paolapersico1
commited on
Commit
•
73a9f87
1
Parent(s):
1e324da
Upload 4 files
Browse files
paola/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for paola (medium)
|
2 |
+
|
3 |
+
* Language: it_IT (Italian, Italy)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/
|
11 |
+
* License: See URL
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
paola/medium/it_IT-paola-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc918b5a0ea6137382833dddfa567bffbe6a5060c02043c87192ee59c04210c
|
3 |
+
size 63511038
|
paola/medium/it_IT-paola-medium.onnx.json
ADDED
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset": "paola",
|
3 |
+
"audio": {
|
4 |
+
"sample_rate": 22050,
|
5 |
+
"quality": "medium"
|
6 |
+
},
|
7 |
+
"espeak": {
|
8 |
+
"voice": "it"
|
9 |
+
},
|
10 |
+
"inference": {
|
11 |
+
"noise_scale": 0.667,
|
12 |
+
"length_scale": 1,
|
13 |
+
"noise_w": 0.8
|
14 |
+
},
|
15 |
+
"phoneme_type": "espeak",
|
16 |
+
"phoneme_map": {},
|
17 |
+
"phoneme_id_map": {
|
18 |
+
" ": [
|
19 |
+
3
|
20 |
+
],
|
21 |
+
"!": [
|
22 |
+
4
|
23 |
+
],
|
24 |
+
"\"": [
|
25 |
+
150
|
26 |
+
],
|
27 |
+
"#": [
|
28 |
+
149
|
29 |
+
],
|
30 |
+
"$": [
|
31 |
+
2
|
32 |
+
],
|
33 |
+
"'": [
|
34 |
+
5
|
35 |
+
],
|
36 |
+
"(": [
|
37 |
+
6
|
38 |
+
],
|
39 |
+
")": [
|
40 |
+
7
|
41 |
+
],
|
42 |
+
",": [
|
43 |
+
8
|
44 |
+
],
|
45 |
+
"-": [
|
46 |
+
9
|
47 |
+
],
|
48 |
+
".": [
|
49 |
+
10
|
50 |
+
],
|
51 |
+
"0": [
|
52 |
+
130
|
53 |
+
],
|
54 |
+
"1": [
|
55 |
+
131
|
56 |
+
],
|
57 |
+
"2": [
|
58 |
+
132
|
59 |
+
],
|
60 |
+
"3": [
|
61 |
+
133
|
62 |
+
],
|
63 |
+
"4": [
|
64 |
+
134
|
65 |
+
],
|
66 |
+
"5": [
|
67 |
+
135
|
68 |
+
],
|
69 |
+
"6": [
|
70 |
+
136
|
71 |
+
],
|
72 |
+
"7": [
|
73 |
+
137
|
74 |
+
],
|
75 |
+
"8": [
|
76 |
+
138
|
77 |
+
],
|
78 |
+
"9": [
|
79 |
+
139
|
80 |
+
],
|
81 |
+
":": [
|
82 |
+
11
|
83 |
+
],
|
84 |
+
";": [
|
85 |
+
12
|
86 |
+
],
|
87 |
+
"?": [
|
88 |
+
13
|
89 |
+
],
|
90 |
+
"^": [
|
91 |
+
1
|
92 |
+
],
|
93 |
+
"_": [
|
94 |
+
0
|
95 |
+
],
|
96 |
+
"a": [
|
97 |
+
14
|
98 |
+
],
|
99 |
+
"b": [
|
100 |
+
15
|
101 |
+
],
|
102 |
+
"c": [
|
103 |
+
16
|
104 |
+
],
|
105 |
+
"d": [
|
106 |
+
17
|
107 |
+
],
|
108 |
+
"e": [
|
109 |
+
18
|
110 |
+
],
|
111 |
+
"f": [
|
112 |
+
19
|
113 |
+
],
|
114 |
+
"h": [
|
115 |
+
20
|
116 |
+
],
|
117 |
+
"i": [
|
118 |
+
21
|
119 |
+
],
|
120 |
+
"j": [
|
121 |
+
22
|
122 |
+
],
|
123 |
+
"k": [
|
124 |
+
23
|
125 |
+
],
|
126 |
+
"l": [
|
127 |
+
24
|
128 |
+
],
|
129 |
+
"m": [
|
130 |
+
25
|
131 |
+
],
|
132 |
+
"n": [
|
133 |
+
26
|
134 |
+
],
|
135 |
+
"o": [
|
136 |
+
27
|
137 |
+
],
|
138 |
+
"p": [
|
139 |
+
28
|
140 |
+
],
|
141 |
+
"q": [
|
142 |
+
29
|
143 |
+
],
|
144 |
+
"r": [
|
145 |
+
30
|
146 |
+
],
|
147 |
+
"s": [
|
148 |
+
31
|
149 |
+
],
|
150 |
+
"t": [
|
151 |
+
32
|
152 |
+
],
|
153 |
+
"u": [
|
154 |
+
33
|
155 |
+
],
|
156 |
+
"v": [
|
157 |
+
34
|
158 |
+
],
|
159 |
+
"w": [
|
160 |
+
35
|
161 |
+
],
|
162 |
+
"x": [
|
163 |
+
36
|
164 |
+
],
|
165 |
+
"y": [
|
166 |
+
37
|
167 |
+
],
|
168 |
+
"z": [
|
169 |
+
38
|
170 |
+
],
|
171 |
+
"æ": [
|
172 |
+
39
|
173 |
+
],
|
174 |
+
"ç": [
|
175 |
+
40
|
176 |
+
],
|
177 |
+
"ð": [
|
178 |
+
41
|
179 |
+
],
|
180 |
+
"ø": [
|
181 |
+
42
|
182 |
+
],
|
183 |
+
"ħ": [
|
184 |
+
43
|
185 |
+
],
|
186 |
+
"ŋ": [
|
187 |
+
44
|
188 |
+
],
|
189 |
+
"œ": [
|
190 |
+
45
|
191 |
+
],
|
192 |
+
"ǀ": [
|
193 |
+
46
|
194 |
+
],
|
195 |
+
"ǁ": [
|
196 |
+
47
|
197 |
+
],
|
198 |
+
"ǂ": [
|
199 |
+
48
|
200 |
+
],
|
201 |
+
"ǃ": [
|
202 |
+
49
|
203 |
+
],
|
204 |
+
"ɐ": [
|
205 |
+
50
|
206 |
+
],
|
207 |
+
"ɑ": [
|
208 |
+
51
|
209 |
+
],
|
210 |
+
"ɒ": [
|
211 |
+
52
|
212 |
+
],
|
213 |
+
"ɓ": [
|
214 |
+
53
|
215 |
+
],
|
216 |
+
"ɔ": [
|
217 |
+
54
|
218 |
+
],
|
219 |
+
"ɕ": [
|
220 |
+
55
|
221 |
+
],
|
222 |
+
"ɖ": [
|
223 |
+
56
|
224 |
+
],
|
225 |
+
"ɗ": [
|
226 |
+
57
|
227 |
+
],
|
228 |
+
"ɘ": [
|
229 |
+
58
|
230 |
+
],
|
231 |
+
"ə": [
|
232 |
+
59
|
233 |
+
],
|
234 |
+
"ɚ": [
|
235 |
+
60
|
236 |
+
],
|
237 |
+
"ɛ": [
|
238 |
+
61
|
239 |
+
],
|
240 |
+
"ɜ": [
|
241 |
+
62
|
242 |
+
],
|
243 |
+
"ɞ": [
|
244 |
+
63
|
245 |
+
],
|
246 |
+
"ɟ": [
|
247 |
+
64
|
248 |
+
],
|
249 |
+
"ɠ": [
|
250 |
+
65
|
251 |
+
],
|
252 |
+
"ɡ": [
|
253 |
+
66
|
254 |
+
],
|
255 |
+
"ɢ": [
|
256 |
+
67
|
257 |
+
],
|
258 |
+
"ɣ": [
|
259 |
+
68
|
260 |
+
],
|
261 |
+
"ɤ": [
|
262 |
+
69
|
263 |
+
],
|
264 |
+
"ɥ": [
|
265 |
+
70
|
266 |
+
],
|
267 |
+
"ɦ": [
|
268 |
+
71
|
269 |
+
],
|
270 |
+
"ɧ": [
|
271 |
+
72
|
272 |
+
],
|
273 |
+
"ɨ": [
|
274 |
+
73
|
275 |
+
],
|
276 |
+
"ɪ": [
|
277 |
+
74
|
278 |
+
],
|
279 |
+
"ɫ": [
|
280 |
+
75
|
281 |
+
],
|
282 |
+
"ɬ": [
|
283 |
+
76
|
284 |
+
],
|
285 |
+
"ɭ": [
|
286 |
+
77
|
287 |
+
],
|
288 |
+
"ɮ": [
|
289 |
+
78
|
290 |
+
],
|
291 |
+
"ɯ": [
|
292 |
+
79
|
293 |
+
],
|
294 |
+
"ɰ": [
|
295 |
+
80
|
296 |
+
],
|
297 |
+
"ɱ": [
|
298 |
+
81
|
299 |
+
],
|
300 |
+
"ɲ": [
|
301 |
+
82
|
302 |
+
],
|
303 |
+
"ɳ": [
|
304 |
+
83
|
305 |
+
],
|
306 |
+
"ɴ": [
|
307 |
+
84
|
308 |
+
],
|
309 |
+
"ɵ": [
|
310 |
+
85
|
311 |
+
],
|
312 |
+
"ɶ": [
|
313 |
+
86
|
314 |
+
],
|
315 |
+
"ɸ": [
|
316 |
+
87
|
317 |
+
],
|
318 |
+
"ɹ": [
|
319 |
+
88
|
320 |
+
],
|
321 |
+
"ɺ": [
|
322 |
+
89
|
323 |
+
],
|
324 |
+
"ɻ": [
|
325 |
+
90
|
326 |
+
],
|
327 |
+
"ɽ": [
|
328 |
+
91
|
329 |
+
],
|
330 |
+
"ɾ": [
|
331 |
+
92
|
332 |
+
],
|
333 |
+
"ʀ": [
|
334 |
+
93
|
335 |
+
],
|
336 |
+
"ʁ": [
|
337 |
+
94
|
338 |
+
],
|
339 |
+
"ʂ": [
|
340 |
+
95
|
341 |
+
],
|
342 |
+
"ʃ": [
|
343 |
+
96
|
344 |
+
],
|
345 |
+
"ʄ": [
|
346 |
+
97
|
347 |
+
],
|
348 |
+
"ʈ": [
|
349 |
+
98
|
350 |
+
],
|
351 |
+
"ʉ": [
|
352 |
+
99
|
353 |
+
],
|
354 |
+
"ʊ": [
|
355 |
+
100
|
356 |
+
],
|
357 |
+
"ʋ": [
|
358 |
+
101
|
359 |
+
],
|
360 |
+
"ʌ": [
|
361 |
+
102
|
362 |
+
],
|
363 |
+
"ʍ": [
|
364 |
+
103
|
365 |
+
],
|
366 |
+
"ʎ": [
|
367 |
+
104
|
368 |
+
],
|
369 |
+
"ʏ": [
|
370 |
+
105
|
371 |
+
],
|
372 |
+
"ʐ": [
|
373 |
+
106
|
374 |
+
],
|
375 |
+
"ʑ": [
|
376 |
+
107
|
377 |
+
],
|
378 |
+
"ʒ": [
|
379 |
+
108
|
380 |
+
],
|
381 |
+
"ʔ": [
|
382 |
+
109
|
383 |
+
],
|
384 |
+
"ʕ": [
|
385 |
+
110
|
386 |
+
],
|
387 |
+
"ʘ": [
|
388 |
+
111
|
389 |
+
],
|
390 |
+
"ʙ": [
|
391 |
+
112
|
392 |
+
],
|
393 |
+
"ʛ": [
|
394 |
+
113
|
395 |
+
],
|
396 |
+
"ʜ": [
|
397 |
+
114
|
398 |
+
],
|
399 |
+
"ʝ": [
|
400 |
+
115
|
401 |
+
],
|
402 |
+
"ʟ": [
|
403 |
+
116
|
404 |
+
],
|
405 |
+
"ʡ": [
|
406 |
+
117
|
407 |
+
],
|
408 |
+
"ʢ": [
|
409 |
+
118
|
410 |
+
],
|
411 |
+
"ʰ": [
|
412 |
+
145
|
413 |
+
],
|
414 |
+
"ʲ": [
|
415 |
+
119
|
416 |
+
],
|
417 |
+
"ˈ": [
|
418 |
+
120
|
419 |
+
],
|
420 |
+
"ˌ": [
|
421 |
+
121
|
422 |
+
],
|
423 |
+
"ː": [
|
424 |
+
122
|
425 |
+
],
|
426 |
+
"ˑ": [
|
427 |
+
123
|
428 |
+
],
|
429 |
+
"˞": [
|
430 |
+
124
|
431 |
+
],
|
432 |
+
"ˤ": [
|
433 |
+
146
|
434 |
+
],
|
435 |
+
"̃": [
|
436 |
+
141
|
437 |
+
],
|
438 |
+
"̧": [
|
439 |
+
140
|
440 |
+
],
|
441 |
+
"̩": [
|
442 |
+
144
|
443 |
+
],
|
444 |
+
"̪": [
|
445 |
+
142
|
446 |
+
],
|
447 |
+
"̯": [
|
448 |
+
143
|
449 |
+
],
|
450 |
+
"̺": [
|
451 |
+
152
|
452 |
+
],
|
453 |
+
"̻": [
|
454 |
+
153
|
455 |
+
],
|
456 |
+
"β": [
|
457 |
+
125
|
458 |
+
],
|
459 |
+
"ε": [
|
460 |
+
147
|
461 |
+
],
|
462 |
+
"θ": [
|
463 |
+
126
|
464 |
+
],
|
465 |
+
"χ": [
|
466 |
+
127
|
467 |
+
],
|
468 |
+
"ᵻ": [
|
469 |
+
128
|
470 |
+
],
|
471 |
+
"↑": [
|
472 |
+
151
|
473 |
+
],
|
474 |
+
"↓": [
|
475 |
+
148
|
476 |
+
],
|
477 |
+
"ⱱ": [
|
478 |
+
129
|
479 |
+
]
|
480 |
+
},
|
481 |
+
"num_symbols": 256,
|
482 |
+
"num_speakers": 1,
|
483 |
+
"speaker_id_map": {},
|
484 |
+
"language": {
|
485 |
+
"code": "it_IT",
|
486 |
+
"family": "it",
|
487 |
+
"region": "IT",
|
488 |
+
"name_native": "Italiano",
|
489 |
+
"name_english": "Italian",
|
490 |
+
"country_english": "Italy"
|
491 |
+
},
|
492 |
+
"piper_version": "1.0.0"
|
493 |
+
}
|
paola/medium/samples/speaker_0.mp3.wav
ADDED
Binary file (350 kB). View file
|
|