Hugging Face's logo

Spaces:
ESpeech
/
open_tts_leaderboard_ru
Running

App Files Community
Den4ikAI commited on
Commit
767ecc3
·
verified ·
1 Parent(s): c6714a7

Update data.json

Browse files
Files changed (1) hide show
  1. data.json +510 -465
data.json CHANGED
@@ -1,467 +1,512 @@
1
  [
2
- {
3
- "engine": "Silero v3_1",
4
- "voice": "Aidar",
5
- "test_date": "21/06/2024",
6
- "type": "single_speaker",
7
- "cer": 0.7,
8
- "xrt_gpu": 0.0177,
9
- "xrt_cpu": 0.1256,
10
- "utmos": 2.544,
11
- "similarity_avg": null,
12
- "similarity_min": null,
13
- "encodec_fad": 97.36,
14
- "hardware": "Local GPU",
15
- "notes": ""
16
- },
17
- {
18
- "engine": "Silero v3_1",
19
- "voice": "Baya",
20
- "test_date": "21/06/2024",
21
- "type": "single_speaker",
22
- "cer": 0.7,
23
- "xrt_gpu": 0.0177,
24
- "xrt_cpu": 0.1256,
25
- "utmos": 2.978,
26
- "similarity_avg": null,
27
- "similarity_min": null,
28
- "encodec_fad": 170.53,
29
- "hardware": "Local GPU",
30
- "notes": ""
31
- },
32
- {
33
- "engine": "Silero 4",
34
- "voice": "Aidar",
35
- "test_date": "21/06/2024",
36
- "type": "single_speaker",
37
- "cer": 1.0,
38
- "xrt_gpu": 0.0149,
39
- "xrt_cpu": 0.0544,
40
- "utmos": 1.755,
41
- "similarity_avg": null,
42
- "similarity_min": null,
43
- "encodec_fad": 79.33,
44
- "hardware": "Local GPU",
45
- "notes": ""
46
- },
47
- {
48
- "engine": "Silero 4",
49
- "voice": "Baya",
50
- "test_date": "21/06/2024",
51
- "type": "single_speaker",
52
- "cer": 0.9,
53
- "xrt_gpu": 0.0149,
54
- "xrt_cpu": 0.0544,
55
- "utmos": 2.144,
56
- "similarity_avg": null,
57
- "similarity_min": null,
58
- "encodec_fad": 118.63,
59
- "hardware": "Local GPU",
60
- "notes": ""
61
- },
62
- {
63
- "engine": "Vosk-TTS 0.9",
64
- "voice": "Multi",
65
- "test_date": "12/06/2025",
66
- "type": "multi_speaker",
67
- "cer": 0.6,
68
- "xrt_gpu": 0.07,
69
- "xrt_cpu": 0.3,
70
- "utmos": 3.29,
71
- "similarity_avg": 0.875,
72
- "similarity_min": 0.600,
73
- "encodec_fad": 0.81,
74
- "hardware": "Local GPU",
75
- "notes": ""
76
- },
77
- {
78
- "engine": "TeraTTS",
79
- "voice": "Natasha",
80
- "test_date": "21/06/2024",
81
- "type": "single_speaker",
82
- "cer": 1.6,
83
- "xrt_gpu": null,
84
- "xrt_cpu": 0.1945,
85
- "utmos": 3.281,
86
- "similarity_avg": null,
87
- "similarity_min": null,
88
- "encodec_fad": 70.10,
89
- "hardware": "Local CPU",
90
- "notes": ""
91
- },
92
- {
93
- "engine": "UtrobinTTS",
94
- "voice": "Male",
95
- "test_date": "21/06/2024",
96
- "type": "single_speaker",
97
- "cer": 2.1,
98
- "xrt_gpu": 0.0265,
99
- "xrt_cpu": 0.1323,
100
- "utmos": 3.186,
101
- "similarity_avg": null,
102
- "similarity_min": null,
103
- "encodec_fad": 46.14,
104
- "hardware": "Local GPU",
105
- "notes": ""
106
- },
107
- {
108
- "engine": "XTTS2",
109
- "voice": "Multi",
110
- "test_date": "21/06/2024",
111
- "type": "voice_cloning",
112
- "cer": 2.7,
113
- "xrt_gpu": 0.3458,
114
- "xrt_cpu": null,
115
- "utmos": 3.035,
116
- "similarity_avg": 0.762,
117
- "similarity_min": 0.468,
118
- "encodec_fad": 5.42,
119
- "hardware": "Local GPU",
120
- "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
121
- },
122
- {
123
- "engine": "Vosk-TTS GPT",
124
- "voice": "Multi",
125
- "test_date": "21/06/2024",
126
- "type": "voice_cloning",
127
- "cer": 2.1,
128
- "xrt_gpu": 0.2690,
129
- "xrt_cpu": null,
130
- "utmos": 3.381,
131
- "similarity_avg": 0.814,
132
- "similarity_min": 0.544,
133
- "encodec_fad": 5.89,
134
- "hardware": "Local GPU",
135
- "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
136
- },
137
- {
138
- "engine": "Piper",
139
- "voice": "Irina",
140
- "test_date": "21/06/2024",
141
- "type": "single_speaker",
142
- "cer": 1.4,
143
- "xrt_gpu": null,
144
- "xrt_cpu": 0.045,
145
- "utmos": 3.672,
146
- "similarity_avg": null,
147
- "similarity_min": null,
148
- "encodec_fad": 74.98,
149
- "hardware": "Local CPU",
150
- "notes": ""
151
- },
152
- {
153
- "engine": "Piper",
154
- "voice": "Ruslan",
155
- "test_date": "21/06/2024",
156
- "type": "single_speaker",
157
- "cer": 3.0,
158
- "xrt_gpu": null,
159
- "xrt_cpu": 0.045,
160
- "utmos": 2.975,
161
- "similarity_avg": null,
162
- "similarity_min": null,
163
- "encodec_fad": 72.22,
164
- "hardware": "Local CPU",
165
- "notes": ""
166
- },
167
- {
168
- "engine": "BeneGes",
169
- "voice": "Ruslan",
170
- "test_date": "21/06/2024",
171
- "type": "single_speaker",
172
- "cer": 2.4,
173
- "xrt_gpu": null,
174
- "xrt_cpu": 0.321,
175
- "utmos": 2.537,
176
- "similarity_avg": null,
177
- "similarity_min": null,
178
- "encodec_fad": 63.02,
179
- "hardware": "Local CPU",
180
- "notes": ""
181
- },
182
- {
183
- "engine": "Tortoise Ruslan",
184
- "voice": "Multi",
185
- "test_date": "21/06/2024",
186
- "type": "voice_cloning",
187
- "cer": 6.2,
188
- "xrt_gpu": 25.03,
189
- "xrt_cpu": null,
190
- "utmos": 2.893,
191
- "similarity_avg": 0.660,
192
- "similarity_min": 0.483,
193
- "encodec_fad": 14.21,
194
- "hardware": "Local GPU",
195
- "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
196
- },
197
- {
198
- "engine": "Bark Small",
199
- "voice": "Ru_4",
200
- "test_date": "21/06/2024",
201
- "type": "single_speaker",
202
- "cer": 10.3,
203
- "xrt_gpu": 1.201,
204
- "xrt_cpu": null,
205
- "utmos": 2.554,
206
- "similarity_avg": null,
207
- "similarity_min": null,
208
- "encodec_fad": 61.71,
209
- "hardware": "Local GPU",
210
- "notes": ""
211
- },
212
- {
213
- "engine": "EdgeTTS",
214
- "voice": "Dmitry",
215
- "test_date": "21/06/2024",
216
- "type": "single_speaker",
217
- "cer": 0.7,
218
- "xrt_gpu": null,
219
- "xrt_cpu": 0.076,
220
- "utmos": 3.565,
221
- "similarity_avg": null,
222
- "similarity_min": null,
223
- "encodec_fad": 32.69,
224
- "hardware": "Cloud",
225
- "notes": "cloud"
226
- },
227
- {
228
- "engine": "EdgeTTS",
229
- "voice": "Svetlana",
230
- "test_date": "21/06/2024",
231
- "type": "single_speaker",
232
- "cer": 0.7,
233
- "xrt_gpu": null,
234
- "xrt_cpu": 0.076,
235
- "utmos": 3.513,
236
- "similarity_avg": null,
237
- "similarity_min": null,
238
- "encodec_fad": 30.60,
239
- "hardware": "Cloud",
240
- "notes": "cloud"
241
- },
242
- {
243
- "engine": "Yandex",
244
- "voice": "Alexander",
245
- "test_date": "21/06/2024",
246
- "type": "single_speaker",
247
- "cer": 0.6,
248
- "xrt_gpu": null,
249
- "xrt_cpu": 0.028,
250
- "utmos": 3.413,
251
- "similarity_avg": null,
252
- "similarity_min": null,
253
- "encodec_fad": 54.10,
254
- "hardware": "Cloud",
255
- "notes": "cloud"
256
- },
257
- {
258
- "engine": "Yandex",
259
- "voice": "Marina",
260
- "test_date": "21/06/2024",
261
- "type": "single_speaker",
262
- "cer": 0.6,
263
- "xrt_gpu": null,
264
- "xrt_cpu": 0.028,
265
- "utmos": 3.482,
266
- "similarity_avg": null,
267
- "similarity_min": null,
268
- "encodec_fad": 26.23,
269
- "hardware": "Cloud",
270
- "notes": "cloud"
271
- },
272
- {
273
- "engine": "Sber",
274
- "voice": "Boris 24",
275
- "test_date": "03/11/2024",
276
- "type": "single_speaker",
277
- "cer": 0.7,
278
- "xrt_gpu": null,
279
- "xrt_cpu": 0.31,
280
- "utmos": 3.747,
281
- "similarity_avg": null,
282
- "similarity_min": null,
283
- "encodec_fad": 26.21,
284
- "hardware": "Cloud",
285
- "notes": "cloud"
286
- },
287
- {
288
- "engine": "Sber",
289
- "voice": "Alexandra 24",
290
- "test_date": "03/11/2024",
291
- "type": "single_speaker",
292
- "cer": 0.8,
293
- "xrt_gpu": null,
294
- "xrt_cpu": 0.30,
295
- "utmos": 3.196,
296
- "similarity_avg": null,
297
- "similarity_min": null,
298
- "encodec_fad": 32.04,
299
- "hardware": "Cloud",
300
- "notes": "cloud"
301
- },
302
- {
303
- "engine": "FishSpeech 1.5",
304
- "voice": "Multi",
305
- "test_date": "07/08/2025",
306
- "type": "voice_cloning",
307
- "cer": 1.5,
308
- "xrt_gpu": 1.7,
309
- "xrt_cpu": null,
310
- "utmos": 3.183,
311
- "similarity_avg": 0.757,
312
- "similarity_min": 0.535,
313
- "encodec_fad": 2.37,
314
- "hardware": "Local GPU",
315
- "notes": ""
316
- },
317
- {
318
- "engine": "Tinkoff",
319
- "voice": "Alyona",
320
- "test_date": "14/12/2024",
321
- "type": "single_speaker",
322
- "cer": 0.7,
323
- "xrt_gpu": null,
324
- "xrt_cpu": 0.16,
325
- "utmos": 3.634,
326
- "similarity_avg": null,
327
- "similarity_min": null,
328
- "encodec_fad": 172.9,
329
- "hardware": "Cloud",
330
- "notes": "cloud"
331
- },
332
- {
333
- "engine": "Tinkoff",
334
- "voice": "Dima",
335
- "test_date": "20/03/2025",
336
- "type": "single_speaker",
337
- "cer": 0.8,
338
- "xrt_gpu": null,
339
- "xrt_cpu": 0.16,
340
- "utmos": 3.568,
341
- "similarity_avg": null,
342
- "similarity_min": null,
343
- "encodec_fad": 129.2,
344
- "hardware": "Cloud",
345
- "notes": "cloud"
346
- },
347
- {
348
- "engine": "Tinkoff",
349
- "voice": "Anna",
350
- "test_date": "20/03/2025",
351
- "type": "single_speaker",
352
- "cer": 0.8,
353
- "xrt_gpu": null,
354
- "xrt_cpu": 0.16,
355
- "utmos": 2.919,
356
- "similarity_avg": null,
357
- "similarity_min": null,
358
- "encodec_fad": 120.5,
359
- "hardware": "Cloud",
360
- "notes": "cloud"
361
- },
362
- {
363
- "engine": "F5-TTS Misha V2",
364
- "voice": "Multi",
365
- "test_date": "07/08/2025",
366
- "type": "voice_cloning",
367
- "cer": 2.4,
368
- "xrt_gpu": 1.37,
369
- "xrt_cpu": null,
370
- "utmos": 3.157,
371
- "similarity_avg": 0.821,
372
- "similarity_min": null,
373
- "encodec_fad": 1.9,
374
- "hardware": "Local GPU",
375
- "notes": ""
376
- },
377
- {
378
- "engine": "ESpeech-TTS-1 [RL] V2",
379
- "voice": "Multi",
380
- "test_date": "17/08/2025",
381
- "type": "voice_cloning",
382
- "cer": 2.3,
383
- "xrt_gpu": 0.19,
384
- "xrt_cpu": null,
385
- "utmos": 3.289,
386
- "similarity_avg": 0.826,
387
- "similarity_min": null,
388
- "encodec_fad": 2.89,
389
- "hardware": "RTX 4090",
390
- "notes": ""
391
- },
392
- {
393
- "engine": "ESpeech-TTS-1 [SFT] 265K",
394
- "voice": "Multi",
395
- "test_date": "17/08/2025",
396
- "type": "voice_cloning",
397
- "cer": 2.9,
398
- "xrt_gpu": 0.19,
399
- "xrt_cpu": null,
400
- "utmos": 3.136,
401
- "similarity_avg": 0.827,
402
- "similarity_min": null,
403
- "encodec_fad": 2.66,
404
- "hardware": "RTX 4090",
405
- "notes": ""
406
- },
407
- {
408
- "engine": "ESpeech-TTS-1 [RL] V1",
409
- "voice": "Multi",
410
- "test_date": "17/08/2025",
411
- "type": "voice_cloning",
412
- "cer": 2.3,
413
- "xrt_gpu": 0.19,
414
- "xrt_cpu": null,
415
- "utmos": 3.239,
416
- "similarity_avg": 0.828,
417
- "similarity_min": null,
418
- "encodec_fad": 2.54,
419
- "hardware": "RTX 4090",
420
- "notes": ""
421
- },
422
- {
423
- "engine": "ESpeech-TTS-1 [SFT] 95K",
424
- "voice": "Multi",
425
- "test_date": "17/08/2025",
426
- "type": "voice_cloning",
427
- "cer": 1.6,
428
- "xrt_gpu": 0.19,
429
- "xrt_cpu": null,
430
- "utmos": 3.198,
431
- "similarity_avg": 0.830,
432
- "similarity_min": null,
433
- "encodec_fad": 3.06,
434
- "hardware": "RTX 4090",
435
- "notes": ""
436
- },
437
- {
438
- "engine": "ESpeech-TTS-1 PODCASTER [SFT]",
439
- "voice": "Multi",
440
- "test_date": "18/08/2025",
441
- "type": "voice_cloning",
442
- "cer": 1.3,
443
- "xrt_gpu": 0.19,
444
- "xrt_cpu": null,
445
- "utmos": 3.203,
446
- "similarity_avg": 0.833,
447
- "similarity_min": null,
448
- "encodec_fad": 3.06,
449
- "hardware": "RTX 4090",
450
- "notes": "Trained ONLY Podcasts"
451
- },
452
- {
453
- "engine": "ElevenLabs Multilingual V2",
454
- "voice": "Multi",
455
- "test_date": "17/08/2025",
456
- "type": "voice_cloning",
457
- "cer": 1.2,
458
- "xrt_gpu": null,
459
- "xrt_cpu": null,
460
- "utmos": 3.309,
461
- "similarity_avg": 0.780,
462
- "similarity_min": null,
463
- "encodec_fad": 3.05,
464
- "hardware": "Cloud",
465
- "notes": "cloud"
466
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
467
  ]
 
1
  [
2
+ {
3
+ "engine": "Silero v3_1",
4
+ "voice": "Aidar",
5
+ "test_date": "21/06/2024",
6
+ "type": "single_speaker",
7
+ "cer": 0.7,
8
+ "xrt_gpu": 0.0177,
9
+ "xrt_cpu": 0.1256,
10
+ "utmos": 2.544,
11
+ "similarity_avg": null,
12
+ "similarity_min": null,
13
+ "encodec_fad": 97.36,
14
+ "hardware": "Local GPU",
15
+ "notes": ""
16
+ },
17
+ {
18
+ "engine": "Silero v3_1",
19
+ "voice": "Baya",
20
+ "test_date": "21/06/2024",
21
+ "type": "single_speaker",
22
+ "cer": 0.7,
23
+ "xrt_gpu": 0.0177,
24
+ "xrt_cpu": 0.1256,
25
+ "utmos": 2.978,
26
+ "similarity_avg": null,
27
+ "similarity_min": null,
28
+ "encodec_fad": 170.53,
29
+ "hardware": "Local GPU",
30
+ "notes": ""
31
+ },
32
+ {
33
+ "engine": "Silero 4",
34
+ "voice": "Aidar",
35
+ "test_date": "21/06/2024",
36
+ "type": "single_speaker",
37
+ "cer": 1,
38
+ "xrt_gpu": 0.0149,
39
+ "xrt_cpu": 0.0544,
40
+ "utmos": 1.755,
41
+ "similarity_avg": null,
42
+ "similarity_min": null,
43
+ "encodec_fad": 79.33,
44
+ "hardware": "Local GPU",
45
+ "notes": ""
46
+ },
47
+ {
48
+ "engine": "Silero 4",
49
+ "voice": "Baya",
50
+ "test_date": "21/06/2024",
51
+ "type": "single_speaker",
52
+ "cer": 0.9,
53
+ "xrt_gpu": 0.0149,
54
+ "xrt_cpu": 0.0544,
55
+ "utmos": 2.144,
56
+ "similarity_avg": null,
57
+ "similarity_min": null,
58
+ "encodec_fad": 118.63,
59
+ "hardware": "Local GPU",
60
+ "notes": ""
61
+ },
62
+ {
63
+ "engine": "Vosk-TTS 0.9",
64
+ "voice": "Multi",
65
+ "test_date": "12/06/2025",
66
+ "type": "multi_speaker",
67
+ "cer": 0.6,
68
+ "xrt_gpu": 0.07,
69
+ "xrt_cpu": 0.3,
70
+ "utmos": 3.29,
71
+ "similarity_avg": 0.875,
72
+ "similarity_min": 0.6,
73
+ "encodec_fad": 0.81,
74
+ "hardware": "Local GPU",
75
+ "notes": ""
76
+ },
77
+ {
78
+ "engine": "TeraTTS",
79
+ "voice": "Natasha",
80
+ "test_date": "21/06/2024",
81
+ "type": "single_speaker",
82
+ "cer": 1.6,
83
+ "xrt_gpu": null,
84
+ "xrt_cpu": 0.1945,
85
+ "utmos": 3.281,
86
+ "similarity_avg": null,
87
+ "similarity_min": null,
88
+ "encodec_fad": 70.1,
89
+ "hardware": "Local CPU",
90
+ "notes": ""
91
+ },
92
+ {
93
+ "engine": "UtrobinTTS",
94
+ "voice": "Male",
95
+ "test_date": "21/06/2024",
96
+ "type": "single_speaker",
97
+ "cer": 2.1,
98
+ "xrt_gpu": 0.0265,
99
+ "xrt_cpu": 0.1323,
100
+ "utmos": 3.186,
101
+ "similarity_avg": null,
102
+ "similarity_min": null,
103
+ "encodec_fad": 46.14,
104
+ "hardware": "Local GPU",
105
+ "notes": ""
106
+ },
107
+ {
108
+ "engine": "XTTS2",
109
+ "voice": "Multi",
110
+ "test_date": "21/06/2024",
111
+ "type": "voice_cloning",
112
+ "cer": 2.7,
113
+ "xrt_gpu": 0.3458,
114
+ "xrt_cpu": null,
115
+ "utmos": 3.035,
116
+ "similarity_avg": 0.762,
117
+ "similarity_min": 0.468,
118
+ "encodec_fad": 5.42,
119
+ "hardware": "Local GPU",
120
+ "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
121
+ },
122
+ {
123
+ "engine": "Vosk-TTS GPT",
124
+ "voice": "Multi",
125
+ "test_date": "21/06/2024",
126
+ "type": "voice_cloning",
127
+ "cer": 2.1,
128
+ "xrt_gpu": 0.269,
129
+ "xrt_cpu": null,
130
+ "utmos": 3.381,
131
+ "similarity_avg": 0.814,
132
+ "similarity_min": 0.544,
133
+ "encodec_fad": 5.89,
134
+ "hardware": "Local GPU",
135
+ "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
136
+ },
137
+ {
138
+ "engine": "Piper",
139
+ "voice": "Irina",
140
+ "test_date": "21/06/2024",
141
+ "type": "single_speaker",
142
+ "cer": 1.4,
143
+ "xrt_gpu": null,
144
+ "xrt_cpu": 0.045,
145
+ "utmos": 3.672,
146
+ "similarity_avg": null,
147
+ "similarity_min": null,
148
+ "encodec_fad": 74.98,
149
+ "hardware": "Local CPU",
150
+ "notes": ""
151
+ },
152
+ {
153
+ "engine": "Piper",
154
+ "voice": "Ruslan",
155
+ "test_date": "21/06/2024",
156
+ "type": "single_speaker",
157
+ "cer": 3,
158
+ "xrt_gpu": null,
159
+ "xrt_cpu": 0.045,
160
+ "utmos": 2.975,
161
+ "similarity_avg": null,
162
+ "similarity_min": null,
163
+ "encodec_fad": 72.22,
164
+ "hardware": "Local CPU",
165
+ "notes": ""
166
+ },
167
+ {
168
+ "engine": "BeneGes",
169
+ "voice": "Ruslan",
170
+ "test_date": "21/06/2024",
171
+ "type": "single_speaker",
172
+ "cer": 2.4,
173
+ "xrt_gpu": null,
174
+ "xrt_cpu": 0.321,
175
+ "utmos": 2.537,
176
+ "similarity_avg": null,
177
+ "similarity_min": null,
178
+ "encodec_fad": 63.02,
179
+ "hardware": "Local CPU",
180
+ "notes": ""
181
+ },
182
+ {
183
+ "engine": "Tortoise Ruslan",
184
+ "voice": "Multi",
185
+ "test_date": "21/06/2024",
186
+ "type": "voice_cloning",
187
+ "cer": 6.2,
188
+ "xrt_gpu": 25.03,
189
+ "xrt_cpu": null,
190
+ "utmos": 2.893,
191
+ "similarity_avg": 0.66,
192
+ "similarity_min": 0.483,
193
+ "encodec_fad": 14.21,
194
+ "hardware": "Local GPU",
195
+ "notes": "Сравнение проводилось на устаревших данных. Данные не верны!"
196
+ },
197
+ {
198
+ "engine": "Bark Small",
199
+ "voice": "Ru_4",
200
+ "test_date": "21/06/2024",
201
+ "type": "single_speaker",
202
+ "cer": 10.3,
203
+ "xrt_gpu": 1.201,
204
+ "xrt_cpu": null,
205
+ "utmos": 2.554,
206
+ "similarity_avg": null,
207
+ "similarity_min": null,
208
+ "encodec_fad": 61.71,
209
+ "hardware": "Local GPU",
210
+ "notes": ""
211
+ },
212
+ {
213
+ "engine": "EdgeTTS",
214
+ "voice": "Dmitry",
215
+ "test_date": "21/06/2024",
216
+ "type": "single_speaker",
217
+ "cer": 0.7,
218
+ "xrt_gpu": null,
219
+ "xrt_cpu": 0.076,
220
+ "utmos": 3.565,
221
+ "similarity_avg": null,
222
+ "similarity_min": null,
223
+ "encodec_fad": 32.69,
224
+ "hardware": "Cloud",
225
+ "notes": "cloud"
226
+ },
227
+ {
228
+ "engine": "EdgeTTS",
229
+ "voice": "Svetlana",
230
+ "test_date": "21/06/2024",
231
+ "type": "single_speaker",
232
+ "cer": 0.7,
233
+ "xrt_gpu": null,
234
+ "xrt_cpu": 0.076,
235
+ "utmos": 3.513,
236
+ "similarity_avg": null,
237
+ "similarity_min": null,
238
+ "encodec_fad": 30.6,
239
+ "hardware": "Cloud",
240
+ "notes": "cloud"
241
+ },
242
+ {
243
+ "engine": "Yandex",
244
+ "voice": "Alexander",
245
+ "test_date": "21/06/2024",
246
+ "type": "single_speaker",
247
+ "cer": 0.6,
248
+ "xrt_gpu": null,
249
+ "xrt_cpu": 0.028,
250
+ "utmos": 3.413,
251
+ "similarity_avg": null,
252
+ "similarity_min": null,
253
+ "encodec_fad": 54.1,
254
+ "hardware": "Cloud",
255
+ "notes": "cloud"
256
+ },
257
+ {
258
+ "engine": "Yandex",
259
+ "voice": "Marina",
260
+ "test_date": "21/06/2024",
261
+ "type": "single_speaker",
262
+ "cer": 0.6,
263
+ "xrt_gpu": null,
264
+ "xrt_cpu": 0.028,
265
+ "utmos": 3.482,
266
+ "similarity_avg": null,
267
+ "similarity_min": null,
268
+ "encodec_fad": 26.23,
269
+ "hardware": "Cloud",
270
+ "notes": "cloud"
271
+ },
272
+ {
273
+ "engine": "Sber",
274
+ "voice": "Boris 24",
275
+ "test_date": "03/11/2024",
276
+ "type": "single_speaker",
277
+ "cer": 0.7,
278
+ "xrt_gpu": null,
279
+ "xrt_cpu": 0.31,
280
+ "utmos": 3.747,
281
+ "similarity_avg": null,
282
+ "similarity_min": null,
283
+ "encodec_fad": 26.21,
284
+ "hardware": "Cloud",
285
+ "notes": "cloud"
286
+ },
287
+ {
288
+ "engine": "Sber",
289
+ "voice": "Alexandra 24",
290
+ "test_date": "03/11/2024",
291
+ "type": "single_speaker",
292
+ "cer": 0.8,
293
+ "xrt_gpu": null,
294
+ "xrt_cpu": 0.3,
295
+ "utmos": 3.196,
296
+ "similarity_avg": null,
297
+ "similarity_min": null,
298
+ "encodec_fad": 32.04,
299
+ "hardware": "Cloud",
300
+ "notes": "cloud"
301
+ },
302
+ {
303
+ "engine": "FishSpeech 1.5",
304
+ "voice": "Multi",
305
+ "test_date": "07/08/2025",
306
+ "type": "voice_cloning",
307
+ "cer": 1.5,
308
+ "xrt_gpu": 1.7,
309
+ "xrt_cpu": null,
310
+ "utmos": 3.183,
311
+ "similarity_avg": 0.757,
312
+ "similarity_min": 0.535,
313
+ "encodec_fad": 2.37,
314
+ "hardware": "Local GPU",
315
+ "notes": ""
316
+ },
317
+ {
318
+ "engine": "Tinkoff",
319
+ "voice": "Alyona",
320
+ "test_date": "14/12/2024",
321
+ "type": "single_speaker",
322
+ "cer": 0.7,
323
+ "xrt_gpu": null,
324
+ "xrt_cpu": 0.16,
325
+ "utmos": 3.634,
326
+ "similarity_avg": null,
327
+ "similarity_min": null,
328
+ "encodec_fad": 172.9,
329
+ "hardware": "Cloud",
330
+ "notes": "cloud"
331
+ },
332
+ {
333
+ "engine": "Tinkoff",
334
+ "voice": "Dima",
335
+ "test_date": "20/03/2025",
336
+ "type": "single_speaker",
337
+ "cer": 0.8,
338
+ "xrt_gpu": null,
339
+ "xrt_cpu": 0.16,
340
+ "utmos": 3.568,
341
+ "similarity_avg": null,
342
+ "similarity_min": null,
343
+ "encodec_fad": 129.2,
344
+ "hardware": "Cloud",
345
+ "notes": "cloud"
346
+ },
347
+ {
348
+ "engine": "Tinkoff",
349
+ "voice": "Anna",
350
+ "test_date": "20/03/2025",
351
+ "type": "single_speaker",
352
+ "cer": 0.8,
353
+ "xrt_gpu": null,
354
+ "xrt_cpu": 0.16,
355
+ "utmos": 2.919,
356
+ "similarity_avg": null,
357
+ "similarity_min": null,
358
+ "encodec_fad": 120.5,
359
+ "hardware": "Cloud",
360
+ "notes": "cloud"
361
+ },
362
+ {
363
+ "engine": "F5-TTS Misha V2",
364
+ "voice": "Multi",
365
+ "test_date": "07/08/2025",
366
+ "type": "voice_cloning",
367
+ "cer": 3,
368
+ "xrt_gpu": 0.19,
369
+ "xrt_cpu": null,
370
+ "utmos": 3.151,
371
+ "similarity_avg": 0.821,
372
+ "similarity_min": null,
373
+ "encodec_fad": 1.9,
374
+ "hardware": "Local GPU",
375
+ "notes": ""
376
+ },
377
+ {
378
+ "engine": "ESpeech-TTS-1 [RL] V2",
379
+ "voice": "Multi",
380
+ "test_date": "17/08/2025",
381
+ "type": "voice_cloning",
382
+ "cer": 1.4,
383
+ "xrt_gpu": 0.19,
384
+ "xrt_cpu": null,
385
+ "utmos": 3.265,
386
+ "similarity_avg": 0.833,
387
+ "similarity_min": null,
388
+ "encodec_fad": 2.12,
389
+ "hardware": "RTX 4090",
390
+ "notes": ""
391
+ },
392
+ {
393
+ "engine": "ESpeech-TTS-1 [SFT] 265K",
394
+ "voice": "Multi",
395
+ "test_date": "17/08/2025",
396
+ "type": "voice_cloning",
397
+ "cer": 2.9,
398
+ "xrt_gpu": 0.19,
399
+ "xrt_cpu": null,
400
+ "utmos": 3.136,
401
+ "similarity_avg": 0.827,
402
+ "similarity_min": null,
403
+ "encodec_fad": 2.66,
404
+ "hardware": "RTX 4090",
405
+ "notes": ""
406
+ },
407
+ {
408
+ "engine": "ESpeech-TTS-1 [RL] V1",
409
+ "voice": "Multi",
410
+ "test_date": "17/08/2025",
411
+ "type": "voice_cloning",
412
+ "cer": 2.3,
413
+ "xrt_gpu": 0.19,
414
+ "xrt_cpu": null,
415
+ "utmos": 3.239,
416
+ "similarity_avg": 0.828,
417
+ "similarity_min": null,
418
+ "encodec_fad": 2.54,
419
+ "hardware": "RTX 4090",
420
+ "notes": ""
421
+ },
422
+ {
423
+ "engine": "ESpeech-TTS-1 [SFT] 95K",
424
+ "voice": "Multi",
425
+ "test_date": "17/08/2025",
426
+ "type": "voice_cloning",
427
+ "cer": 1.6,
428
+ "xrt_gpu": 0.19,
429
+ "xrt_cpu": null,
430
+ "utmos": 3.198,
431
+ "similarity_avg": 0.83,
432
+ "similarity_min": null,
433
+ "encodec_fad": 3.06,
434
+ "hardware": "RTX 4090",
435
+ "notes": ""
436
+ },
437
+ {
438
+ "engine": "ESpeech-TTS-1 PODCASTER [SFT]",
439
+ "voice": "Multi",
440
+ "test_date": "18/08/2025",
441
+ "type": "voice_cloning",
442
+ "cer": 2.5,
443
+ "xrt_gpu": 0.19,
444
+ "xrt_cpu": null,
445
+ "utmos": 3.294,
446
+ "similarity_avg": 0.824,
447
+ "similarity_min": null,
448
+ "encodec_fad": 2.52,
449
+ "hardware": "RTX 4090",
450
+ "notes": "Trained ONLY Podcasts"
451
+ },
452
+ {
453
+ "engine": "ElevenLabs Multilingual V2",
454
+ "voice": "Multi",
455
+ "test_date": "17/08/2025",
456
+ "type": "voice_cloning",
457
+ "cer": 1.2,
458
+ "xrt_gpu": null,
459
+ "xrt_cpu": null,
460
+ "utmos": 3.309,
461
+ "similarity_avg": 0.78,
462
+ "similarity_min": null,
463
+ "encodec_fad": 3.05,
464
+ "hardware": "Cloud",
465
+ "notes": "cloud"
466
+ },
467
+ {
468
+ "engine": "MWS AI",
469
+ "voice": "Multi",
470
+ "test_date": "28/08/2025",
471
+ "type": "voice_cloning",
472
+ "cer": 0.8,
473
+ "xrt_gpu": null,
474
+ "xrt_cpu": null,
475
+ "utmos": 3.313,
476
+ "similarity_avg": 0.8,
477
+ "similarity_min": null,
478
+ "encodec_fad": 3.33,
479
+ "hardware": "Cloud",
480
+ "notes": "cloud"
481
+ },
482
+ {
483
+ "engine": "MWS AI",
484
+ "voice": "Islam",
485
+ "test_date": "28/08/2025",
486
+ "type": "voice_cloning",
487
+ "cer": 0.9,
488
+ "xrt_gpu": null,
489
+ "xrt_cpu": null,
490
+ "utmos": 3.667,
491
+ "similarity_avg": null,
492
+ "similarity_min": null,
493
+ "encodec_fad": null,
494
+ "hardware": "Cloud",
495
+ "notes": "cloud"
496
+ },
497
+ {
498
+ "engine": "MWS AI",
499
+ "voice": "Maria",
500
+ "test_date": "28/08/2025",
501
+ "type": "voice_cloning",
502
+ "cer": 0.8,
503
+ "xrt_gpu": null,
504
+ "xrt_cpu": null,
505
+ "utmos": 3.694,
506
+ "similarity_avg": null,
507
+ "similarity_min": null,
508
+ "encodec_fad": null,
509
+ "hardware": "Cloud",
510
+ "notes": "cloud"
511
+ }
512
  ]