+ "language_id",
343
+ "emotion_id"
344
+ ],
345
+ "outputs": [
346
+ "vocos_features"
347
+ ],
348
+ "required": false
349
+ },
350
+ "vocoder_adapter_512": {
351
+ "artifacts": {
352
+ "onnx": {
353
+ "format": "onnx",
354
+ "path": "onnx/components/vocoder_adapter_b512.onnx"
355
+ }
356
+ },
357
+ "inputs": [
358
+ "latents",
359
+ "latent_mask",
360
+ "voice_id",
361
+ "language_id",
362
+ "emotion_id"
363
+ ],
364
+ "outputs": [
365
+ "vocos_features"
366
+ ],
367
+ "required": false
368
+ }
369
+ },
370
+ "contract_version": "1.0.0",
371
+ "controls": {
372
+ "affect": {
373
+ "all_zero_is_explicit": true,
374
+ "axes": [
375
+ "calm",
376
+ "joy",
377
+ "anger",
378
+ "sadness",
379
+ "whisper"
380
+ ],
381
+ "axis_maximums": {
382
+ "calm": 0.75
383
+ },
384
+ "axis_minimums": {
385
+ "calm": 0.25
386
+ },
387
+ "axis_order_version": 3,
388
+ "condition_mask_input": true,
389
+ "default_preset": "neutral",
390
+ "dimension": 5,
391
+ "enabled": true,
392
+ "guidance": {
393
+ "default_scale": 1.0,
394
+ "enabled": true,
395
+ "host_linear_combination": true,
396
+ "identity_reference_retained": true,
397
+ "minimum_scale": 0.0,
398
+ "null_condition_mask": 0.0
399
+ },
400
+ "legacy_presets": {
401
+ "angry": [
402
+ 0.25,
403
+ 0.0,
404
+ 0.75,
405
+ 0.0,
406
+ 0.0
407
+ ],
408
+ "excited": [
409
+ 0.25,
410
+ 1.0,
411
+ 0.25,
412
+ 0.0,
413
+ 0.0
414
+ ],
415
+ "friendly": [
416
+ 0.5,
417
+ 0.5,
418
+ 0.0,
419
+ 0.0,
420
+ 0.0
421
+ ],
422
+ "frustrated": [
423
+ 0.25,
424
+ 0.0,
425
+ 0.5,
426
+ 0.25,
427
+ 0.0
428
+ ],
429
+ "happy": [
430
+ 0.25,
431
+ 0.75,
432
+ 0.0,
433
+ 0.0,
434
+ 0.0
435
+ ],
436
+ "neutral": [
437
+ 0.5,
438
+ 0.25,
439
+ 0.0,
440
+ 0.0,
441
+ 0.0
442
+ ],
443
+ "sad": [
444
+ 0.25,
445
+ 0.0,
446
+ 0.0,
447
+ 0.75,
448
+ 0.0
449
+ ],
450
+ "whisper": [
451
+ 0.25,
452
+ 0.0,
453
+ 0.0,
454
+ 0.0,
455
+ 1.0
456
+ ]
457
+ },
458
+ "partial_defaults": {
459
+ "anger": 0.0,
460
+ "calm": 0.5,
461
+ "joy": 0.0,
462
+ "sadness": 0.0,
463
+ "whisper": 0.0
464
+ },
465
+ "preset_version": 3,
466
+ "presets": {
467
+ "anger": [
468
+ 0.25,
469
+ 0.0,
470
+ 0.75,
471
+ 0.0,
472
+ 0.0
473
+ ],
474
+ "calm": [
475
+ 0.5,
476
+ 0.0,
477
+ 0.0,
478
+ 0.0,
479
+ 0.0
480
+ ],
481
+ "joy": [
482
+ 0.25,
483
+ 0.75,
484
+ 0.0,
485
+ 0.0,
486
+ 0.0
487
+ ],
488
+ "neutral": [
489
+ 0.5,
490
+ 0.25,
491
+ 0.0,
492
+ 0.0,
493
+ 0.0
494
+ ],
495
+ "sadness": [
496
+ 0.25,
497
+ 0.0,
498
+ 0.0,
499
+ 0.75,
500
+ 0.0
501
+ ],
502
+ "whisper": [
503
+ 0.25,
504
+ 0.0,
505
+ 0.0,
506
+ 0.0,
507
+ 1.0
508
+ ]
509
+ },
510
+ "range": [
511
+ 0.0,
512
+ 1.0
513
+ ],
514
+ "value_semantics": "independent_continuous_intensities_no_simplex_v1"
515
+ },
516
+ "chunk_context": {
517
+ "artificial_continuation_boundaries": [
518
+ "chunk_continue"
519
+ ],
520
+ "artificial_continuation_phone": null,
521
+ "boundary_after_values": [
522
+ "sentence_end",
523
+ "paragraph_end",
524
+ "clause_continue",
525
+ "chunk_continue"
526
+ ],
527
+ "boundary_before_values": [
528
+ "sentence_start",
529
+ "paragraph_start",
530
+ "clause_continue",
531
+ "chunk_continue"
532
+ ],
533
+ "clause_continuation_fallback_phone": "<pause_comma>",
534
+ "conditioning": "boundary_embeddings",
535
+ "context_phone_tokens": {
536
+ "continuation": "<ctx_continuation>",
537
+ "sentence_end": "<ctx_sentence_end>",
538
+ "sentence_start": "<ctx_sentence_start>"
539
+ },
540
+ "default_boundary_after": "sentence_end",
541
+ "default_boundary_before": "sentence_start",
542
+ "emit_context_phone_tokens": false,
543
+ "linguistic_continuation_boundaries": [
544
+ "clause_continue"
545
+ ],
546
+ "schema_version": 2
547
+ },
548
+ "emotion_guidance": {
549
+ "emotion_condition_mask_input": true,
550
+ "enabled": false,
551
+ "reference_condition_mask_input": true,
552
+ "strength_mixing": "runtime_linear_combination"
553
+ },
554
+ "emotions": {
555
+ "asset": "assets/emotions.json",
556
+ "count": 13,
557
+ "enabled": false
558
+ },
559
+ "energy": {
560
+ "default": 1.0,
561
+ "max": 1.5,
562
+ "min": 0.5
563
+ },
564
+ "fixed_shapes": {
565
+ "g2p_text_tokens": 512,
566
+ "latent_frames": 640,
567
+ "phone_frames": 512
568
+ },
569
+ "graph_input_contract": "scyllasband_affect_v3",
570
+ "onnx": {
571
+ "dynamic_vector_batch": true,
572
+ "dynamic_vector_batch_max": 4,
573
+ "external_data": true,
574
+ "opset": 18,
575
+ "providers_validated": [
576
+ "CPUExecutionProvider"
577
+ ],
578
+ "quantization": {
579
+ "activation_type": "float32",
580
+ "format": "onnx_dynamic_int8",
581
+ "g2p": true,
582
+ "g2p_sha256": "514a30da9ca4e78124c2726d81c56e7fe604aa9886f151387ff55a200589d3f5",
583
+ "g2p_source": "promoted_prequantized",
584
+ "op_types": [
585
+ "MatMul",
586
+ "Gemm"
587
+ ],
588
+ "per_channel": true,
589
+ "preserved_fp32_components": [
590
+ "duration_predictor",
591
+ "vector_context_encoder",
592
+ "vocoder_adapter",
593
+ "vocoder"
594
+ ],
595
+ "source_manifest_sha256": "bae35950bdcd330ca027dcbe291a5d26e0fa8e7a8cff3352594378a567060079",
596
+ "status": "candidate",
597
+ "vector_components": [
598
+ "onnx/components/vector_estimator_b256.onnx",
599
+ "onnx/components/vector_estimator_b384.onnx",
600
+ "onnx/components/vector_estimator_b512.onnx",
601
+ "onnx/components/vector_estimator_b640.onnx"
602
+ ],
603
+ "vector_profile": "transformer_core",
604
+ "weight_type": "QInt8"
605
+ },
606
+ "shared_initializer_map": "onnx/components/shared_weights.json",
607
+ "shared_weights": "onnx/components/shared_weights.bin",
608
+ "shared_weights_bytes": 260751424,
609
+ "unique_tensor_count": 403
610
+ },
611
+ "pitch": {
612
+ "default": 0.0,
613
+ "max": 4.0,
614
+ "min": -4.0
615
+ },
616
+ "prefix_conditioning": {
617
+ "component": "vector_estimator",
618
+ "enabled": true,
619
+ "inputs": [
620
+ "prefix_latents",
621
+ "prefix_mask"
622
+ ],
623
+ "max_frames": 24
624
+ },
625
+ "punctuation_silence": {
626
+ "calibrated_floors": false,
627
+ "floor_table_ms": {},
628
+ "silence_phone": "<sil>",
629
+ "target": "explicit_silence"
630
+ },
631
+ "reference_packs": {
632
+ "affect_routing": {
633
+ "enabled": true,
634
+ "mixed_axis_policy": "human_affect_is_semantic_authority",
635
+ "source": "human_affect_plus_measured_prosody",
636
+ "version": "native_exact_primary_relative_residual_v4"
637
+ },
638
+ "asset_dir": "assets/voice_packs",
639
+ "conditioning": {
640
+ "duration_predictor": "additive",
641
+ "vector_estimator": "film",
642
+ "vocoder": "off"
643
+ },
644
+ "enabled": true,
645
+ "fallback_weight": 0.25,
646
+ "identity_dim": 512,
647
+ "learned_style_embedding": false,
648
+ "manifest": "assets/voice_packs/reference_packs.json",
649
+ "model_contract": "identity_plus_measured_relative_prosody_v4",
650
+ "normalization": "frozen_global_median_iqr_from_pack_index",
651
+ "prosody_baseline_dim": 32,
652
+ "prosody_confidence_input": true,
653
+ "prosody_delta_dim": 32,
654
+ "prosody_dim": 32,
655
+ "prosody_feature_mask_input": true,
656
+ "schema_version": 4,
657
+ "style_dim": 0
658
+ },
659
+ "sampler": {
660
+ "choices": [
661
+ "euler",
662
+ "heun"
663
+ ],
664
+ "default": "euler"
665
+ },
666
+ "span_conditioning": {
667
+ "context_max_phones": 768,
668
+ "enabled": true,
669
+ "encoder_component": "vector_context_encoder",
670
+ "encoder_inputs": [
671
+ "span_context_phone_ids",
672
+ "span_context_segment_ids",
673
+ "span_context_mask"
674
+ ],
675
+ "hidden_size": 512,
676
+ "segments": 3,
677
+ "solver_input": "span_context_hidden"
678
+ },
679
+ "speed": {
680
+ "default": 1.0,
681
+ "max": 1.25,
682
+ "min": 0.75
683
+ },
684
+ "steps": {
685
+ "default": 8,
686
+ "max": 64,
687
+ "min": 1
688
+ },
689
+ "target_buckets": {
690
+ "bucket_margin_frames": 0,
691
+ "buckets": [
692
+ {
693
+ "default": false,
694
+ "latent_frames": 256,
695
+ "vector_estimator": "vector_estimator_256",
696
+ "vector_estimator_prefix": "vector_estimator_prefix_256",
697
+ "vector_estimator_tail": "vector_estimator_tail_256",
698
+ "vocoder": "vocoder_256"
699
+ },
700
+ {
701
+ "default": false,
702
+ "latent_frames": 384,
703
+ "vector_estimator": "vector_estimator_384",
704
+ "vector_estimator_prefix": "vector_estimator_prefix_384",
705
+ "vector_estimator_tail": "vector_estimator_tail_384",
706
+ "vocoder": "vocoder_384"
707
+ },
708
+ {
709
+ "default": false,
710
+ "latent_frames": 512,
711
+ "vector_estimator": "vector_estimator_512",
712
+ "vector_estimator_prefix": "vector_estimator_prefix_512",
713
+ "vector_estimator_tail": "vector_estimator_tail_512",
714
+ "vocoder": "vocoder_512"
715
+ },
716
+ {
717
+ "default": true,
718
+ "latent_frames": 640,
719
+ "vector_estimator": "vector_estimator",
720
+ "vector_estimator_prefix": "vector_estimator_prefix",
721
+ "vector_estimator_tail": "vector_estimator_tail",
722
+ "vocoder": "vocoder"
723
+ }
724
+ ],
725
+ "default_latent_frames": 640,
726
+ "enabled": true,
727
+ "policy": "smallest_fit"
728
+ },
729
+ "text_normalizer": {
730
+ "prepared_contract_recorded": true,
731
+ "sha256": "d8fd1b2415d0d100d1c70237a4469117ee6b73d0e4da703e4654c83192779cc4",
732
+ "version": "scyllasband_spoken_text_v2_2026_08_05"
733
+ }
734
+ },
735
+ "dataset_summary": {
736
+ "duration_hours": 2642.6550362963917,
737
+ "input_dir": "output/emotional_multilingual_v3",
738
+ "languages": {
739
+ "de": 281316,
740
+ "en_gb": 133173,
741
+ "en_us": 309827,
742
+ "es": 267424,
743
+ "fr": 276128,
744
+ "it": 271161,
745
+ "vi": 249577
746
+ },
747
+ "max_duration_seconds": 24.686625,
748
+ "min_duration_seconds": 0.754125,
749
+ "samples": 1788606,
750
+ "voices": 10
751
+ },
752
+ "default_language": "en_us",
753
+ "export_status": "complete_onnx",
754
+ "languages": [
755
+ "en_us",
756
+ "en_gb",
757
+ "es",
758
+ "it",
759
+ "fr",
760
+ "de",
761
+ "vi"
762
+ ],
763
+ "model_name": "scyllasband",
764
+ "model_version": "2",
765
+ "preferred_backends": [
766
+ "onnx"
767
+ ],
768
+ "voices": [
769
+ {
770
+ "default_language": "en_us",
771
+ "embedding_path": "assets/voice_packs/ariadne.npz",
772
+ "id": "ariadne",
773
+ "languages": [
774
+ "en_us",
775
+ "en_gb",
776
+ "es",
777
+ "it",
778
+ "fr",
779
+ "de",
780
+ "vi"
781
+ ],
782
+ "name": "ariadne",
783
+ "styles": [
784
+ "default"
785
+ ]
786
+ },
787
+ {
788
+ "default_language": "en_us",
789
+ "embedding_path": "assets/voice_packs/felix.npz",
790
+ "id": "felix",
791
+ "languages": [
792
+ "en_us",
793
+ "en_gb",
794
+ "es",
795
+ "it",
796
+ "fr",
797
+ "de",
798
+ "vi"
799
+ ],
800
+ "name": "felix",
801
+ "styles": [
802
+ "default"
803
+ ]
804
+ },
805
+ {
806
+ "default_language": "en_us",
807
+ "embedding_path": "assets/voice_packs/gwen.npz",
808
+ "id": "gwen",
809
+ "languages": [
810
+ "en_us",
811
+ "en_gb",
812
+ "es",
813
+ "it",
814
+ "fr",
815
+ "de",
816
+ "vi"
817
+ ],
818
+ "name": "gwen",
819
+ "styles": [
820
+ "default"
821
+ ]
822
+ },
823
+ {
824
+ "default_language": "en_gb",
825
+ "embedding_path": "assets/voice_packs/ink.npz",
826
+ "id": "ink",
827
+ "languages": [
828
+ "en_gb",
829
+ "en_us",
830
+ "es",
831
+ "it",
832
+ "fr",
833
+ "de",
834
+ "vi"
835
+ ],
836
+ "name": "ink",
837
+ "styles": [
838
+ "default"
839
+ ]
840
+ },
841
+ {
842
+ "default_language": "en_us",
843
+ "embedding_path": "assets/voice_packs/max.npz",
844
+ "id": "max",
845
+ "languages": [
846
+ "en_us",
847
+ "en_gb",
848
+ "es",
849
+ "it",
850
+ "fr",
851
+ "de",
852
+ "vi"
853
+ ],
854
+ "name": "max",
855
+ "styles": [
856
+ "default"
857
+ ]
858
+ },
859
+ {
860
+ "default_language": "en_gb",
861
+ "embedding_path": "assets/voice_packs/orpheus.npz",
862
+ "id": "orpheus",
863
+ "languages": [
864
+ "en_gb",
865
+ "en_us",
866
+ "es",
867
+ "it",
868
+ "fr",
869
+ "de",
870
+ "vi"
871
+ ],
872
+ "name": "orpheus",
873
+ "styles": [
874
+ "default"
875
+ ]
876
+ },
877
+ {
878
+ "default_language": "en_us",
879
+ "embedding_path": "assets/voice_packs/rex.npz",
880
+ "id": "rex",
881
+ "languages": [
882
+ "en_us",
883
+ "en_gb",
884
+ "es",
885
+ "it",
886
+ "fr",
887
+ "de",
888
+ "vi"
889
+ ],
890
+ "name": "rex",
891
+ "styles": [
892
+ "default"
893
+ ]
894
+ },
895
+ {
896
+ "default_language": "en_us",
897
+ "embedding_path": "assets/voice_packs/scylla.npz",
898
+ "id": "scylla",
899
+ "languages": [
900
+ "en_us",
901
+ "en_gb",
902
+ "es",
903
+ "it",
904
+ "fr",
905
+ "de",
906
+ "vi"
907
+ ],
908
+ "name": "scylla",
909
+ "styles": [
910
+ "default"
911
+ ]
912
+ },
913
+ {
914
+ "default_language": "en_us",
915
+ "embedding_path": "assets/voice_packs/stone.npz",
916
+ "id": "stone",
917
+ "languages": [
918
+ "en_us",
919
+ "en_gb",
920
+ "es",
921
+ "it",
922
+ "fr",
923
+ "de",
924
+ "vi"
925
+ ],
926
+ "name": "stone",
927
+ "styles": [
928
+ "default"
929
+ ]
930
+ },
931
+ {
932
+ "default_language": "en_gb",
933
+ "embedding_path": "assets/voice_packs/tuesday.npz",
934
+ "id": "tuesday",
935
+ "languages": [
936
+ "en_gb",
937
+ "en_us",
938
+ "es",
939
+ "it",
940
+ "fr",
941
+ "de",
942
+ "vi"
943
+ ],
944
+ "name": "tuesday",
945
+ "styles": [
946
+ "default"
947
+ ]
948
+ }
949
+ ]
950
+ }
onnx-int8/onnx/components/duration_predictor.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36430acf05c297cdcfd8f0c7b0a5bad476a10d0f2b471daac0846f4e343c0c70
3
+ size 71971
onnx-int8/onnx/components/shared_weights.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723376d28a248cf14a6780058ef29cc3a808b19c9658b12e082a9a1b35a75646
3
+ size 260751424
onnx-int8/onnx/components/shared_weights.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx-int8/onnx/components/vector_context_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea197e0bc4176f30749b485daf0794fd6fbb62fa8f4e45c1e2b0ced96bf31d9
3
+ size 10417
onnx-int8/onnx/components/vector_estimator_b256.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a65c704fe72f7f4d31df37098a62c8e5ba7bb56c2b7dd624490a5ae1c606feb2
3
+ size 797695
onnx-int8/onnx/components/vector_estimator_b384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91dc96757a8e07d6006fe35b9f2ea850f9c07e540bcc654db7e146591a51ae7
3
+ size 1138687
onnx-int8/onnx/components/vector_estimator_b512.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609de784ed9f6c195bcb92857cf915b6d0ac79ac8c7550fbb2f175a30a2dae10
3
+ size 1610751
onnx-int8/onnx/components/vector_estimator_b640.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2d42e5cd92de52cbb06d1a0f31606a81a330556463da2531dcc8c138fe5ce3
3
+ size 2213888
onnx-int8/onnx/components/vocoder_adapter_b256.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3674908e6784a864763430682dd5411ac1bbd3d8a1d46a1a92ad1d3db19916a
3
+ size 67036
onnx-int8/onnx/components/vocoder_adapter_b384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a186adbf9bcea8362614047905e6b22681ebc206daa00637f790d1f034e7774
3
+ size 67036
onnx-int8/onnx/components/vocoder_adapter_b512.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9479a7f3d455fa662027d6046c6e6c4fbde8f1fe86a24d9b8a5ac6133f16dce
3
+ size 67036
onnx-int8/onnx/components/vocoder_adapter_b640.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610ca882aff6943f322400a9e52eb679fe8206c43aa996700f8fd92e253b9292
3
+ size 67036
onnx-int8/onnx/components/vocoder_b256.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353b4b8bd439dac46277f631facb291fc8eee314570e850aa6918fe3d3530130
3
+ size 122574
onnx-int8/onnx/components/vocoder_b384.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221d823cafc0f4e418865c99a8664e7bb795d119a9207e9cc58b0db981337477
3
+ size 122575
onnx-int8/onnx/components/vocoder_b512.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d494f66d069aa40bb74bf1bf16ca9432e935c8959da14d9e03281dc8f5f7213
3
+ size 122575
onnx-int8/onnx/components/vocoder_b640.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ffd1c735a03f383a5b08a2e43c75b41736efa569bc26764b86fb1c0401418a
3
+ size 122576
onnx-int8/onnx/g2p/export_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "scyllasband_g2p",
3
+ "source_checkpoint": "output/deepphonemizer_multilingual/model_v10_7lang/checkpoints/model_step_250k.pt",
4
+ "opset": 18,
5
+ "languages": [
6
+ "de",
7
+ "en_gb",
8
+ "en_us",
9
+ "es",
10
+ "fr",
11
+ "it",
12
+ "vi"
13
+ ],
14
+ "model_type": "transformer",
15
+ "input_granularity": "phrase",
16
+ "training_mix": "phrase_word_chunked_clean",
17
+ "phoneme_token_mode": "char",
18
+ "phrase_rows_per_language": 200000,
19
+ "word_rows_per_language": 200000,
20
+ "batch_dynamic": true,
21
+ "onnx_exporter": "dynamo",
22
+ "onnx_export_layout": "batch_first",
23
+ "onnx_padded_output": "ctc_blank",
24
+ "onnx_export_batch_size": 4,
25
+ "onnx_export_max_batch_size": 256,
26
+ "onnx_quantization": "dynamic_int8",
27
+ "onnx_fp32_model": "model.fp32.onnx",
28
+ "onnx_quantized_parity_tolerance": 3.0
29
+ }
onnx-int8/onnx/g2p/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514a30da9ca4e78124c2726d81c56e7fe604aa9886f151387ff55a200589d3f5
3
+ size 40564642
onnx-int8/onnx/g2p/phoneme_dict.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "de": {},
3
+ "en_gb": {},
4
+ "en_us": {},
5
+ "es": {},
6
+ "fr": {},
7
+ "it": {},
8
+ "vi": {}
9
+ }
onnx-int8/onnx/g2p/tokenizer.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "deepphonemizer_forward_ctc",
3
+ "languages": [
4
+ "de",
5
+ "en_gb",
6
+ "en_us",
7
+ "es",
8
+ "fr",
9
+ "it",
10
+ "vi"
11
+ ],
12
+ "char_repeats": 4,
13
+ "lowercase": true,
14
+ "phoneme_token_mode": "char",
15
+ "text_symbols": {
16
+ "_": 0,
17
+ "<de>": 1,
18
+ "<en_gb>": 2,
19
+ "<en_us>": 3,
20
+ "<es>": 4,
21
+ "<fr>": 5,
22
+ "<it>": 6,
23
+ "<vi>": 7,
24
+ "<end>": 8,
25
+ "\b": 9,
26
+ " ": 10,
27
+ "!": 11,
28
+ "\"": 12,
29
+ "#": 13,
30
+ "$": 14,
31
+ "%": 15,
32
+ "&": 16,
33
+ "'": 17,
34
+ "(": 18,
35
+ ")": 19,
36
+ "*": 20,
37
+ "+": 21,
38
+ ",": 22,
39
+ "-": 23,
40
+ ".": 24,
41
+ "/": 25,
42
+ "0": 26,
43
+ "1": 27,
44
+ "2": 28,
45
+ "3": 29,
46
+ "4": 30,
47
+ "5": 31,
48
+ "6": 32,
49
+ "7": 33,
50
+ "8": 34,
51
+ "9": 35,
52
+ ":": 36,
53
+ ";": 37,
54
+ "<": 38,
55
+ "=": 39,
56
+ ">": 40,
57
+ "?": 41,
58
+ "@": 42,
59
+ "A": 43,
60
+ "B": 44,
61
+ "C": 45,
62
+ "D": 46,
63
+ "E": 47,
64
+ "F": 48,
65
+ "G": 49,
66
+ "H": 50,
67
+ "I": 51,
68
+ "J": 52,
69
+ "K": 53,
70
+ "L": 54,
71
+ "M": 55,
72
+ "N": 56,
73
+ "O": 57,
74
+ "P": 58,
75
+ "Q": 59,
76
+ "R": 60,
77
+ "S": 61,
78
+ "T": 62,
79
+ "U": 63,
80
+ "V": 64,
81
+ "W": 65,
82
+ "X": 66,
83
+ "Y": 67,
84
+ "Z": 68,
85
+ "[": 69,
86
+ "\\": 70,
87
+ "]": 71,
88
+ "^": 72,
89
+ "`": 73,
90
+ "a": 74,
91
+ "b": 75,
92
+ "c": 76,
93
+ "d": 77,
94
+ "e": 78,
95
+ "f": 79,
96
+ "g": 80,
97
+ "h": 81,
98
+ "i": 82,
99
+ "j": 83,
100
+ "k": 84,
101
+ "l": 85,
102
+ "m": 86,
103
+ "n": 87,
104
+ "o": 88,
105
+ "p": 89,
106
+ "q": 90,
107
+ "r": 91,
108
+ "s": 92,
109
+ "t": 93,
110
+ "u": 94,
111
+ "v": 95,
112
+ "w": 96,
113
+ "x": 97,
114
+ "y": 98,
115
+ "z": 99,
116
+ "{": 100,
117
+ "|": 101,
118
+ "}": 102,
119
+ "~": 103,
120
+ "¡": 104,
121
+ "¢": 105,
122
+ "£": 106,
123
+ "¥": 107,
124
+ "§": 108,
125
+ "ª": 109,
126
+ "«": 110,
127
+ "­": 111,
128
+ "®": 112,
129
+ "°": 113,
130
+ "±": 114,
131
+ "²": 115,
132
+ "³": 116,
133
+ "´": 117,
134
+ "¶": 118,
135
+ "·": 119,
136
+ "¹": 120,
137
+ "º": 121,
138
+ "»": 122,
139
+ "¼": 123,
140
+ "½": 124,
141
+ "¾": 125,
142
+ "¿": 126,
143
+ "À": 127,
144
+ "Á": 128,
145
+ "Â": 129,
146
+ "Ä": 130,
147
+ "Å": 131,
148
+ "Æ": 132,
149
+ "Ç": 133,
150
+ "È": 134,
151
+ "É": 135,
152
+ "Ê": 136,
153
+ "Í": 137,
154
+ "Ï": 138,
155
+ "Ñ": 139,
156
+ "Ó": 140,
157
+ "Ô": 141,
158
+ "Ö": 142,
159
+ "×": 143,
160
+ "Ù": 144,
161
+ "Ú": 145,
162
+ "Ü": 146,
163
+ "Ý": 147,
164
+ "Þ": 148,
165
+ "ß": 149,
166
+ "à": 150,
167
+ "á": 151,
168
+ "â": 152,
169
+ "ã": 153,
170
+ "ä": 154,
171
+ "å": 155,
172
+ "æ": 156,
173
+ "ç": 157,
174
+ "è": 158,
175
+ "é": 159,
176
+ "ê": 160,
177
+ "ë": 161,
178
+ "ì": 162,
179
+ "í": 163,
180
+ "î": 164,
181
+ "ï": 165,
182
+ "ð": 166,
183
+ "ñ": 167,
184
+ "ò": 168,
185
+ "ó": 169,
186
+ "ô": 170,
187
+ "õ": 171,
188
+ "ö": 172,
189
+ "ø": 173,
190
+ "ù": 174,
191
+ "ú": 175,
192
+ "û": 176,
193
+ "ü": 177,
194
+ "ý": 178,
195
+ "þ": 179,
196
+ "ÿ": 180,
197
+ "ā": 181,
198
+ "Ă": 182,
199
+ "ă": 183,
200
+ "ą": 184,
201
+ "ć": 185,
202
+ "č": 186,
203
+ "Đ": 187,
204
+ "đ": 188,
205
+ "ē": 189,
206
+ "ė": 190,
207
+ "ę": 191,
208
+ "ğ": 192,
209
+ "ġ": 193,
210
+ "ĩ": 194,
211
+ "ī": 195,
212
+ "ļ": 196,
213
+ "ł": 197,
214
+ "ń": 198,
215
+ "Ō": 199,
216
+ "ō": 200,
217
+ "Œ": 201,
218
+ "œ": 202,
219
+ "ŕ": 203,
220
+ "ś": 204,
221
+ "ş": 205,
222
+ "š": 206,
223
+ "ŧ": 207,
224
+ "ũ": 208,
225
+ "ū": 209,
226
+ "ŭ": 210,
227
+ "ů": 211,
228
+ "ű": 212,
229
+ "ż": 213,
230
+ "Ž": 214,
231
+ "ž": 215,
232
+ "ſ": 216,
233
+ "Ơ": 217,
234
+ "ơ": 218,
235
+ "Ư": 219,
236
+ "ư": 220,
237
+ "ǁ": 221,
238
+ "ǂ": 222,
239
+ "ǐ": 223,
240
+ "ǘ": 224,
241
+ "ǧ": 225,
242
+ "ș": 226,
243
+ "Ȝ": 227,
244
+ "ȝ": 228,
245
+ "ȟ": 229,
246
+ "ɛ": 230,
247
+ "ʰ": 231,
248
+ "ˆ": 232,
249
+ "ˈ": 233,
250
+ "ˢ": 234,
251
+ "̃": 235,
252
+ "̍": 236,
253
+ "̣": 237,
254
+ "̱": 238,
255
+ "͈": 239,
256
+ "α": 240,
257
+ "β": 241,
258
+ "γ": 242,
259
+ "δ": 243,
260
+ "ε": 244,
261
+ "η": 245,
262
+ "κ": 246,
263
+ "μ": 247,
264
+ "ξ": 248,
265
+ "π": 249,
266
+ "ς": 250,
267
+ "σ": 251,
268
+ "χ": 252,
269
+ "ψ": 253,
270
+ "а": 254,
271
+ "д": 255,
272
+ "е": 256,
273
+ "з": 257,
274
+ "и": 258,
275
+ "к": 259,
276
+ "л": 260,
277
+ "о": 261,
278
+ "п": 262,
279
+ "р": 263,
280
+ "с": 264,
281
+ "т": 265,
282
+ "ч": 266,
283
+ "ь": 267,
284
+ "ง": 268,
285
+ "ย": 269,
286
+ "า": 270,
287
+ "่": 271,
288
+ "ည": 272,
289
+ "လ": 273,
290
+ "း": 274,
291
+ "်": 275,
292
+ "ᵈ": 276,
293
+ "ᵗ": 277,
294
+ "ḅ": 278,
295
+ "ḍ": 279,
296
+ "ḳ": 280,
297
+ "ṅ": 281,
298
+ "Ṭ": 282,
299
+ "ẓ": 283,
300
+ "ạ": 284,
301
+ "Ả": 285,
302
+ "ả": 286,
303
+ "Ấ": 287,
304
+ "ấ": 288,
305
+ "ầ": 289,
306
+ "ẩ": 290,
307
+ "ẫ": 291,
308
+ "ậ": 292,
309
+ "ắ": 293,
310
+ "ằ": 294,
311
+ "ẳ": 295,
312
+ "ẵ": 296,
313
+ "ặ": 297,
314
+ "ẹ": 298,
315
+ "ẻ": 299,
316
+ "ẽ": 300,
317
+ "Ế": 301,
318
+ "ế": 302,
319
+ "Ề": 303,
320
+ "ề": 304,
321
+ "ể": 305,
322
+ "ễ": 306,
323
+ "ệ": 307,
324
+ "ỉ": 308,
325
+ "ị": 309,
326
+ "ọ": 310,
327
+ "ỏ": 311,
328
+ "Ố": 312,
329
+ "ố": 313,
330
+ "Ồ": 314,
331
+ "ồ": 315,
332
+ "Ổ": 316,
333
+ "ổ": 317,
334
+ "ỗ": 318,
335
+ "Ộ": 319,
336
+ "ộ": 320,
337
+ "ớ": 321,
338
+ "Ờ": 322,
339
+ "ờ": 323,
340
+ "Ở": 324,
341
+ "ở": 325,
342
+ "ỡ": 326,
343
+ "ợ": 327,
344
+ "ụ": 328,
345
+ "ủ": 329,
346
+ "Ứ": 330,
347
+ "ứ": 331,
348
+ "Ừ": 332,
349
+ "ừ": 333,
350
+ "ử": 334,
351
+ "ữ": 335,
352
+ "ự": 336,
353
+ "ỳ": 337,
354
+ "ỵ": 338,
355
+ "Ỷ": 339,
356
+ "ỷ": 340,
357
+ "ỹ": 341,
358
+ "ὖ": 342,
359
+ "ὼ": 343,
360
+ "ῆ": 344,
361
+ "​": 345,
362
+ "‐": 346,
363
+ "—": 347,
364
+ "―": 348,
365
+ "†": 349,
366
+ "•": 350,
367
+ "…": 351,
368
+ "‰": 352,
369
+ "′": 353,
370
+ "″": 354,
371
+ "⁄": 355,
372
+ "⁷": 356,
373
+ "⁻": 357,
374
+ "₀": 358,
375
+ "₁": 359,
376
+ "₂": 360,
377
+ "₃": 361,
378
+ "₄": 362,
379
+ "₅": 363,
380
+ "₆": 364,
381
+ "₇": 365,
382
+ "₈": 366,
383
+ "€": 367,
384
+ "₹": 368,
385
+ "⅓": 369,
386
+ "⅔": 370,
387
+ "⅖": 371,
388
+ "⅙": 372,
389
+ "⅛": 373,
390
+ "⅝": 374,
391
+ "√": 375,
392
+ "│": 376,
393
+ "♦": 377,
394
+ "⚓": 378,
395
+ "✈": 379,
396
+ "✠": 380,
397
+ "✨": 381,
398
+ "⟙": 382,
399
+ "⸺": 383,
400
+ "。": 384,
401
+ "〈": 385,
402
+ "な": 386,
403
+ "三": 387,
404
+ "次": 388,
405
+ "肿": 389,
406
+ "臃": 390,
407
+ "구": 391,
408
+ "로": 392,
409
+ "요": 393,
410
+ "ﷺ": 394,
411
+ "️": 395,
412
+ "𝑥": 396,
413
+ "𝑦": 397,
414
+ "🌊": 398,
415
+ "🌿": 399,
416
+ "💦": 400,
417
+ "💨": 401
418
+ },
419
+ "phoneme_symbols": {
420
+ "0": "_",
421
+ "1": "<de>",
422
+ "2": "<en_gb>",
423
+ "3": "<en_us>",
424
+ "4": "<es>",
425
+ "5": "<fr>",
426
+ "6": "<it>",
427
+ "7": "<vi>",
428
+ "8": "<end>",
429
+ "9": " ",
430
+ "10": "!",
431
+ "11": ",",
432
+ "12": "-",
433
+ "13": ".",
434
+ "14": "1",
435
+ "15": "2",
436
+ "16": "4",
437
+ "17": "5",
438
+ "18": "6",
439
+ "19": "7",
440
+ "20": ":",
441
+ "21": ";",
442
+ "22": "?",
443
+ "23": "a",
444
+ "24": "b",
445
+ "25": "c",
446
+ "26": "d",
447
+ "27": "e",
448
+ "28": "f",
449
+ "29": "h",
450
+ "30": "i",
451
+ "31": "j",
452
+ "32": "k",
453
+ "33": "l",
454
+ "34": "m",
455
+ "35": "n",
456
+ "36": "o",
457
+ "37": "p",
458
+ "38": "q",
459
+ "39": "r",
460
+ "40": "s",
461
+ "41": "t",
462
+ "42": "u",
463
+ "43": "v",
464
+ "44": "w",
465
+ "45": "x",
466
+ "46": "y",
467
+ "47": "z",
468
+ "48": "«",
469
+ "49": "»",
470
+ "50": "æ",
471
+ "51": "ç",
472
+ "52": "ð",
473
+ "53": "ø",
474
+ "54": "ŋ",
475
+ "55": "œ",
476
+ "56": "ɐ",
477
+ "57": "ɑ",
478
+ "58": "ɒ",
479
+ "59": "ɔ",
480
+ "60": "ɗ",
481
+ "61": "ə",
482
+ "62": "ɚ",
483
+ "63": "ɛ",
484
+ "64": "ɜ",
485
+ "65": "ɟ",
486
+ "66": "ɡ",
487
+ "67": "ɣ",
488
+ "68": "ɨ",
489
+ "69": "ɪ",
490
+ "70": "ɬ",
491
+ "71": "ɯ",
492
+ "72": "ɲ",
493
+ "73": "ɹ",
494
+ "74": "ɾ",
495
+ "75": "ʁ",
496
+ "76": "ʃ",
497
+ "77": "ʊ",
498
+ "78": "ʌ",
499
+ "79": "ʎ",
500
+ "80": "ʐ",
501
+ "81": "ʒ",
502
+ "82": "ʔ",
503
+ "83": "ʝ",
504
+ "84": "ʲ",
505
+ "85": "ˈ",
506
+ "86": "ˌ",
507
+ "87": "ː",
508
+ "88": "̃",
509
+ "89": "̩",
510
+ "90": "̪",
511
+ "91": "β",
512
+ "92": "θ",
513
+ "93": "ᵻ",
514
+ "94": "—",
515
+ "95": "…"
516
+ }
517
+ }