Michael Hansen
commited on
Commit
·
8aaa3c9
1
Parent(s):
97d9931
New voices
Browse files- _script/voicefest.py +4 -0
- cs/cs_CZ/jirka/medium/MODEL_CARD +15 -0
- cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx +3 -0
- cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx.json +508 -0
- de/de_DE/thorsten/high/MODEL_CARD +15 -0
- de/de_DE/thorsten/high/de_DE-thorsten-high.onnx +3 -0
- de/de_DE/thorsten/high/de_DE-thorsten-high.onnx.json +493 -0
- hu/hu_HU/anna/medium/MODEL_CARD +15 -0
- hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx +3 -0
- hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx.json +508 -0
- hu/hu_HU/berta/medium/MODEL_CARD +15 -0
- hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx +3 -0
- hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx.json +502 -0
- pt/pt_PT/tugão/medium/MODEL_CARD +15 -0
- pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx +3 -0
- pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx.json +508 -0
- sk/sk_SK/lili/medium/MODEL_CARD +15 -0
- sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx +3 -0
- sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx.json +502 -0
- tr/tr_TR/fahrettin/medium/MODEL_CARD +15 -0
- tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx +3 -0
- tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx.json +508 -0
- voices.json +210 -0
_script/voicefest.py
CHANGED
@@ -19,6 +19,7 @@ class Language:
|
|
19 |
|
20 |
_LANGUAGES = {
|
21 |
"ca_ES": Language("Català", "Catalan", "Spain"),
|
|
|
22 |
"da_DK": Language("Dansk", "Danish", "Denmark"),
|
23 |
"de_DE": Language("Deutsch", "German", "Germany"),
|
24 |
"el_GR": Language("Ελληνικά", "Greek", "Greece"),
|
@@ -30,6 +31,7 @@ _LANGUAGES = {
|
|
30 |
"fr_FR": Language("Français", "French", "France"),
|
31 |
"is_IS": Language("íslenska", "Icelandic", "Iceland"),
|
32 |
"it_IT": Language("Italiano", "Italian", "Italy"),
|
|
|
33 |
"ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
|
34 |
"kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
|
35 |
"lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
|
@@ -39,8 +41,10 @@ _LANGUAGES = {
|
|
39 |
"no_NO": Language("Norsk", "Norwegian", "Norway"),
|
40 |
"pl_PL": Language("Polski", "Polish", "Poland"),
|
41 |
"pt_BR": Language("Português", "Portuguese", "Brazil"),
|
|
|
42 |
"ro_RO": Language("Română", "Romanian", "Romania"),
|
43 |
"ru_RU": Language("Русский", "Russian", "Russia"),
|
|
|
44 |
"sr_RS": Language("srpski", "Serbian", "Serbia"),
|
45 |
"sv_SE": Language("Svenska", "Swedish", "Sweden"),
|
46 |
"sw_CD": Language("Kiswahili", "Swahili", "Democratic Republic of the Congo"),
|
|
|
19 |
|
20 |
_LANGUAGES = {
|
21 |
"ca_ES": Language("Català", "Catalan", "Spain"),
|
22 |
+
"cs_CZ": Language("Čeština", "Czech", "Czech Republic"),
|
23 |
"da_DK": Language("Dansk", "Danish", "Denmark"),
|
24 |
"de_DE": Language("Deutsch", "German", "Germany"),
|
25 |
"el_GR": Language("Ελληνικά", "Greek", "Greece"),
|
|
|
31 |
"fr_FR": Language("Français", "French", "France"),
|
32 |
"is_IS": Language("íslenska", "Icelandic", "Iceland"),
|
33 |
"it_IT": Language("Italiano", "Italian", "Italy"),
|
34 |
+
"hu_HU": Language("Magyar", "Hungarian", "Hungary"),
|
35 |
"ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
|
36 |
"kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
|
37 |
"lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
|
|
|
41 |
"no_NO": Language("Norsk", "Norwegian", "Norway"),
|
42 |
"pl_PL": Language("Polski", "Polish", "Poland"),
|
43 |
"pt_BR": Language("Português", "Portuguese", "Brazil"),
|
44 |
+
"pt_PT": Language("Português", "Portuguese", "Portugal"),
|
45 |
"ro_RO": Language("Română", "Romanian", "Romania"),
|
46 |
"ru_RU": Language("Русский", "Russian", "Russia"),
|
47 |
+
"sk_SK": Language("Slovenčina", "Slovak", "Slovakia"),
|
48 |
"sr_RS": Language("srpski", "Serbian", "Serbia"),
|
49 |
"sv_SE": Language("Svenska", "Swedish", "Sweden"),
|
50 |
"sw_CD": Language("Kiswahili", "Swahili", "Democratic Republic of the Congo"),
|
cs/cs_CZ/jirka/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for jirka (medium)
|
2 |
+
|
3 |
+
* Language: cs_CZ (Czech, Czech Republic)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbd5c900acacc8e8cbecd64347abb8de39c00a9d3104bed06fee92e4f319efc8
|
3 |
+
size 63201294
|
cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "cs"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̊": [
|
447 |
+
158
|
448 |
+
],
|
449 |
+
"̝": [
|
450 |
+
157
|
451 |
+
],
|
452 |
+
"̧": [
|
453 |
+
140
|
454 |
+
],
|
455 |
+
"̩": [
|
456 |
+
144
|
457 |
+
],
|
458 |
+
"̪": [
|
459 |
+
142
|
460 |
+
],
|
461 |
+
"̯": [
|
462 |
+
143
|
463 |
+
],
|
464 |
+
"̺": [
|
465 |
+
152
|
466 |
+
],
|
467 |
+
"̻": [
|
468 |
+
153
|
469 |
+
],
|
470 |
+
"β": [
|
471 |
+
125
|
472 |
+
],
|
473 |
+
"ε": [
|
474 |
+
147
|
475 |
+
],
|
476 |
+
"θ": [
|
477 |
+
126
|
478 |
+
],
|
479 |
+
"χ": [
|
480 |
+
127
|
481 |
+
],
|
482 |
+
"ᵻ": [
|
483 |
+
128
|
484 |
+
],
|
485 |
+
"↑": [
|
486 |
+
151
|
487 |
+
],
|
488 |
+
"↓": [
|
489 |
+
148
|
490 |
+
],
|
491 |
+
"ⱱ": [
|
492 |
+
129
|
493 |
+
]
|
494 |
+
},
|
495 |
+
"num_symbols": 256,
|
496 |
+
"num_speakers": 1,
|
497 |
+
"speaker_id_map": {},
|
498 |
+
"piper_version": "1.0.0",
|
499 |
+
"language": {
|
500 |
+
"code": "cs_CZ",
|
501 |
+
"family": "cs",
|
502 |
+
"region": "CZ",
|
503 |
+
"name_native": "Čeština",
|
504 |
+
"name_english": "Czech",
|
505 |
+
"country_english": "Czech Republic"
|
506 |
+
},
|
507 |
+
"dataset": "jirka"
|
508 |
+
}
|
de/de_DE/thorsten/high/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for thorsten (high)
|
2 |
+
|
3 |
+
* Language: de_DE (German, Germany)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/thorstenMueller/Thorsten-Voice
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (high quality).
|
de/de_DE/thorsten/high/de_DE-thorsten-high.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9df1c43c61149ef9b39e618e2b861fbe41e1fcea9390b2dac62e8761573ea4f1
|
3 |
+
size 113895201
|
de/de_DE/thorsten/high/de_DE-thorsten-high.onnx.json
ADDED
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "high"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "de"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
"_": [
|
18 |
+
0
|
19 |
+
],
|
20 |
+
"^": [
|
21 |
+
1
|
22 |
+
],
|
23 |
+
"$": [
|
24 |
+
2
|
25 |
+
],
|
26 |
+
" ": [
|
27 |
+
3
|
28 |
+
],
|
29 |
+
"!": [
|
30 |
+
4
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
":": [
|
51 |
+
11
|
52 |
+
],
|
53 |
+
";": [
|
54 |
+
12
|
55 |
+
],
|
56 |
+
"?": [
|
57 |
+
13
|
58 |
+
],
|
59 |
+
"a": [
|
60 |
+
14
|
61 |
+
],
|
62 |
+
"b": [
|
63 |
+
15
|
64 |
+
],
|
65 |
+
"c": [
|
66 |
+
16
|
67 |
+
],
|
68 |
+
"d": [
|
69 |
+
17
|
70 |
+
],
|
71 |
+
"e": [
|
72 |
+
18
|
73 |
+
],
|
74 |
+
"f": [
|
75 |
+
19
|
76 |
+
],
|
77 |
+
"h": [
|
78 |
+
20
|
79 |
+
],
|
80 |
+
"i": [
|
81 |
+
21
|
82 |
+
],
|
83 |
+
"j": [
|
84 |
+
22
|
85 |
+
],
|
86 |
+
"k": [
|
87 |
+
23
|
88 |
+
],
|
89 |
+
"l": [
|
90 |
+
24
|
91 |
+
],
|
92 |
+
"m": [
|
93 |
+
25
|
94 |
+
],
|
95 |
+
"n": [
|
96 |
+
26
|
97 |
+
],
|
98 |
+
"o": [
|
99 |
+
27
|
100 |
+
],
|
101 |
+
"p": [
|
102 |
+
28
|
103 |
+
],
|
104 |
+
"q": [
|
105 |
+
29
|
106 |
+
],
|
107 |
+
"r": [
|
108 |
+
30
|
109 |
+
],
|
110 |
+
"s": [
|
111 |
+
31
|
112 |
+
],
|
113 |
+
"t": [
|
114 |
+
32
|
115 |
+
],
|
116 |
+
"u": [
|
117 |
+
33
|
118 |
+
],
|
119 |
+
"v": [
|
120 |
+
34
|
121 |
+
],
|
122 |
+
"w": [
|
123 |
+
35
|
124 |
+
],
|
125 |
+
"x": [
|
126 |
+
36
|
127 |
+
],
|
128 |
+
"y": [
|
129 |
+
37
|
130 |
+
],
|
131 |
+
"z": [
|
132 |
+
38
|
133 |
+
],
|
134 |
+
"æ": [
|
135 |
+
39
|
136 |
+
],
|
137 |
+
"ç": [
|
138 |
+
40
|
139 |
+
],
|
140 |
+
"ð": [
|
141 |
+
41
|
142 |
+
],
|
143 |
+
"ø": [
|
144 |
+
42
|
145 |
+
],
|
146 |
+
"ħ": [
|
147 |
+
43
|
148 |
+
],
|
149 |
+
"ŋ": [
|
150 |
+
44
|
151 |
+
],
|
152 |
+
"œ": [
|
153 |
+
45
|
154 |
+
],
|
155 |
+
"ǀ": [
|
156 |
+
46
|
157 |
+
],
|
158 |
+
"ǁ": [
|
159 |
+
47
|
160 |
+
],
|
161 |
+
"ǂ": [
|
162 |
+
48
|
163 |
+
],
|
164 |
+
"ǃ": [
|
165 |
+
49
|
166 |
+
],
|
167 |
+
"ɐ": [
|
168 |
+
50
|
169 |
+
],
|
170 |
+
"ɑ": [
|
171 |
+
51
|
172 |
+
],
|
173 |
+
"ɒ": [
|
174 |
+
52
|
175 |
+
],
|
176 |
+
"ɓ": [
|
177 |
+
53
|
178 |
+
],
|
179 |
+
"ɔ": [
|
180 |
+
54
|
181 |
+
],
|
182 |
+
"ɕ": [
|
183 |
+
55
|
184 |
+
],
|
185 |
+
"ɖ": [
|
186 |
+
56
|
187 |
+
],
|
188 |
+
"ɗ": [
|
189 |
+
57
|
190 |
+
],
|
191 |
+
"ɘ": [
|
192 |
+
58
|
193 |
+
],
|
194 |
+
"ə": [
|
195 |
+
59
|
196 |
+
],
|
197 |
+
"ɚ": [
|
198 |
+
60
|
199 |
+
],
|
200 |
+
"ɛ": [
|
201 |
+
61
|
202 |
+
],
|
203 |
+
"ɜ": [
|
204 |
+
62
|
205 |
+
],
|
206 |
+
"ɞ": [
|
207 |
+
63
|
208 |
+
],
|
209 |
+
"ɟ": [
|
210 |
+
64
|
211 |
+
],
|
212 |
+
"ɠ": [
|
213 |
+
65
|
214 |
+
],
|
215 |
+
"ɡ": [
|
216 |
+
66
|
217 |
+
],
|
218 |
+
"ɢ": [
|
219 |
+
67
|
220 |
+
],
|
221 |
+
"ɣ": [
|
222 |
+
68
|
223 |
+
],
|
224 |
+
"ɤ": [
|
225 |
+
69
|
226 |
+
],
|
227 |
+
"ɥ": [
|
228 |
+
70
|
229 |
+
],
|
230 |
+
"ɦ": [
|
231 |
+
71
|
232 |
+
],
|
233 |
+
"ɧ": [
|
234 |
+
72
|
235 |
+
],
|
236 |
+
"ɨ": [
|
237 |
+
73
|
238 |
+
],
|
239 |
+
"ɪ": [
|
240 |
+
74
|
241 |
+
],
|
242 |
+
"ɫ": [
|
243 |
+
75
|
244 |
+
],
|
245 |
+
"ɬ": [
|
246 |
+
76
|
247 |
+
],
|
248 |
+
"ɭ": [
|
249 |
+
77
|
250 |
+
],
|
251 |
+
"ɮ": [
|
252 |
+
78
|
253 |
+
],
|
254 |
+
"ɯ": [
|
255 |
+
79
|
256 |
+
],
|
257 |
+
"ɰ": [
|
258 |
+
80
|
259 |
+
],
|
260 |
+
"ɱ": [
|
261 |
+
81
|
262 |
+
],
|
263 |
+
"ɲ": [
|
264 |
+
82
|
265 |
+
],
|
266 |
+
"ɳ": [
|
267 |
+
83
|
268 |
+
],
|
269 |
+
"ɴ": [
|
270 |
+
84
|
271 |
+
],
|
272 |
+
"ɵ": [
|
273 |
+
85
|
274 |
+
],
|
275 |
+
"ɶ": [
|
276 |
+
86
|
277 |
+
],
|
278 |
+
"ɸ": [
|
279 |
+
87
|
280 |
+
],
|
281 |
+
"ɹ": [
|
282 |
+
88
|
283 |
+
],
|
284 |
+
"ɺ": [
|
285 |
+
89
|
286 |
+
],
|
287 |
+
"ɻ": [
|
288 |
+
90
|
289 |
+
],
|
290 |
+
"ɽ": [
|
291 |
+
91
|
292 |
+
],
|
293 |
+
"ɾ": [
|
294 |
+
92
|
295 |
+
],
|
296 |
+
"ʀ": [
|
297 |
+
93
|
298 |
+
],
|
299 |
+
"ʁ": [
|
300 |
+
94
|
301 |
+
],
|
302 |
+
"ʂ": [
|
303 |
+
95
|
304 |
+
],
|
305 |
+
"ʃ": [
|
306 |
+
96
|
307 |
+
],
|
308 |
+
"ʄ": [
|
309 |
+
97
|
310 |
+
],
|
311 |
+
"ʈ": [
|
312 |
+
98
|
313 |
+
],
|
314 |
+
"ʉ": [
|
315 |
+
99
|
316 |
+
],
|
317 |
+
"ʊ": [
|
318 |
+
100
|
319 |
+
],
|
320 |
+
"ʋ": [
|
321 |
+
101
|
322 |
+
],
|
323 |
+
"ʌ": [
|
324 |
+
102
|
325 |
+
],
|
326 |
+
"ʍ": [
|
327 |
+
103
|
328 |
+
],
|
329 |
+
"ʎ": [
|
330 |
+
104
|
331 |
+
],
|
332 |
+
"ʏ": [
|
333 |
+
105
|
334 |
+
],
|
335 |
+
"ʐ": [
|
336 |
+
106
|
337 |
+
],
|
338 |
+
"ʑ": [
|
339 |
+
107
|
340 |
+
],
|
341 |
+
"ʒ": [
|
342 |
+
108
|
343 |
+
],
|
344 |
+
"ʔ": [
|
345 |
+
109
|
346 |
+
],
|
347 |
+
"ʕ": [
|
348 |
+
110
|
349 |
+
],
|
350 |
+
"ʘ": [
|
351 |
+
111
|
352 |
+
],
|
353 |
+
"ʙ": [
|
354 |
+
112
|
355 |
+
],
|
356 |
+
"ʛ": [
|
357 |
+
113
|
358 |
+
],
|
359 |
+
"ʜ": [
|
360 |
+
114
|
361 |
+
],
|
362 |
+
"ʝ": [
|
363 |
+
115
|
364 |
+
],
|
365 |
+
"ʟ": [
|
366 |
+
116
|
367 |
+
],
|
368 |
+
"ʡ": [
|
369 |
+
117
|
370 |
+
],
|
371 |
+
"ʢ": [
|
372 |
+
118
|
373 |
+
],
|
374 |
+
"ʲ": [
|
375 |
+
119
|
376 |
+
],
|
377 |
+
"ˈ": [
|
378 |
+
120
|
379 |
+
],
|
380 |
+
"ˌ": [
|
381 |
+
121
|
382 |
+
],
|
383 |
+
"ː": [
|
384 |
+
122
|
385 |
+
],
|
386 |
+
"ˑ": [
|
387 |
+
123
|
388 |
+
],
|
389 |
+
"˞": [
|
390 |
+
124
|
391 |
+
],
|
392 |
+
"β": [
|
393 |
+
125
|
394 |
+
],
|
395 |
+
"θ": [
|
396 |
+
126
|
397 |
+
],
|
398 |
+
"χ": [
|
399 |
+
127
|
400 |
+
],
|
401 |
+
"ᵻ": [
|
402 |
+
128
|
403 |
+
],
|
404 |
+
"ⱱ": [
|
405 |
+
129
|
406 |
+
],
|
407 |
+
"0": [
|
408 |
+
130
|
409 |
+
],
|
410 |
+
"1": [
|
411 |
+
131
|
412 |
+
],
|
413 |
+
"2": [
|
414 |
+
132
|
415 |
+
],
|
416 |
+
"3": [
|
417 |
+
133
|
418 |
+
],
|
419 |
+
"4": [
|
420 |
+
134
|
421 |
+
],
|
422 |
+
"5": [
|
423 |
+
135
|
424 |
+
],
|
425 |
+
"6": [
|
426 |
+
136
|
427 |
+
],
|
428 |
+
"7": [
|
429 |
+
137
|
430 |
+
],
|
431 |
+
"8": [
|
432 |
+
138
|
433 |
+
],
|
434 |
+
"9": [
|
435 |
+
139
|
436 |
+
],
|
437 |
+
"̧": [
|
438 |
+
140
|
439 |
+
],
|
440 |
+
"̃": [
|
441 |
+
141
|
442 |
+
],
|
443 |
+
"̪": [
|
444 |
+
142
|
445 |
+
],
|
446 |
+
"̯": [
|
447 |
+
143
|
448 |
+
],
|
449 |
+
"̩": [
|
450 |
+
144
|
451 |
+
],
|
452 |
+
"ʰ": [
|
453 |
+
145
|
454 |
+
],
|
455 |
+
"ˤ": [
|
456 |
+
146
|
457 |
+
],
|
458 |
+
"ε": [
|
459 |
+
147
|
460 |
+
],
|
461 |
+
"↓": [
|
462 |
+
148
|
463 |
+
],
|
464 |
+
"#": [
|
465 |
+
149
|
466 |
+
],
|
467 |
+
"\"": [
|
468 |
+
150
|
469 |
+
],
|
470 |
+
"↑": [
|
471 |
+
151
|
472 |
+
],
|
473 |
+
"̺": [
|
474 |
+
152
|
475 |
+
],
|
476 |
+
"̻": [
|
477 |
+
153
|
478 |
+
]
|
479 |
+
},
|
480 |
+
"num_symbols": 256,
|
481 |
+
"num_speakers": 1,
|
482 |
+
"speaker_id_map": {},
|
483 |
+
"piper_version": "1.0.0",
|
484 |
+
"language": {
|
485 |
+
"code": "de_DE",
|
486 |
+
"family": "de",
|
487 |
+
"region": "DE",
|
488 |
+
"name_native": "Deutsch",
|
489 |
+
"name_english": "German",
|
490 |
+
"country_english": "Germany"
|
491 |
+
},
|
492 |
+
"dataset": "thorsten"
|
493 |
+
}
|
hu/hu_HU/anna/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for anna (medium)
|
2 |
+
|
3 |
+
* Language: hu_HU (Hungarian, Hungary)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:968c0c3a66cb667811242cc88653bff9247395fc7a0517fbeef7d8c08cdae62a
|
3 |
+
size 63201294
|
hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "hu"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̊": [
|
447 |
+
158
|
448 |
+
],
|
449 |
+
"̝": [
|
450 |
+
157
|
451 |
+
],
|
452 |
+
"̧": [
|
453 |
+
140
|
454 |
+
],
|
455 |
+
"̩": [
|
456 |
+
144
|
457 |
+
],
|
458 |
+
"̪": [
|
459 |
+
142
|
460 |
+
],
|
461 |
+
"̯": [
|
462 |
+
143
|
463 |
+
],
|
464 |
+
"̺": [
|
465 |
+
152
|
466 |
+
],
|
467 |
+
"̻": [
|
468 |
+
153
|
469 |
+
],
|
470 |
+
"β": [
|
471 |
+
125
|
472 |
+
],
|
473 |
+
"ε": [
|
474 |
+
147
|
475 |
+
],
|
476 |
+
"θ": [
|
477 |
+
126
|
478 |
+
],
|
479 |
+
"χ": [
|
480 |
+
127
|
481 |
+
],
|
482 |
+
"ᵻ": [
|
483 |
+
128
|
484 |
+
],
|
485 |
+
"↑": [
|
486 |
+
151
|
487 |
+
],
|
488 |
+
"↓": [
|
489 |
+
148
|
490 |
+
],
|
491 |
+
"ⱱ": [
|
492 |
+
129
|
493 |
+
]
|
494 |
+
},
|
495 |
+
"num_symbols": 256,
|
496 |
+
"num_speakers": 1,
|
497 |
+
"speaker_id_map": {},
|
498 |
+
"piper_version": "1.0.0",
|
499 |
+
"language": {
|
500 |
+
"code": "hu_HU",
|
501 |
+
"family": "hu",
|
502 |
+
"region": "HU",
|
503 |
+
"name_native": "Magyar",
|
504 |
+
"name_english": "Hungarian",
|
505 |
+
"country_english": "Hungary"
|
506 |
+
},
|
507 |
+
"dataset": "anna"
|
508 |
+
}
|
hu/hu_HU/berta/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for berta (medium)
|
2 |
+
|
3 |
+
* Language: hu_HU (Hungarian, Hungary)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eed05f767573b77fd2c07e6bccaa9b3c77089a55b9239c3099ecd3d17a59be3
|
3 |
+
size 63201294
|
hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx.json
ADDED
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "hu"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̧": [
|
447 |
+
140
|
448 |
+
],
|
449 |
+
"̩": [
|
450 |
+
144
|
451 |
+
],
|
452 |
+
"̪": [
|
453 |
+
142
|
454 |
+
],
|
455 |
+
"̯": [
|
456 |
+
143
|
457 |
+
],
|
458 |
+
"̺": [
|
459 |
+
152
|
460 |
+
],
|
461 |
+
"̻": [
|
462 |
+
153
|
463 |
+
],
|
464 |
+
"β": [
|
465 |
+
125
|
466 |
+
],
|
467 |
+
"ε": [
|
468 |
+
147
|
469 |
+
],
|
470 |
+
"θ": [
|
471 |
+
126
|
472 |
+
],
|
473 |
+
"χ": [
|
474 |
+
127
|
475 |
+
],
|
476 |
+
"ᵻ": [
|
477 |
+
128
|
478 |
+
],
|
479 |
+
"↑": [
|
480 |
+
151
|
481 |
+
],
|
482 |
+
"↓": [
|
483 |
+
148
|
484 |
+
],
|
485 |
+
"ⱱ": [
|
486 |
+
129
|
487 |
+
]
|
488 |
+
},
|
489 |
+
"num_symbols": 256,
|
490 |
+
"num_speakers": 1,
|
491 |
+
"speaker_id_map": {},
|
492 |
+
"piper_version": "1.0.0",
|
493 |
+
"language": {
|
494 |
+
"code": "hu_HU",
|
495 |
+
"family": "hu",
|
496 |
+
"region": "HU",
|
497 |
+
"name_native": "Magyar",
|
498 |
+
"name_english": "Hungarian",
|
499 |
+
"country_english": "Hungary"
|
500 |
+
},
|
501 |
+
"dataset": "berta"
|
502 |
+
}
|
pt/pt_PT/tugão/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for tugão (medium)
|
2 |
+
|
3 |
+
* Language: pt_PT (Portuguese, Portugal)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:223a7aaca69a155c61897e8ada7c3b13bc306e16c72dbb9c2fed733e2b0927d4
|
3 |
+
size 63201294
|
pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "pt"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̊": [
|
447 |
+
158
|
448 |
+
],
|
449 |
+
"̝": [
|
450 |
+
157
|
451 |
+
],
|
452 |
+
"̧": [
|
453 |
+
140
|
454 |
+
],
|
455 |
+
"̩": [
|
456 |
+
144
|
457 |
+
],
|
458 |
+
"̪": [
|
459 |
+
142
|
460 |
+
],
|
461 |
+
"̯": [
|
462 |
+
143
|
463 |
+
],
|
464 |
+
"̺": [
|
465 |
+
152
|
466 |
+
],
|
467 |
+
"̻": [
|
468 |
+
153
|
469 |
+
],
|
470 |
+
"β": [
|
471 |
+
125
|
472 |
+
],
|
473 |
+
"ε": [
|
474 |
+
147
|
475 |
+
],
|
476 |
+
"θ": [
|
477 |
+
126
|
478 |
+
],
|
479 |
+
"χ": [
|
480 |
+
127
|
481 |
+
],
|
482 |
+
"ᵻ": [
|
483 |
+
128
|
484 |
+
],
|
485 |
+
"↑": [
|
486 |
+
151
|
487 |
+
],
|
488 |
+
"↓": [
|
489 |
+
148
|
490 |
+
],
|
491 |
+
"ⱱ": [
|
492 |
+
129
|
493 |
+
]
|
494 |
+
},
|
495 |
+
"num_symbols": 256,
|
496 |
+
"num_speakers": 1,
|
497 |
+
"speaker_id_map": {},
|
498 |
+
"piper_version": "1.0.0",
|
499 |
+
"language": {
|
500 |
+
"code": "pt_PT",
|
501 |
+
"family": "pt",
|
502 |
+
"region": "PT",
|
503 |
+
"name_native": "Português",
|
504 |
+
"name_english": "Portuguese",
|
505 |
+
"country_english": "Portugal"
|
506 |
+
},
|
507 |
+
"dataset": "tugão"
|
508 |
+
}
|
sk/sk_SK/lili/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for lili (medium)
|
2 |
+
|
3 |
+
* Language: sk_SK (Slovak, Slovakia)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8e21603e0165252849efe0bcb3fbffd1b3193c36bd1f556e1106911e8015526
|
3 |
+
size 63201294
|
sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx.json
ADDED
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "sk"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̧": [
|
447 |
+
140
|
448 |
+
],
|
449 |
+
"̩": [
|
450 |
+
144
|
451 |
+
],
|
452 |
+
"̪": [
|
453 |
+
142
|
454 |
+
],
|
455 |
+
"̯": [
|
456 |
+
143
|
457 |
+
],
|
458 |
+
"̺": [
|
459 |
+
152
|
460 |
+
],
|
461 |
+
"̻": [
|
462 |
+
153
|
463 |
+
],
|
464 |
+
"β": [
|
465 |
+
125
|
466 |
+
],
|
467 |
+
"ε": [
|
468 |
+
147
|
469 |
+
],
|
470 |
+
"θ": [
|
471 |
+
126
|
472 |
+
],
|
473 |
+
"χ": [
|
474 |
+
127
|
475 |
+
],
|
476 |
+
"ᵻ": [
|
477 |
+
128
|
478 |
+
],
|
479 |
+
"↑": [
|
480 |
+
151
|
481 |
+
],
|
482 |
+
"↓": [
|
483 |
+
148
|
484 |
+
],
|
485 |
+
"ⱱ": [
|
486 |
+
129
|
487 |
+
]
|
488 |
+
},
|
489 |
+
"num_symbols": 256,
|
490 |
+
"num_speakers": 1,
|
491 |
+
"speaker_id_map": {},
|
492 |
+
"piper_version": "1.0.0",
|
493 |
+
"language": {
|
494 |
+
"code": "sk_SK",
|
495 |
+
"family": "sk",
|
496 |
+
"region": "SK",
|
497 |
+
"name_native": "Slovenčina",
|
498 |
+
"name_english": "Slovak",
|
499 |
+
"country_english": "Slovakia"
|
500 |
+
},
|
501 |
+
"dataset": "lili"
|
502 |
+
}
|
tr/tr_TR/fahrettin/medium/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for fahrettin (medium)
|
2 |
+
|
3 |
+
* Language: tr_TR (Turkish, Turkey)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
11 |
+
* License: CC0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39081c47270180e8a0dfac69b07bf329fb6d039fcc1279dbe26c2daf2848b190
|
3 |
+
size 63201294
|
tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "tr"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
" ": [
|
18 |
+
3
|
19 |
+
],
|
20 |
+
"!": [
|
21 |
+
4
|
22 |
+
],
|
23 |
+
"\"": [
|
24 |
+
150
|
25 |
+
],
|
26 |
+
"#": [
|
27 |
+
149
|
28 |
+
],
|
29 |
+
"$": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
"0": [
|
51 |
+
130
|
52 |
+
],
|
53 |
+
"1": [
|
54 |
+
131
|
55 |
+
],
|
56 |
+
"2": [
|
57 |
+
132
|
58 |
+
],
|
59 |
+
"3": [
|
60 |
+
133
|
61 |
+
],
|
62 |
+
"4": [
|
63 |
+
134
|
64 |
+
],
|
65 |
+
"5": [
|
66 |
+
135
|
67 |
+
],
|
68 |
+
"6": [
|
69 |
+
136
|
70 |
+
],
|
71 |
+
"7": [
|
72 |
+
137
|
73 |
+
],
|
74 |
+
"8": [
|
75 |
+
138
|
76 |
+
],
|
77 |
+
"9": [
|
78 |
+
139
|
79 |
+
],
|
80 |
+
":": [
|
81 |
+
11
|
82 |
+
],
|
83 |
+
";": [
|
84 |
+
12
|
85 |
+
],
|
86 |
+
"?": [
|
87 |
+
13
|
88 |
+
],
|
89 |
+
"X": [
|
90 |
+
156
|
91 |
+
],
|
92 |
+
"^": [
|
93 |
+
1
|
94 |
+
],
|
95 |
+
"_": [
|
96 |
+
0
|
97 |
+
],
|
98 |
+
"a": [
|
99 |
+
14
|
100 |
+
],
|
101 |
+
"b": [
|
102 |
+
15
|
103 |
+
],
|
104 |
+
"c": [
|
105 |
+
16
|
106 |
+
],
|
107 |
+
"d": [
|
108 |
+
17
|
109 |
+
],
|
110 |
+
"e": [
|
111 |
+
18
|
112 |
+
],
|
113 |
+
"f": [
|
114 |
+
19
|
115 |
+
],
|
116 |
+
"g": [
|
117 |
+
154
|
118 |
+
],
|
119 |
+
"h": [
|
120 |
+
20
|
121 |
+
],
|
122 |
+
"i": [
|
123 |
+
21
|
124 |
+
],
|
125 |
+
"j": [
|
126 |
+
22
|
127 |
+
],
|
128 |
+
"k": [
|
129 |
+
23
|
130 |
+
],
|
131 |
+
"l": [
|
132 |
+
24
|
133 |
+
],
|
134 |
+
"m": [
|
135 |
+
25
|
136 |
+
],
|
137 |
+
"n": [
|
138 |
+
26
|
139 |
+
],
|
140 |
+
"o": [
|
141 |
+
27
|
142 |
+
],
|
143 |
+
"p": [
|
144 |
+
28
|
145 |
+
],
|
146 |
+
"q": [
|
147 |
+
29
|
148 |
+
],
|
149 |
+
"r": [
|
150 |
+
30
|
151 |
+
],
|
152 |
+
"s": [
|
153 |
+
31
|
154 |
+
],
|
155 |
+
"t": [
|
156 |
+
32
|
157 |
+
],
|
158 |
+
"u": [
|
159 |
+
33
|
160 |
+
],
|
161 |
+
"v": [
|
162 |
+
34
|
163 |
+
],
|
164 |
+
"w": [
|
165 |
+
35
|
166 |
+
],
|
167 |
+
"x": [
|
168 |
+
36
|
169 |
+
],
|
170 |
+
"y": [
|
171 |
+
37
|
172 |
+
],
|
173 |
+
"z": [
|
174 |
+
38
|
175 |
+
],
|
176 |
+
"æ": [
|
177 |
+
39
|
178 |
+
],
|
179 |
+
"ç": [
|
180 |
+
40
|
181 |
+
],
|
182 |
+
"ð": [
|
183 |
+
41
|
184 |
+
],
|
185 |
+
"ø": [
|
186 |
+
42
|
187 |
+
],
|
188 |
+
"ħ": [
|
189 |
+
43
|
190 |
+
],
|
191 |
+
"ŋ": [
|
192 |
+
44
|
193 |
+
],
|
194 |
+
"œ": [
|
195 |
+
45
|
196 |
+
],
|
197 |
+
"ǀ": [
|
198 |
+
46
|
199 |
+
],
|
200 |
+
"ǁ": [
|
201 |
+
47
|
202 |
+
],
|
203 |
+
"ǂ": [
|
204 |
+
48
|
205 |
+
],
|
206 |
+
"ǃ": [
|
207 |
+
49
|
208 |
+
],
|
209 |
+
"ɐ": [
|
210 |
+
50
|
211 |
+
],
|
212 |
+
"ɑ": [
|
213 |
+
51
|
214 |
+
],
|
215 |
+
"ɒ": [
|
216 |
+
52
|
217 |
+
],
|
218 |
+
"ɓ": [
|
219 |
+
53
|
220 |
+
],
|
221 |
+
"ɔ": [
|
222 |
+
54
|
223 |
+
],
|
224 |
+
"ɕ": [
|
225 |
+
55
|
226 |
+
],
|
227 |
+
"ɖ": [
|
228 |
+
56
|
229 |
+
],
|
230 |
+
"ɗ": [
|
231 |
+
57
|
232 |
+
],
|
233 |
+
"ɘ": [
|
234 |
+
58
|
235 |
+
],
|
236 |
+
"ə": [
|
237 |
+
59
|
238 |
+
],
|
239 |
+
"ɚ": [
|
240 |
+
60
|
241 |
+
],
|
242 |
+
"ɛ": [
|
243 |
+
61
|
244 |
+
],
|
245 |
+
"ɜ": [
|
246 |
+
62
|
247 |
+
],
|
248 |
+
"ɞ": [
|
249 |
+
63
|
250 |
+
],
|
251 |
+
"ɟ": [
|
252 |
+
64
|
253 |
+
],
|
254 |
+
"ɠ": [
|
255 |
+
65
|
256 |
+
],
|
257 |
+
"ɡ": [
|
258 |
+
66
|
259 |
+
],
|
260 |
+
"ɢ": [
|
261 |
+
67
|
262 |
+
],
|
263 |
+
"ɣ": [
|
264 |
+
68
|
265 |
+
],
|
266 |
+
"ɤ": [
|
267 |
+
69
|
268 |
+
],
|
269 |
+
"ɥ": [
|
270 |
+
70
|
271 |
+
],
|
272 |
+
"ɦ": [
|
273 |
+
71
|
274 |
+
],
|
275 |
+
"ɧ": [
|
276 |
+
72
|
277 |
+
],
|
278 |
+
"ɨ": [
|
279 |
+
73
|
280 |
+
],
|
281 |
+
"ɪ": [
|
282 |
+
74
|
283 |
+
],
|
284 |
+
"ɫ": [
|
285 |
+
75
|
286 |
+
],
|
287 |
+
"ɬ": [
|
288 |
+
76
|
289 |
+
],
|
290 |
+
"ɭ": [
|
291 |
+
77
|
292 |
+
],
|
293 |
+
"ɮ": [
|
294 |
+
78
|
295 |
+
],
|
296 |
+
"ɯ": [
|
297 |
+
79
|
298 |
+
],
|
299 |
+
"ɰ": [
|
300 |
+
80
|
301 |
+
],
|
302 |
+
"ɱ": [
|
303 |
+
81
|
304 |
+
],
|
305 |
+
"ɲ": [
|
306 |
+
82
|
307 |
+
],
|
308 |
+
"ɳ": [
|
309 |
+
83
|
310 |
+
],
|
311 |
+
"ɴ": [
|
312 |
+
84
|
313 |
+
],
|
314 |
+
"ɵ": [
|
315 |
+
85
|
316 |
+
],
|
317 |
+
"ɶ": [
|
318 |
+
86
|
319 |
+
],
|
320 |
+
"ɸ": [
|
321 |
+
87
|
322 |
+
],
|
323 |
+
"ɹ": [
|
324 |
+
88
|
325 |
+
],
|
326 |
+
"ɺ": [
|
327 |
+
89
|
328 |
+
],
|
329 |
+
"ɻ": [
|
330 |
+
90
|
331 |
+
],
|
332 |
+
"ɽ": [
|
333 |
+
91
|
334 |
+
],
|
335 |
+
"ɾ": [
|
336 |
+
92
|
337 |
+
],
|
338 |
+
"ʀ": [
|
339 |
+
93
|
340 |
+
],
|
341 |
+
"ʁ": [
|
342 |
+
94
|
343 |
+
],
|
344 |
+
"ʂ": [
|
345 |
+
95
|
346 |
+
],
|
347 |
+
"ʃ": [
|
348 |
+
96
|
349 |
+
],
|
350 |
+
"ʄ": [
|
351 |
+
97
|
352 |
+
],
|
353 |
+
"ʈ": [
|
354 |
+
98
|
355 |
+
],
|
356 |
+
"ʉ": [
|
357 |
+
99
|
358 |
+
],
|
359 |
+
"ʊ": [
|
360 |
+
100
|
361 |
+
],
|
362 |
+
"ʋ": [
|
363 |
+
101
|
364 |
+
],
|
365 |
+
"ʌ": [
|
366 |
+
102
|
367 |
+
],
|
368 |
+
"ʍ": [
|
369 |
+
103
|
370 |
+
],
|
371 |
+
"ʎ": [
|
372 |
+
104
|
373 |
+
],
|
374 |
+
"ʏ": [
|
375 |
+
105
|
376 |
+
],
|
377 |
+
"ʐ": [
|
378 |
+
106
|
379 |
+
],
|
380 |
+
"ʑ": [
|
381 |
+
107
|
382 |
+
],
|
383 |
+
"ʒ": [
|
384 |
+
108
|
385 |
+
],
|
386 |
+
"ʔ": [
|
387 |
+
109
|
388 |
+
],
|
389 |
+
"ʕ": [
|
390 |
+
110
|
391 |
+
],
|
392 |
+
"ʘ": [
|
393 |
+
111
|
394 |
+
],
|
395 |
+
"ʙ": [
|
396 |
+
112
|
397 |
+
],
|
398 |
+
"ʛ": [
|
399 |
+
113
|
400 |
+
],
|
401 |
+
"ʜ": [
|
402 |
+
114
|
403 |
+
],
|
404 |
+
"ʝ": [
|
405 |
+
115
|
406 |
+
],
|
407 |
+
"ʟ": [
|
408 |
+
116
|
409 |
+
],
|
410 |
+
"ʡ": [
|
411 |
+
117
|
412 |
+
],
|
413 |
+
"ʢ": [
|
414 |
+
118
|
415 |
+
],
|
416 |
+
"ʦ": [
|
417 |
+
155
|
418 |
+
],
|
419 |
+
"ʰ": [
|
420 |
+
145
|
421 |
+
],
|
422 |
+
"ʲ": [
|
423 |
+
119
|
424 |
+
],
|
425 |
+
"ˈ": [
|
426 |
+
120
|
427 |
+
],
|
428 |
+
"ˌ": [
|
429 |
+
121
|
430 |
+
],
|
431 |
+
"ː": [
|
432 |
+
122
|
433 |
+
],
|
434 |
+
"ˑ": [
|
435 |
+
123
|
436 |
+
],
|
437 |
+
"˞": [
|
438 |
+
124
|
439 |
+
],
|
440 |
+
"ˤ": [
|
441 |
+
146
|
442 |
+
],
|
443 |
+
"̃": [
|
444 |
+
141
|
445 |
+
],
|
446 |
+
"̊": [
|
447 |
+
158
|
448 |
+
],
|
449 |
+
"̝": [
|
450 |
+
157
|
451 |
+
],
|
452 |
+
"̧": [
|
453 |
+
140
|
454 |
+
],
|
455 |
+
"̩": [
|
456 |
+
144
|
457 |
+
],
|
458 |
+
"̪": [
|
459 |
+
142
|
460 |
+
],
|
461 |
+
"̯": [
|
462 |
+
143
|
463 |
+
],
|
464 |
+
"̺": [
|
465 |
+
152
|
466 |
+
],
|
467 |
+
"̻": [
|
468 |
+
153
|
469 |
+
],
|
470 |
+
"β": [
|
471 |
+
125
|
472 |
+
],
|
473 |
+
"ε": [
|
474 |
+
147
|
475 |
+
],
|
476 |
+
"θ": [
|
477 |
+
126
|
478 |
+
],
|
479 |
+
"χ": [
|
480 |
+
127
|
481 |
+
],
|
482 |
+
"ᵻ": [
|
483 |
+
128
|
484 |
+
],
|
485 |
+
"↑": [
|
486 |
+
151
|
487 |
+
],
|
488 |
+
"↓": [
|
489 |
+
148
|
490 |
+
],
|
491 |
+
"ⱱ": [
|
492 |
+
129
|
493 |
+
]
|
494 |
+
},
|
495 |
+
"num_symbols": 256,
|
496 |
+
"num_speakers": 1,
|
497 |
+
"speaker_id_map": {},
|
498 |
+
"piper_version": "1.0.0",
|
499 |
+
"language": {
|
500 |
+
"code": "tr_TR",
|
501 |
+
"family": "tr",
|
502 |
+
"region": "TR",
|
503 |
+
"name_native": "Türkçe",
|
504 |
+
"name_english": "Turkish",
|
505 |
+
"country_english": "Turkey"
|
506 |
+
},
|
507 |
+
"dataset": "fahrettin"
|
508 |
+
}
|
voices.json
CHANGED
@@ -93,6 +93,36 @@
|
|
93 |
"ca-upc_pau-x-low"
|
94 |
]
|
95 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
"da_DK-talesyntese-medium": {
|
97 |
"key": "da_DK-talesyntese-medium",
|
98 |
"name": "talesyntese",
|
@@ -285,6 +315,36 @@
|
|
285 |
"de-ramona-low"
|
286 |
]
|
287 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
288 |
"de_DE-thorsten-low": {
|
289 |
"key": "de_DE-thorsten-low",
|
290 |
"name": "thorsten",
|
@@ -2645,6 +2705,66 @@
|
|
2645 |
},
|
2646 |
"aliases": []
|
2647 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2648 |
"is_IS-bui-medium": {
|
2649 |
"key": "is_IS-bui-medium",
|
2650 |
"name": "bui",
|
@@ -3446,6 +3566,36 @@
|
|
3446 |
},
|
3447 |
"aliases": []
|
3448 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3449 |
"ro_RO-mihai-medium": {
|
3450 |
"key": "ro_RO-mihai-medium",
|
3451 |
"name": "mihai",
|
@@ -3598,6 +3748,36 @@
|
|
3598 |
},
|
3599 |
"aliases": []
|
3600 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3601 |
"sr_RS-serbski_institut-medium": {
|
3602 |
"key": "sr_RS-serbski_institut-medium",
|
3603 |
"name": "serbski_institut",
|
@@ -3721,6 +3901,36 @@
|
|
3721 |
},
|
3722 |
"aliases": []
|
3723 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3724 |
"uk_UA-lada-x_low": {
|
3725 |
"key": "uk_UA-lada-x_low",
|
3726 |
"name": "lada",
|
|
|
93 |
"ca-upc_pau-x-low"
|
94 |
]
|
95 |
},
|
96 |
+
"cs_CZ-jirka-medium": {
|
97 |
+
"key": "cs_CZ-jirka-medium",
|
98 |
+
"name": "jirka",
|
99 |
+
"language": {
|
100 |
+
"code": "cs_CZ",
|
101 |
+
"family": "cs",
|
102 |
+
"region": "CZ",
|
103 |
+
"name_native": "Čeština",
|
104 |
+
"name_english": "Czech",
|
105 |
+
"country_english": "Czech Republic"
|
106 |
+
},
|
107 |
+
"quality": "medium",
|
108 |
+
"num_speakers": 1,
|
109 |
+
"speaker_id_map": {},
|
110 |
+
"files": {
|
111 |
+
"cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx": {
|
112 |
+
"size_bytes": 63201294,
|
113 |
+
"md5_digest": "da2deb0a3f93226a3f9b6e40d43c46ca"
|
114 |
+
},
|
115 |
+
"cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx.json": {
|
116 |
+
"size_bytes": 5025,
|
117 |
+
"md5_digest": "2762e45c5b084694093c683a5da7cf94"
|
118 |
+
},
|
119 |
+
"cs/cs_CZ/jirka/medium/MODEL_CARD": {
|
120 |
+
"size_bytes": 281,
|
121 |
+
"md5_digest": "85a220211eadd9b89f3dc023d82966b4"
|
122 |
+
}
|
123 |
+
},
|
124 |
+
"aliases": []
|
125 |
+
},
|
126 |
"da_DK-talesyntese-medium": {
|
127 |
"key": "da_DK-talesyntese-medium",
|
128 |
"name": "talesyntese",
|
|
|
315 |
"de-ramona-low"
|
316 |
]
|
317 |
},
|
318 |
+
"de_DE-thorsten-high": {
|
319 |
+
"key": "de_DE-thorsten-high",
|
320 |
+
"name": "thorsten",
|
321 |
+
"language": {
|
322 |
+
"code": "de_DE",
|
323 |
+
"family": "de",
|
324 |
+
"region": "DE",
|
325 |
+
"name_native": "Deutsch",
|
326 |
+
"name_english": "German",
|
327 |
+
"country_english": "Germany"
|
328 |
+
},
|
329 |
+
"quality": "high",
|
330 |
+
"num_speakers": 1,
|
331 |
+
"speaker_id_map": {},
|
332 |
+
"files": {
|
333 |
+
"de/de_DE/thorsten/high/de_DE-thorsten-high.onnx": {
|
334 |
+
"size_bytes": 113895201,
|
335 |
+
"md5_digest": "256505fe58fb8b9d6ed78b83f6b8a9d2"
|
336 |
+
},
|
337 |
+
"de/de_DE/thorsten/high/de_DE-thorsten-high.onnx.json": {
|
338 |
+
"size_bytes": 4875,
|
339 |
+
"md5_digest": "e81686e00a9d825e2488ead660bec6fd"
|
340 |
+
},
|
341 |
+
"de/de_DE/thorsten/high/MODEL_CARD": {
|
342 |
+
"size_bytes": 281,
|
343 |
+
"md5_digest": "582a051328d56a564e8a38c9029ae630"
|
344 |
+
}
|
345 |
+
},
|
346 |
+
"aliases": []
|
347 |
+
},
|
348 |
"de_DE-thorsten-low": {
|
349 |
"key": "de_DE-thorsten-low",
|
350 |
"name": "thorsten",
|
|
|
2705 |
},
|
2706 |
"aliases": []
|
2707 |
},
|
2708 |
+
"hu_HU-anna-medium": {
|
2709 |
+
"key": "hu_HU-anna-medium",
|
2710 |
+
"name": "anna",
|
2711 |
+
"language": {
|
2712 |
+
"code": "hu_HU",
|
2713 |
+
"family": "hu",
|
2714 |
+
"region": "HU",
|
2715 |
+
"name_native": "Magyar",
|
2716 |
+
"name_english": "Hungarian",
|
2717 |
+
"country_english": "Hungary"
|
2718 |
+
},
|
2719 |
+
"quality": "medium",
|
2720 |
+
"num_speakers": 1,
|
2721 |
+
"speaker_id_map": {},
|
2722 |
+
"files": {
|
2723 |
+
"hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx": {
|
2724 |
+
"size_bytes": 63201294,
|
2725 |
+
"md5_digest": "3796f9fa28bd8d390d17828e2e2e952d"
|
2726 |
+
},
|
2727 |
+
"hu/hu_HU/anna/medium/hu_HU-anna-medium.onnx.json": {
|
2728 |
+
"size_bytes": 5018,
|
2729 |
+
"md5_digest": "ae63867e2c2cb6695555a17bdee8b751"
|
2730 |
+
},
|
2731 |
+
"hu/hu_HU/anna/medium/MODEL_CARD": {
|
2732 |
+
"size_bytes": 277,
|
2733 |
+
"md5_digest": "1a1332b041bc211d4d14fbd93eff03e9"
|
2734 |
+
}
|
2735 |
+
},
|
2736 |
+
"aliases": []
|
2737 |
+
},
|
2738 |
+
"hu_HU-berta-medium": {
|
2739 |
+
"key": "hu_HU-berta-medium",
|
2740 |
+
"name": "berta",
|
2741 |
+
"language": {
|
2742 |
+
"code": "hu_HU",
|
2743 |
+
"family": "hu",
|
2744 |
+
"region": "HU",
|
2745 |
+
"name_native": "Magyar",
|
2746 |
+
"name_english": "Hungarian",
|
2747 |
+
"country_english": "Hungary"
|
2748 |
+
},
|
2749 |
+
"quality": "medium",
|
2750 |
+
"num_speakers": 1,
|
2751 |
+
"speaker_id_map": {},
|
2752 |
+
"files": {
|
2753 |
+
"hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx": {
|
2754 |
+
"size_bytes": 63201294,
|
2755 |
+
"md5_digest": "a94cc2562ba892f462cb502f9d3c3ca3"
|
2756 |
+
},
|
2757 |
+
"hu/hu_HU/berta/medium/hu_HU-berta-medium.onnx.json": {
|
2758 |
+
"size_bytes": 4961,
|
2759 |
+
"md5_digest": "1f722cc72f330e3ba0222c6a94a527fa"
|
2760 |
+
},
|
2761 |
+
"hu/hu_HU/berta/medium/MODEL_CARD": {
|
2762 |
+
"size_bytes": 278,
|
2763 |
+
"md5_digest": "009624d3fa8f0f1e73c22a6277798c95"
|
2764 |
+
}
|
2765 |
+
},
|
2766 |
+
"aliases": []
|
2767 |
+
},
|
2768 |
"is_IS-bui-medium": {
|
2769 |
"key": "is_IS-bui-medium",
|
2770 |
"name": "bui",
|
|
|
3566 |
},
|
3567 |
"aliases": []
|
3568 |
},
|
3569 |
+
"pt_PT-tugão-medium": {
|
3570 |
+
"key": "pt_PT-tugão-medium",
|
3571 |
+
"name": "tugão",
|
3572 |
+
"language": {
|
3573 |
+
"code": "pt_PT",
|
3574 |
+
"family": "pt",
|
3575 |
+
"region": "PT",
|
3576 |
+
"name_native": "Português",
|
3577 |
+
"name_english": "Portuguese",
|
3578 |
+
"country_english": "Portugal"
|
3579 |
+
},
|
3580 |
+
"quality": "medium",
|
3581 |
+
"num_speakers": 1,
|
3582 |
+
"speaker_id_map": {},
|
3583 |
+
"files": {
|
3584 |
+
"pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx": {
|
3585 |
+
"size_bytes": 63201294,
|
3586 |
+
"md5_digest": "0642048511ffe36c3b519520614b53f4"
|
3587 |
+
},
|
3588 |
+
"pt/pt_PT/tugão/medium/pt_PT-tugão-medium.onnx.json": {
|
3589 |
+
"size_bytes": 5026,
|
3590 |
+
"md5_digest": "c4113a1da477aa6db28420454c142ebd"
|
3591 |
+
},
|
3592 |
+
"pt/pt_PT/tugão/medium/MODEL_CARD": {
|
3593 |
+
"size_bytes": 281,
|
3594 |
+
"md5_digest": "fcaafaf8d265f5a5b8e83df547f49bfd"
|
3595 |
+
}
|
3596 |
+
},
|
3597 |
+
"aliases": []
|
3598 |
+
},
|
3599 |
"ro_RO-mihai-medium": {
|
3600 |
"key": "ro_RO-mihai-medium",
|
3601 |
"name": "mihai",
|
|
|
3748 |
},
|
3749 |
"aliases": []
|
3750 |
},
|
3751 |
+
"sk_SK-lili-medium": {
|
3752 |
+
"key": "sk_SK-lili-medium",
|
3753 |
+
"name": "lili",
|
3754 |
+
"language": {
|
3755 |
+
"code": "sk_SK",
|
3756 |
+
"family": "sk",
|
3757 |
+
"region": "SK",
|
3758 |
+
"name_native": "Slovenčina",
|
3759 |
+
"name_english": "Slovak",
|
3760 |
+
"country_english": "Slovakia"
|
3761 |
+
},
|
3762 |
+
"quality": "medium",
|
3763 |
+
"num_speakers": 1,
|
3764 |
+
"speaker_id_map": {},
|
3765 |
+
"files": {
|
3766 |
+
"sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx": {
|
3767 |
+
"size_bytes": 63201294,
|
3768 |
+
"md5_digest": "836e078518042448bda8416a8ea52984"
|
3769 |
+
},
|
3770 |
+
"sk/sk_SK/lili/medium/sk_SK-lili-medium.onnx.json": {
|
3771 |
+
"size_bytes": 4963,
|
3772 |
+
"md5_digest": "e49cbd13cb5ce5b8f7e1c1479ec2cc91"
|
3773 |
+
},
|
3774 |
+
"sk/sk_SK/lili/medium/MODEL_CARD": {
|
3775 |
+
"size_bytes": 275,
|
3776 |
+
"md5_digest": "101dc437bf775a45dd6eedb14d9cfb4e"
|
3777 |
+
}
|
3778 |
+
},
|
3779 |
+
"aliases": []
|
3780 |
+
},
|
3781 |
"sr_RS-serbski_institut-medium": {
|
3782 |
"key": "sr_RS-serbski_institut-medium",
|
3783 |
"name": "serbski_institut",
|
|
|
3901 |
},
|
3902 |
"aliases": []
|
3903 |
},
|
3904 |
+
"tr_TR-fahrettin-medium": {
|
3905 |
+
"key": "tr_TR-fahrettin-medium",
|
3906 |
+
"name": "fahrettin",
|
3907 |
+
"language": {
|
3908 |
+
"code": "tr_TR",
|
3909 |
+
"family": "tr",
|
3910 |
+
"region": "TR",
|
3911 |
+
"name_native": "Türkçe",
|
3912 |
+
"name_english": "Turkish",
|
3913 |
+
"country_english": "Turkey"
|
3914 |
+
},
|
3915 |
+
"quality": "medium",
|
3916 |
+
"num_speakers": 1,
|
3917 |
+
"speaker_id_map": {},
|
3918 |
+
"files": {
|
3919 |
+
"tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx": {
|
3920 |
+
"size_bytes": 63201294,
|
3921 |
+
"md5_digest": "3ab8730ec3a132c79c74a45c451372f8"
|
3922 |
+
},
|
3923 |
+
"tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx.json": {
|
3924 |
+
"size_bytes": 5022,
|
3925 |
+
"md5_digest": "38b7beb509cb459da3c8f95841a59435"
|
3926 |
+
},
|
3927 |
+
"tr/tr_TR/fahrettin/medium/MODEL_CARD": {
|
3928 |
+
"size_bytes": 279,
|
3929 |
+
"md5_digest": "f0fe18e5a6b7615d59a89dfe4873247f"
|
3930 |
+
}
|
3931 |
+
},
|
3932 |
+
"aliases": []
|
3933 |
+
},
|
3934 |
"uk_UA-lada-x_low": {
|
3935 |
"key": "uk_UA-lada-x_low",
|
3936 |
"name": "lada",
|