https://huggingface.co/rhasspy/piper-voices/tree/main
#49
by PUREDNA - opened
This view is limited to 50 files because it contains too many changes. See the raw diff here.
- _script/voicefest.py +0 -4
- cs/cs_CZ/jirka/low/MODEL_CARD +1 -1
- cs/cs_CZ/jirka/medium/MODEL_CARD +1 -1
- en/en_US/joe/medium/MODEL_CARD +1 -1
- es/es_ES/davefx/medium/MODEL_CARD +1 -1
- es/es_MX/ald/medium/es_MX-ald-medium.onnx.json +2 -2
- eu/eu_ES/antton/medium/MODEL_CARD +0 -15
- eu/eu_ES/antton/medium/eu_ES-antton-medium.onnx.json +0 -514
- eu/eu_ES/antton/medium/samples/speaker_0.mp3 +0 -3
- eu/eu_ES/maider/medium/MODEL_CARD +0 -15
- eu/eu_ES/maider/medium/eu_ES-maider-medium.onnx.json +0 -514
- eu/eu_ES/maider/medium/samples/speaker_0.mp3 +0 -3
- hu/hu_HU/anna/medium/MODEL_CARD +1 -1
- hu/hu_HU/berta/medium/MODEL_CARD +1 -1
- hu/hu_HU/imre/medium/MODEL_CARD +1 -1
- ku/ku_TR/berfin_renas/medium/MODEL_CARD +0 -142
- ku/ku_TR/berfin_renas/medium/ku_TR-berfin_renas-medium.onnx +0 -3
- ku/ku_TR/berfin_renas/medium/ku_TR-berfin_renas-medium.onnx.json +0 -517
- ku/ku_TR/berfin_renas/medium/samples/speaker_1.mp3 +0 -3
- ne/ne_NP/chitwan/medium/MODEL_CARD +1 -1
- nl/nl_NL/alex/medium/MODEL_CARD +0 -15
- nl/nl_NL/alex/medium/nl_NL-alex-medium.onnx +0 -3
- nl/nl_NL/alex/medium/samples/speaker_0.mp3 +0 -3
- nl/nl_NL/pim/medium/MODEL_CARD +1 -1
- nl/nl_NL/ronnie/medium/MODEL_CARD +1 -1
- pl/pl_PL/bass/high/MODEL_CARD +0 -13
- pl/pl_PL/bass/high/pl_PL-bass-high.onnx +0 -3
- pl/pl_PL/bass/high/samples/speaker_0.mp3 +0 -3
- pl/pl_PL/darkman/medium/MODEL_CARD +1 -1
- pl/pl_PL/gosia/medium/MODEL_CARD +1 -1
- pt/pt_BR/cadu/medium/MODEL_CARD +1 -1
- pt/pt_BR/faber/medium/MODEL_CARD +1 -1
- pt/pt_BR/jeff/medium/MODEL_CARD +1 -1
- pt/pt_PT/tugão/medium/MODEL_CARD +1 -1
- ro/ro_RO/mihai/medium/MODEL_CARD +1 -1
- ru/ru_RU/denis/medium/MODEL_CARD +1 -1
- ru/ru_RU/dmitri/medium/MODEL_CARD +1 -1
- sk/sk_SK/lili/medium/MODEL_CARD +1 -1
- sq/sq_AL/edon/medium/samples/speaker_0.mp3 +0 -3
- sq/sq_AL/edon/medium/sq_AL-edon-medium.onnx +0 -3
- sq/sq_AL/edon/medium/sq_AL-edon-medium.onnx.json +0 -502
- sv/sv_SE/alma/medium/MODEL_CARD +0 -15
- sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx +0 -3
- sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx.json +0 -420
- {sq/sq_AL/edon → tr/tr_TR/fahrettin}/medium/MODEL_CARD +4 -4
- {sv/sv_SE/alma → tr/tr_TR/fahrettin}/medium/samples/speaker_0.mp3 +2 -2
- eu/eu_ES/maider/medium/eu_ES-maider-medium.onnx → tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx +2 -2
- nl/nl_NL/alex/medium/nl_NL-alex-medium.onnx.json → tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx.json +18 -12
- {zh/zh_CN/chaowen → tr/tr_TR/fettah}/medium/MODEL_CARD +5 -5
- {ku/ku_TR/berfin_renas → tr/tr_TR/fettah}/medium/samples/speaker_0.mp3 +2 -2
_script/voicefest.py
CHANGED
|
@@ -31,7 +31,6 @@ _LANGUAGES = {
|
|
| 31 |
"es_AR": Language("Español", "Spanish", "Argentina"),
|
| 32 |
"es_ES": Language("Español", "Spanish", "Spain"),
|
| 33 |
"es_MX": Language("Español", "Spanish", "Mexico"),
|
| 34 |
-
"eu_ES": Language("Euskara", "Basque", "Spain"),
|
| 35 |
"fa_IR": Language("فارسی", "Farsi", "Iran"),
|
| 36 |
"fi_FI": Language("Suomi", "Finnish", "Finland"),
|
| 37 |
"fr_FR": Language("Français", "French", "France"),
|
|
@@ -43,7 +42,6 @@ _LANGUAGES = {
|
|
| 43 |
"hu_HU": Language("Magyar", "Hungarian", "Hungary"),
|
| 44 |
"ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
|
| 45 |
"kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
|
| 46 |
-
"ku_TR": Language("Kurmancî", "Kurmanji Kurdish", "Turkey"),
|
| 47 |
"lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
|
| 48 |
"lv_LV": Language("Latviešu", "Latvian", "Latvia"),
|
| 49 |
"ne_NP": Language("नेपाली", "Nepali", "Nepal"),
|
|
@@ -58,14 +56,12 @@ _LANGUAGES = {
|
|
| 58 |
"ru_RU": Language("Русский", "Russian", "Russia"),
|
| 59 |
"sk_SK": Language("Slovenčina", "Slovak", "Slovakia"),
|
| 60 |
"sl_SI": Language("Slovenščina", "Slovenian", "Slovenia"),
|
| 61 |
-
"sq_AL": Language("shqip", "Albanian", "Albania"),
|
| 62 |
"sr_RS": Language("srpski", "Serbian", "Serbia"),
|
| 63 |
"sv_SE": Language("Svenska", "Swedish", "Sweden"),
|
| 64 |
"sw_CD": Language("Kiswahili", "Swahili", "Democratic Republic of the Congo"),
|
| 65 |
"te_IN": Language("తెలుగు", "Telugu", "India"),
|
| 66 |
"tr_TR": Language("Türkçe", "Turkish", "Turkey"),
|
| 67 |
"uk_UA": Language("украї́нська мо́ва", "Ukrainian", "Ukraine"),
|
| 68 |
-
"ur_PK": Language("اردو", "Urdu", "Pakistan"),
|
| 69 |
"vi_VN": Language("Tiếng Việt", "Vietnamese", "Vietnam"),
|
| 70 |
"zh_CN": Language("简体中文", "Chinese", "China"),
|
| 71 |
}
|
|
|
|
| 31 |
"es_AR": Language("Español", "Spanish", "Argentina"),
|
| 32 |
"es_ES": Language("Español", "Spanish", "Spain"),
|
| 33 |
"es_MX": Language("Español", "Spanish", "Mexico"),
|
|
|
|
| 34 |
"fa_IR": Language("فارسی", "Farsi", "Iran"),
|
| 35 |
"fi_FI": Language("Suomi", "Finnish", "Finland"),
|
| 36 |
"fr_FR": Language("Français", "French", "France"),
|
|
|
|
| 42 |
"hu_HU": Language("Magyar", "Hungarian", "Hungary"),
|
| 43 |
"ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
|
| 44 |
"kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
|
|
|
|
| 45 |
"lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
|
| 46 |
"lv_LV": Language("Latviešu", "Latvian", "Latvia"),
|
| 47 |
"ne_NP": Language("नेपाली", "Nepali", "Nepal"),
|
|
|
|
| 56 |
"ru_RU": Language("Русский", "Russian", "Russia"),
|
| 57 |
"sk_SK": Language("Slovenčina", "Slovak", "Slovakia"),
|
| 58 |
"sl_SI": Language("Slovenščina", "Slovenian", "Slovenia"),
|
|
|
|
| 59 |
"sr_RS": Language("srpski", "Serbian", "Serbia"),
|
| 60 |
"sv_SE": Language("Svenska", "Swedish", "Sweden"),
|
| 61 |
"sw_CD": Language("Kiswahili", "Swahili", "Democratic Republic of the Congo"),
|
| 62 |
"te_IN": Language("తెలుగు", "Telugu", "India"),
|
| 63 |
"tr_TR": Language("Türkçe", "Turkish", "Turkey"),
|
| 64 |
"uk_UA": Language("украї́нська мо́ва", "Ukrainian", "Ukraine"),
|
|
|
|
| 65 |
"vi_VN": Language("Tiếng Việt", "Vietnamese", "Vietnam"),
|
| 66 |
"zh_CN": Language("简体中文", "Chinese", "China"),
|
| 67 |
}
|
cs/cs_CZ/jirka/low/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
cs/cs_CZ/jirka/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
en/en_US/joe/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
es/es_ES/davefx/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
es/es_MX/ald/medium/es_MX-ald-medium.onnx.json
CHANGED
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"length_scale": 1,
|
| 12 |
"noise_w": 0.8
|
| 13 |
},
|
| 14 |
-
"phoneme_type": "
|
| 15 |
"phoneme_map": {},
|
| 16 |
"phoneme_id_map": {
|
| 17 |
"_": [
|
|
@@ -490,4 +490,4 @@
|
|
| 490 |
"country_english": "Mexico"
|
| 491 |
},
|
| 492 |
"dataset": "ald"
|
| 493 |
-
}
|
|
|
|
| 11 |
"length_scale": 1,
|
| 12 |
"noise_w": 0.8
|
| 13 |
},
|
| 14 |
+
"phoneme_type": "PhonemeType.ESPEAK",
|
| 15 |
"phoneme_map": {},
|
| 16 |
"phoneme_id_map": {
|
| 17 |
"_": [
|
|
|
|
| 490 |
"country_english": "Mexico"
|
| 491 |
},
|
| 492 |
"dataset": "ald"
|
| 493 |
+
}
|
eu/eu_ES/antton/medium/MODEL_CARD
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
# Model card for antton (medium)
|
| 2 |
-
|
| 3 |
-
* Language: eu_ES (Basque, Spain)
|
| 4 |
-
* Speakers: 1
|
| 5 |
-
* Quality: medium
|
| 6 |
-
* Samplerate: 22,050Hz
|
| 7 |
-
|
| 8 |
-
## Dataset
|
| 9 |
-
|
| 10 |
-
* URL: https://huggingface.co/datasets/itzune/antton-dataset
|
| 11 |
-
* License: Creative Commons Attribution 4.0
|
| 12 |
-
|
| 13 |
-
## Training
|
| 14 |
-
|
| 15 |
-
Finetuned from U.S English amy voice (medium quality).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eu/eu_ES/antton/medium/eu_ES-antton-medium.onnx.json
DELETED
|
@@ -1,514 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"audio": {
|
| 3 |
-
"sample_rate": 22050,
|
| 4 |
-
"quality": "medium"
|
| 5 |
-
},
|
| 6 |
-
"espeak": {
|
| 7 |
-
"voice": "eu"
|
| 8 |
-
},
|
| 9 |
-
"language": {
|
| 10 |
-
"code": "eu_ES",
|
| 11 |
-
"family": "eu",
|
| 12 |
-
"region": "ES",
|
| 13 |
-
"name_native": "Euskara",
|
| 14 |
-
"name_english": "Basque",
|
| 15 |
-
"country_english": "Spain"
|
| 16 |
-
},
|
| 17 |
-
"phoneme_type": "espeak",
|
| 18 |
-
"num_symbols": 256,
|
| 19 |
-
"num_speakers": 1,
|
| 20 |
-
"inference": {
|
| 21 |
-
"noise_scale": 0.667,
|
| 22 |
-
"length_scale": 1.0,
|
| 23 |
-
"noise_w": 0.8
|
| 24 |
-
},
|
| 25 |
-
"phoneme_id_map": {
|
| 26 |
-
"_": [
|
| 27 |
-
0
|
| 28 |
-
],
|
| 29 |
-
"^": [
|
| 30 |
-
1
|
| 31 |
-
],
|
| 32 |
-
"$": [
|
| 33 |
-
2
|
| 34 |
-
],
|
| 35 |
-
" ": [
|
| 36 |
-
3
|
| 37 |
-
],
|
| 38 |
-
"!": [
|
| 39 |
-
4
|
| 40 |
-
],
|
| 41 |
-
"'": [
|
| 42 |
-
5
|
| 43 |
-
],
|
| 44 |
-
"(": [
|
| 45 |
-
6
|
| 46 |
-
],
|
| 47 |
-
")": [
|
| 48 |
-
7
|
| 49 |
-
],
|
| 50 |
-
",": [
|
| 51 |
-
8
|
| 52 |
-
],
|
| 53 |
-
"-": [
|
| 54 |
-
9
|
| 55 |
-
],
|
| 56 |
-
".": [
|
| 57 |
-
10
|
| 58 |
-
],
|
| 59 |
-
":": [
|
| 60 |
-
11
|
| 61 |
-
],
|
| 62 |
-
";": [
|
| 63 |
-
12
|
| 64 |
-
],
|
| 65 |
-
"?": [
|
| 66 |
-
13
|
| 67 |
-
],
|
| 68 |
-
"a": [
|
| 69 |
-
14
|
| 70 |
-
],
|
| 71 |
-
"b": [
|
| 72 |
-
15
|
| 73 |
-
],
|
| 74 |
-
"c": [
|
| 75 |
-
16
|
| 76 |
-
],
|
| 77 |
-
"d": [
|
| 78 |
-
17
|
| 79 |
-
],
|
| 80 |
-
"e": [
|
| 81 |
-
18
|
| 82 |
-
],
|
| 83 |
-
"f": [
|
| 84 |
-
19
|
| 85 |
-
],
|
| 86 |
-
"h": [
|
| 87 |
-
20
|
| 88 |
-
],
|
| 89 |
-
"i": [
|
| 90 |
-
21
|
| 91 |
-
],
|
| 92 |
-
"j": [
|
| 93 |
-
22
|
| 94 |
-
],
|
| 95 |
-
"k": [
|
| 96 |
-
23
|
| 97 |
-
],
|
| 98 |
-
"l": [
|
| 99 |
-
24
|
| 100 |
-
],
|
| 101 |
-
"m": [
|
| 102 |
-
25
|
| 103 |
-
],
|
| 104 |
-
"n": [
|
| 105 |
-
26
|
| 106 |
-
],
|
| 107 |
-
"o": [
|
| 108 |
-
27
|
| 109 |
-
],
|
| 110 |
-
"p": [
|
| 111 |
-
28
|
| 112 |
-
],
|
| 113 |
-
"q": [
|
| 114 |
-
29
|
| 115 |
-
],
|
| 116 |
-
"r": [
|
| 117 |
-
30
|
| 118 |
-
],
|
| 119 |
-
"s": [
|
| 120 |
-
31
|
| 121 |
-
],
|
| 122 |
-
"t": [
|
| 123 |
-
32
|
| 124 |
-
],
|
| 125 |
-
"u": [
|
| 126 |
-
33
|
| 127 |
-
],
|
| 128 |
-
"v": [
|
| 129 |
-
34
|
| 130 |
-
],
|
| 131 |
-
"w": [
|
| 132 |
-
35
|
| 133 |
-
],
|
| 134 |
-
"x": [
|
| 135 |
-
36
|
| 136 |
-
],
|
| 137 |
-
"y": [
|
| 138 |
-
37
|
| 139 |
-
],
|
| 140 |
-
"z": [
|
| 141 |
-
38
|
| 142 |
-
],
|
| 143 |
-
"æ": [
|
| 144 |
-
39
|
| 145 |
-
],
|
| 146 |
-
"ç": [
|
| 147 |
-
40
|
| 148 |
-
],
|
| 149 |
-
"ð": [
|
| 150 |
-
41
|
| 151 |
-
],
|
| 152 |
-
"ø": [
|
| 153 |
-
42
|
| 154 |
-
],
|
| 155 |
-
"ħ": [
|
| 156 |
-
43
|
| 157 |
-
],
|
| 158 |
-
"ŋ": [
|
| 159 |
-
44
|
| 160 |
-
],
|
| 161 |
-
"œ": [
|
| 162 |
-
45
|
| 163 |
-
],
|
| 164 |
-
"ǀ": [
|
| 165 |
-
46
|
| 166 |
-
],
|
| 167 |
-
"ǁ": [
|
| 168 |
-
47
|
| 169 |
-
],
|
| 170 |
-
"ǂ": [
|
| 171 |
-
48
|
| 172 |
-
],
|
| 173 |
-
"ǃ": [
|
| 174 |
-
49
|
| 175 |
-
],
|
| 176 |
-
"ɐ": [
|
| 177 |
-
50
|
| 178 |
-
],
|
| 179 |
-
"ɑ": [
|
| 180 |
-
51
|
| 181 |
-
],
|
| 182 |
-
"ɒ": [
|
| 183 |
-
52
|
| 184 |
-
],
|
| 185 |
-
"ɓ": [
|
| 186 |
-
53
|
| 187 |
-
],
|
| 188 |
-
"ɔ": [
|
| 189 |
-
54
|
| 190 |
-
],
|
| 191 |
-
"ɕ": [
|
| 192 |
-
55
|
| 193 |
-
],
|
| 194 |
-
"ɖ": [
|
| 195 |
-
56
|
| 196 |
-
],
|
| 197 |
-
"ɗ": [
|
| 198 |
-
57
|
| 199 |
-
],
|
| 200 |
-
"ɘ": [
|
| 201 |
-
58
|
| 202 |
-
],
|
| 203 |
-
"ə": [
|
| 204 |
-
59
|
| 205 |
-
],
|
| 206 |
-
"ɚ": [
|
| 207 |
-
60
|
| 208 |
-
],
|
| 209 |
-
"ɛ": [
|
| 210 |
-
61
|
| 211 |
-
],
|
| 212 |
-
"ɜ": [
|
| 213 |
-
62
|
| 214 |
-
],
|
| 215 |
-
"ɞ": [
|
| 216 |
-
63
|
| 217 |
-
],
|
| 218 |
-
"ɟ": [
|
| 219 |
-
64
|
| 220 |
-
],
|
| 221 |
-
"ɠ": [
|
| 222 |
-
65
|
| 223 |
-
],
|
| 224 |
-
"ɡ": [
|
| 225 |
-
66
|
| 226 |
-
],
|
| 227 |
-
"ɢ": [
|
| 228 |
-
67
|
| 229 |
-
],
|
| 230 |
-
"ɣ": [
|
| 231 |
-
68
|
| 232 |
-
],
|
| 233 |
-
"ɤ": [
|
| 234 |
-
69
|
| 235 |
-
],
|
| 236 |
-
"ɥ": [
|
| 237 |
-
70
|
| 238 |
-
],
|
| 239 |
-
"ɦ": [
|
| 240 |
-
71
|
| 241 |
-
],
|
| 242 |
-
"ɧ": [
|
| 243 |
-
72
|
| 244 |
-
],
|
| 245 |
-
"ɨ": [
|
| 246 |
-
73
|
| 247 |
-
],
|
| 248 |
-
"ɪ": [
|
| 249 |
-
74
|
| 250 |
-
],
|
| 251 |
-
"ɫ": [
|
| 252 |
-
75
|
| 253 |
-
],
|
| 254 |
-
"ɬ": [
|
| 255 |
-
76
|
| 256 |
-
],
|
| 257 |
-
"ɭ": [
|
| 258 |
-
77
|
| 259 |
-
],
|
| 260 |
-
"ɮ": [
|
| 261 |
-
78
|
| 262 |
-
],
|
| 263 |
-
"ɯ": [
|
| 264 |
-
79
|
| 265 |
-
],
|
| 266 |
-
"ɰ": [
|
| 267 |
-
80
|
| 268 |
-
],
|
| 269 |
-
"ɱ": [
|
| 270 |
-
81
|
| 271 |
-
],
|
| 272 |
-
"ɲ": [
|
| 273 |
-
82
|
| 274 |
-
],
|
| 275 |
-
"ɳ": [
|
| 276 |
-
83
|
| 277 |
-
],
|
| 278 |
-
"ɴ": [
|
| 279 |
-
84
|
| 280 |
-
],
|
| 281 |
-
"ɵ": [
|
| 282 |
-
85
|
| 283 |
-
],
|
| 284 |
-
"ɶ": [
|
| 285 |
-
86
|
| 286 |
-
],
|
| 287 |
-
"ɸ": [
|
| 288 |
-
87
|
| 289 |
-
],
|
| 290 |
-
"ɹ": [
|
| 291 |
-
88
|
| 292 |
-
],
|
| 293 |
-
"ɺ": [
|
| 294 |
-
89
|
| 295 |
-
],
|
| 296 |
-
"ɻ": [
|
| 297 |
-
90
|
| 298 |
-
],
|
| 299 |
-
"ɽ": [
|
| 300 |
-
91
|
| 301 |
-
],
|
| 302 |
-
"ɾ": [
|
| 303 |
-
92
|
| 304 |
-
],
|
| 305 |
-
"ʀ": [
|
| 306 |
-
93
|
| 307 |
-
],
|
| 308 |
-
"ʁ": [
|
| 309 |
-
94
|
| 310 |
-
],
|
| 311 |
-
"ʂ": [
|
| 312 |
-
95
|
| 313 |
-
],
|
| 314 |
-
"ʃ": [
|
| 315 |
-
96
|
| 316 |
-
],
|
| 317 |
-
"ʄ": [
|
| 318 |
-
97
|
| 319 |
-
],
|
| 320 |
-
"ʈ": [
|
| 321 |
-
98
|
| 322 |
-
],
|
| 323 |
-
"ʉ": [
|
| 324 |
-
99
|
| 325 |
-
],
|
| 326 |
-
"ʊ": [
|
| 327 |
-
100
|
| 328 |
-
],
|
| 329 |
-
"ʋ": [
|
| 330 |
-
101
|
| 331 |
-
],
|
| 332 |
-
"ʌ": [
|
| 333 |
-
102
|
| 334 |
-
],
|
| 335 |
-
"ʍ": [
|
| 336 |
-
103
|
| 337 |
-
],
|
| 338 |
-
"ʎ": [
|
| 339 |
-
104
|
| 340 |
-
],
|
| 341 |
-
"ʏ": [
|
| 342 |
-
105
|
| 343 |
-
],
|
| 344 |
-
"ʐ": [
|
| 345 |
-
106
|
| 346 |
-
],
|
| 347 |
-
"ʑ": [
|
| 348 |
-
107
|
| 349 |
-
],
|
| 350 |
-
"ʒ": [
|
| 351 |
-
108
|
| 352 |
-
],
|
| 353 |
-
"ʔ": [
|
| 354 |
-
109
|
| 355 |
-
],
|
| 356 |
-
"ʕ": [
|
| 357 |
-
110
|
| 358 |
-
],
|
| 359 |
-
"ʘ": [
|
| 360 |
-
111
|
| 361 |
-
],
|
| 362 |
-
"ʙ": [
|
| 363 |
-
112
|
| 364 |
-
],
|
| 365 |
-
"ʛ": [
|
| 366 |
-
113
|
| 367 |
-
],
|
| 368 |
-
"ʜ": [
|
| 369 |
-
114
|
| 370 |
-
],
|
| 371 |
-
"ʝ": [
|
| 372 |
-
115
|
| 373 |
-
],
|
| 374 |
-
"ʟ": [
|
| 375 |
-
116
|
| 376 |
-
],
|
| 377 |
-
"ʡ": [
|
| 378 |
-
117
|
| 379 |
-
],
|
| 380 |
-
"ʢ": [
|
| 381 |
-
118
|
| 382 |
-
],
|
| 383 |
-
"ʲ": [
|
| 384 |
-
119
|
| 385 |
-
],
|
| 386 |
-
"ˈ": [
|
| 387 |
-
120
|
| 388 |
-
],
|
| 389 |
-
"ˌ": [
|
| 390 |
-
121
|
| 391 |
-
],
|
| 392 |
-
"ː": [
|
| 393 |
-
122
|
| 394 |
-
],
|
| 395 |
-
"ˑ": [
|
| 396 |
-
123
|
| 397 |
-
],
|
| 398 |
-
"˞": [
|
| 399 |
-
124
|
| 400 |
-
],
|
| 401 |
-
"β": [
|
| 402 |
-
125
|
| 403 |
-
],
|
| 404 |
-
"θ": [
|
| 405 |
-
126
|
| 406 |
-
],
|
| 407 |
-
"χ": [
|
| 408 |
-
127
|
| 409 |
-
],
|
| 410 |
-
"ᵻ": [
|
| 411 |
-
128
|
| 412 |
-
],
|
| 413 |
-
"ⱱ": [
|
| 414 |
-
129
|
| 415 |
-
],
|
| 416 |
-
"0": [
|
| 417 |
-
130
|
| 418 |
-
],
|
| 419 |
-
"1": [
|
| 420 |
-
131
|
| 421 |
-
],
|
| 422 |
-
"2": [
|
| 423 |
-
132
|
| 424 |
-
],
|
| 425 |
-
"3": [
|
| 426 |
-
133
|
| 427 |
-
],
|
| 428 |
-
"4": [
|
| 429 |
-
134
|
| 430 |
-
],
|
| 431 |
-
"5": [
|
| 432 |
-
135
|
| 433 |
-
],
|
| 434 |
-
"6": [
|
| 435 |
-
136
|
| 436 |
-
],
|
| 437 |
-
"7": [
|
| 438 |
-
137
|
| 439 |
-
],
|
| 440 |
-
"8": [
|
| 441 |
-
138
|
| 442 |
-
],
|
| 443 |
-
"9": [
|
| 444 |
-
139
|
| 445 |
-
],
|
| 446 |
-
"̧": [
|
| 447 |
-
140
|
| 448 |
-
],
|
| 449 |
-
"̃": [
|
| 450 |
-
141
|
| 451 |
-
],
|
| 452 |
-
"̪": [
|
| 453 |
-
142
|
| 454 |
-
],
|
| 455 |
-
"̯": [
|
| 456 |
-
143
|
| 457 |
-
],
|
| 458 |
-
"̩": [
|
| 459 |
-
144
|
| 460 |
-
],
|
| 461 |
-
"ʰ": [
|
| 462 |
-
145
|
| 463 |
-
],
|
| 464 |
-
"ˤ": [
|
| 465 |
-
146
|
| 466 |
-
],
|
| 467 |
-
"ε": [
|
| 468 |
-
147
|
| 469 |
-
],
|
| 470 |
-
"↓": [
|
| 471 |
-
148
|
| 472 |
-
],
|
| 473 |
-
"#": [
|
| 474 |
-
149
|
| 475 |
-
],
|
| 476 |
-
"\"": [
|
| 477 |
-
150
|
| 478 |
-
],
|
| 479 |
-
"↑": [
|
| 480 |
-
151
|
| 481 |
-
],
|
| 482 |
-
"̺": [
|
| 483 |
-
152
|
| 484 |
-
],
|
| 485 |
-
"̻": [
|
| 486 |
-
153
|
| 487 |
-
],
|
| 488 |
-
"g": [
|
| 489 |
-
154
|
| 490 |
-
],
|
| 491 |
-
"ʦ": [
|
| 492 |
-
155
|
| 493 |
-
],
|
| 494 |
-
"X": [
|
| 495 |
-
156
|
| 496 |
-
],
|
| 497 |
-
"̝": [
|
| 498 |
-
157
|
| 499 |
-
],
|
| 500 |
-
"̊": [
|
| 501 |
-
158
|
| 502 |
-
],
|
| 503 |
-
"ɝ": [
|
| 504 |
-
159
|
| 505 |
-
],
|
| 506 |
-
"ʷ": [
|
| 507 |
-
160
|
| 508 |
-
]
|
| 509 |
-
},
|
| 510 |
-
"speaker_id_map": {},
|
| 511 |
-
"hop_length": 256,
|
| 512 |
-
"piper_version": "1.3.0",
|
| 513 |
-
"dataset": "antton"
|
| 514 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eu/eu_ES/antton/medium/samples/speaker_0.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:78164b1dd7a805235b58ed7ee9e6d251d9f3ebd6a48f1fcb73f0155e1427dd48
|
| 3 |
-
size 131707
|
|
|
|
|
|
|
|
|
|
|
|
eu/eu_ES/maider/medium/MODEL_CARD
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
# Model card for maider (medium)
|
| 2 |
-
|
| 3 |
-
* Language: eu_ES (Basque, Spain)
|
| 4 |
-
* Speakers: 1
|
| 5 |
-
* Quality: medium
|
| 6 |
-
* Samplerate: 22,050Hz
|
| 7 |
-
|
| 8 |
-
## Dataset
|
| 9 |
-
|
| 10 |
-
* URL: https://huggingface.co/datasets/itzune/maider-dataset
|
| 11 |
-
* License: Creative Commons Attribution 4.0
|
| 12 |
-
|
| 13 |
-
## Training
|
| 14 |
-
|
| 15 |
-
Finetuned from U.S English amy voice (medium quality).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eu/eu_ES/maider/medium/eu_ES-maider-medium.onnx.json
DELETED
|
@@ -1,514 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"audio": {
|
| 3 |
-
"sample_rate": 22050,
|
| 4 |
-
"quality": "medium"
|
| 5 |
-
},
|
| 6 |
-
"espeak": {
|
| 7 |
-
"voice": "eu"
|
| 8 |
-
},
|
| 9 |
-
"language": {
|
| 10 |
-
"code": "eu_ES",
|
| 11 |
-
"family": "eu",
|
| 12 |
-
"region": "ES",
|
| 13 |
-
"name_native": "Euskara",
|
| 14 |
-
"name_english": "Basque",
|
| 15 |
-
"country_english": "Spain"
|
| 16 |
-
},
|
| 17 |
-
"phoneme_type": "espeak",
|
| 18 |
-
"num_symbols": 256,
|
| 19 |
-
"num_speakers": 1,
|
| 20 |
-
"inference": {
|
| 21 |
-
"noise_scale": 0.667,
|
| 22 |
-
"length_scale": 1.0,
|
| 23 |
-
"noise_w": 0.8
|
| 24 |
-
},
|
| 25 |
-
"phoneme_id_map": {
|
| 26 |
-
"_": [
|
| 27 |
-
0
|
| 28 |
-
],
|
| 29 |
-
"^": [
|
| 30 |
-
1
|
| 31 |
-
],
|
| 32 |
-
"$": [
|
| 33 |
-
2
|
| 34 |
-
],
|
| 35 |
-
" ": [
|
| 36 |
-
3
|
| 37 |
-
],
|
| 38 |
-
"!": [
|
| 39 |
-
4
|
| 40 |
-
],
|
| 41 |
-
"'": [
|
| 42 |
-
5
|
| 43 |
-
],
|
| 44 |
-
"(": [
|
| 45 |
-
6
|
| 46 |
-
],
|
| 47 |
-
")": [
|
| 48 |
-
7
|
| 49 |
-
],
|
| 50 |
-
",": [
|
| 51 |
-
8
|
| 52 |
-
],
|
| 53 |
-
"-": [
|
| 54 |
-
9
|
| 55 |
-
],
|
| 56 |
-
".": [
|
| 57 |
-
10
|
| 58 |
-
],
|
| 59 |
-
":": [
|
| 60 |
-
11
|
| 61 |
-
],
|
| 62 |
-
";": [
|
| 63 |
-
12
|
| 64 |
-
],
|
| 65 |
-
"?": [
|
| 66 |
-
13
|
| 67 |
-
],
|
| 68 |
-
"a": [
|
| 69 |
-
14
|
| 70 |
-
],
|
| 71 |
-
"b": [
|
| 72 |
-
15
|
| 73 |
-
],
|
| 74 |
-
"c": [
|
| 75 |
-
16
|
| 76 |
-
],
|
| 77 |
-
"d": [
|
| 78 |
-
17
|
| 79 |
-
],
|
| 80 |
-
"e": [
|
| 81 |
-
18
|
| 82 |
-
],
|
| 83 |
-
"f": [
|
| 84 |
-
19
|
| 85 |
-
],
|
| 86 |
-
"h": [
|
| 87 |
-
20
|
| 88 |
-
],
|
| 89 |
-
"i": [
|
| 90 |
-
21
|
| 91 |
-
],
|
| 92 |
-
"j": [
|
| 93 |
-
22
|
| 94 |
-
],
|
| 95 |
-
"k": [
|
| 96 |
-
23
|
| 97 |
-
],
|
| 98 |
-
"l": [
|
| 99 |
-
24
|
| 100 |
-
],
|
| 101 |
-
"m": [
|
| 102 |
-
25
|
| 103 |
-
],
|
| 104 |
-
"n": [
|
| 105 |
-
26
|
| 106 |
-
],
|
| 107 |
-
"o": [
|
| 108 |
-
27
|
| 109 |
-
],
|
| 110 |
-
"p": [
|
| 111 |
-
28
|
| 112 |
-
],
|
| 113 |
-
"q": [
|
| 114 |
-
29
|
| 115 |
-
],
|
| 116 |
-
"r": [
|
| 117 |
-
30
|
| 118 |
-
],
|
| 119 |
-
"s": [
|
| 120 |
-
31
|
| 121 |
-
],
|
| 122 |
-
"t": [
|
| 123 |
-
32
|
| 124 |
-
],
|
| 125 |
-
"u": [
|
| 126 |
-
33
|
| 127 |
-
],
|
| 128 |
-
"v": [
|
| 129 |
-
34
|
| 130 |
-
],
|
| 131 |
-
"w": [
|
| 132 |
-
35
|
| 133 |
-
],
|
| 134 |
-
"x": [
|
| 135 |
-
36
|
| 136 |
-
],
|
| 137 |
-
"y": [
|
| 138 |
-
37
|
| 139 |
-
],
|
| 140 |
-
"z": [
|
| 141 |
-
38
|
| 142 |
-
],
|
| 143 |
-
"æ": [
|
| 144 |
-
39
|
| 145 |
-
],
|
| 146 |
-
"ç": [
|
| 147 |
-
40
|
| 148 |
-
],
|
| 149 |
-
"ð": [
|
| 150 |
-
41
|
| 151 |
-
],
|
| 152 |
-
"ø": [
|
| 153 |
-
42
|
| 154 |
-
],
|
| 155 |
-
"ħ": [
|
| 156 |
-
43
|
| 157 |
-
],
|
| 158 |
-
"ŋ": [
|
| 159 |
-
44
|
| 160 |
-
],
|
| 161 |
-
"œ": [
|
| 162 |
-
45
|
| 163 |
-
],
|
| 164 |
-
"ǀ": [
|
| 165 |
-
46
|
| 166 |
-
],
|
| 167 |
-
"ǁ": [
|
| 168 |
-
47
|
| 169 |
-
],
|
| 170 |
-
"ǂ": [
|
| 171 |
-
48
|
| 172 |
-
],
|
| 173 |
-
"ǃ": [
|
| 174 |
-
49
|
| 175 |
-
],
|
| 176 |
-
"ɐ": [
|
| 177 |
-
50
|
| 178 |
-
],
|
| 179 |
-
"ɑ": [
|
| 180 |
-
51
|
| 181 |
-
],
|
| 182 |
-
"ɒ": [
|
| 183 |
-
52
|
| 184 |
-
],
|
| 185 |
-
"ɓ": [
|
| 186 |
-
53
|
| 187 |
-
],
|
| 188 |
-
"ɔ": [
|
| 189 |
-
54
|
| 190 |
-
],
|
| 191 |
-
"ɕ": [
|
| 192 |
-
55
|
| 193 |
-
],
|
| 194 |
-
"ɖ": [
|
| 195 |
-
56
|
| 196 |
-
],
|
| 197 |
-
"ɗ": [
|
| 198 |
-
57
|
| 199 |
-
],
|
| 200 |
-
"ɘ": [
|
| 201 |
-
58
|
| 202 |
-
],
|
| 203 |
-
"ə": [
|
| 204 |
-
59
|
| 205 |
-
],
|
| 206 |
-
"ɚ": [
|
| 207 |
-
60
|
| 208 |
-
],
|
| 209 |
-
"ɛ": [
|
| 210 |
-
61
|
| 211 |
-
],
|
| 212 |
-
"ɜ": [
|
| 213 |
-
62
|
| 214 |
-
],
|
| 215 |
-
"ɞ": [
|
| 216 |
-
63
|
| 217 |
-
],
|
| 218 |
-
"ɟ": [
|
| 219 |
-
64
|
| 220 |
-
],
|
| 221 |
-
"ɠ": [
|
| 222 |
-
65
|
| 223 |
-
],
|
| 224 |
-
"ɡ": [
|
| 225 |
-
66
|
| 226 |
-
],
|
| 227 |
-
"ɢ": [
|
| 228 |
-
67
|
| 229 |
-
],
|
| 230 |
-
"ɣ": [
|
| 231 |
-
68
|
| 232 |
-
],
|
| 233 |
-
"ɤ": [
|
| 234 |
-
69
|
| 235 |
-
],
|
| 236 |
-
"ɥ": [
|
| 237 |
-
70
|
| 238 |
-
],
|
| 239 |
-
"ɦ": [
|
| 240 |
-
71
|
| 241 |
-
],
|
| 242 |
-
"ɧ": [
|
| 243 |
-
72
|
| 244 |
-
],
|
| 245 |
-
"ɨ": [
|
| 246 |
-
73
|
| 247 |
-
],
|
| 248 |
-
"ɪ": [
|
| 249 |
-
74
|
| 250 |
-
],
|
| 251 |
-
"ɫ": [
|
| 252 |
-
75
|
| 253 |
-
],
|
| 254 |
-
"ɬ": [
|
| 255 |
-
76
|
| 256 |
-
],
|
| 257 |
-
"ɭ": [
|
| 258 |
-
77
|
| 259 |
-
],
|
| 260 |
-
"ɮ": [
|
| 261 |
-
78
|
| 262 |
-
],
|
| 263 |
-
"ɯ": [
|
| 264 |
-
79
|
| 265 |
-
],
|
| 266 |
-
"ɰ": [
|
| 267 |
-
80
|
| 268 |
-
],
|
| 269 |
-
"ɱ": [
|
| 270 |
-
81
|
| 271 |
-
],
|
| 272 |
-
"ɲ": [
|
| 273 |
-
82
|
| 274 |
-
],
|
| 275 |
-
"ɳ": [
|
| 276 |
-
83
|
| 277 |
-
],
|
| 278 |
-
"ɴ": [
|
| 279 |
-
84
|
| 280 |
-
],
|
| 281 |
-
"ɵ": [
|
| 282 |
-
85
|
| 283 |
-
],
|
| 284 |
-
"ɶ": [
|
| 285 |
-
86
|
| 286 |
-
],
|
| 287 |
-
"ɸ": [
|
| 288 |
-
87
|
| 289 |
-
],
|
| 290 |
-
"ɹ": [
|
| 291 |
-
88
|
| 292 |
-
],
|
| 293 |
-
"ɺ": [
|
| 294 |
-
89
|
| 295 |
-
],
|
| 296 |
-
"ɻ": [
|
| 297 |
-
90
|
| 298 |
-
],
|
| 299 |
-
"ɽ": [
|
| 300 |
-
91
|
| 301 |
-
],
|
| 302 |
-
"ɾ": [
|
| 303 |
-
92
|
| 304 |
-
],
|
| 305 |
-
"ʀ": [
|
| 306 |
-
93
|
| 307 |
-
],
|
| 308 |
-
"ʁ": [
|
| 309 |
-
94
|
| 310 |
-
],
|
| 311 |
-
"ʂ": [
|
| 312 |
-
95
|
| 313 |
-
],
|
| 314 |
-
"ʃ": [
|
| 315 |
-
96
|
| 316 |
-
],
|
| 317 |
-
"ʄ": [
|
| 318 |
-
97
|
| 319 |
-
],
|
| 320 |
-
"ʈ": [
|
| 321 |
-
98
|
| 322 |
-
],
|
| 323 |
-
"ʉ": [
|
| 324 |
-
99
|
| 325 |
-
],
|
| 326 |
-
"ʊ": [
|
| 327 |
-
100
|
| 328 |
-
],
|
| 329 |
-
"ʋ": [
|
| 330 |
-
101
|
| 331 |
-
],
|
| 332 |
-
"ʌ": [
|
| 333 |
-
102
|
| 334 |
-
],
|
| 335 |
-
"ʍ": [
|
| 336 |
-
103
|
| 337 |
-
],
|
| 338 |
-
"ʎ": [
|
| 339 |
-
104
|
| 340 |
-
],
|
| 341 |
-
"ʏ": [
|
| 342 |
-
105
|
| 343 |
-
],
|
| 344 |
-
"ʐ": [
|
| 345 |
-
106
|
| 346 |
-
],
|
| 347 |
-
"ʑ": [
|
| 348 |
-
107
|
| 349 |
-
],
|
| 350 |
-
"ʒ": [
|
| 351 |
-
108
|
| 352 |
-
],
|
| 353 |
-
"ʔ": [
|
| 354 |
-
109
|
| 355 |
-
],
|
| 356 |
-
"ʕ": [
|
| 357 |
-
110
|
| 358 |
-
],
|
| 359 |
-
"ʘ": [
|
| 360 |
-
111
|
| 361 |
-
],
|
| 362 |
-
"ʙ": [
|
| 363 |
-
112
|
| 364 |
-
],
|
| 365 |
-
"ʛ": [
|
| 366 |
-
113
|
| 367 |
-
],
|
| 368 |
-
"ʜ": [
|
| 369 |
-
114
|
| 370 |
-
],
|
| 371 |
-
"ʝ": [
|
| 372 |
-
115
|
| 373 |
-
],
|
| 374 |
-
"ʟ": [
|
| 375 |
-
116
|
| 376 |
-
],
|
| 377 |
-
"ʡ": [
|
| 378 |
-
117
|
| 379 |
-
],
|
| 380 |
-
"ʢ": [
|
| 381 |
-
118
|
| 382 |
-
],
|
| 383 |
-
"ʲ": [
|
| 384 |
-
119
|
| 385 |
-
],
|
| 386 |
-
"ˈ": [
|
| 387 |
-
120
|
| 388 |
-
],
|
| 389 |
-
"ˌ": [
|
| 390 |
-
121
|
| 391 |
-
],
|
| 392 |
-
"ː": [
|
| 393 |
-
122
|
| 394 |
-
],
|
| 395 |
-
"ˑ": [
|
| 396 |
-
123
|
| 397 |
-
],
|
| 398 |
-
"˞": [
|
| 399 |
-
124
|
| 400 |
-
],
|
| 401 |
-
"β": [
|
| 402 |
-
125
|
| 403 |
-
],
|
| 404 |
-
"θ": [
|
| 405 |
-
126
|
| 406 |
-
],
|
| 407 |
-
"χ": [
|
| 408 |
-
127
|
| 409 |
-
],
|
| 410 |
-
"ᵻ": [
|
| 411 |
-
128
|
| 412 |
-
],
|
| 413 |
-
"ⱱ": [
|
| 414 |
-
129
|
| 415 |
-
],
|
| 416 |
-
"0": [
|
| 417 |
-
130
|
| 418 |
-
],
|
| 419 |
-
"1": [
|
| 420 |
-
131
|
| 421 |
-
],
|
| 422 |
-
"2": [
|
| 423 |
-
132
|
| 424 |
-
],
|
| 425 |
-
"3": [
|
| 426 |
-
133
|
| 427 |
-
],
|
| 428 |
-
"4": [
|
| 429 |
-
134
|
| 430 |
-
],
|
| 431 |
-
"5": [
|
| 432 |
-
135
|
| 433 |
-
],
|
| 434 |
-
"6": [
|
| 435 |
-
136
|
| 436 |
-
],
|
| 437 |
-
"7": [
|
| 438 |
-
137
|
| 439 |
-
],
|
| 440 |
-
"8": [
|
| 441 |
-
138
|
| 442 |
-
],
|
| 443 |
-
"9": [
|
| 444 |
-
139
|
| 445 |
-
],
|
| 446 |
-
"̧": [
|
| 447 |
-
140
|
| 448 |
-
],
|
| 449 |
-
"̃": [
|
| 450 |
-
141
|
| 451 |
-
],
|
| 452 |
-
"̪": [
|
| 453 |
-
142
|
| 454 |
-
],
|
| 455 |
-
"̯": [
|
| 456 |
-
143
|
| 457 |
-
],
|
| 458 |
-
"̩": [
|
| 459 |
-
144
|
| 460 |
-
],
|
| 461 |
-
"ʰ": [
|
| 462 |
-
145
|
| 463 |
-
],
|
| 464 |
-
"ˤ": [
|
| 465 |
-
146
|
| 466 |
-
],
|
| 467 |
-
"ε": [
|
| 468 |
-
147
|
| 469 |
-
],
|
| 470 |
-
"↓": [
|
| 471 |
-
148
|
| 472 |
-
],
|
| 473 |
-
"#": [
|
| 474 |
-
149
|
| 475 |
-
],
|
| 476 |
-
"\"": [
|
| 477 |
-
150
|
| 478 |
-
],
|
| 479 |
-
"↑": [
|
| 480 |
-
151
|
| 481 |
-
],
|
| 482 |
-
"̺": [
|
| 483 |
-
152
|
| 484 |
-
],
|
| 485 |
-
"̻": [
|
| 486 |
-
153
|
| 487 |
-
],
|
| 488 |
-
"g": [
|
| 489 |
-
154
|
| 490 |
-
],
|
| 491 |
-
"ʦ": [
|
| 492 |
-
155
|
| 493 |
-
],
|
| 494 |
-
"X": [
|
| 495 |
-
156
|
| 496 |
-
],
|
| 497 |
-
"̝": [
|
| 498 |
-
157
|
| 499 |
-
],
|
| 500 |
-
"̊": [
|
| 501 |
-
158
|
| 502 |
-
],
|
| 503 |
-
"ɝ": [
|
| 504 |
-
159
|
| 505 |
-
],
|
| 506 |
-
"ʷ": [
|
| 507 |
-
160
|
| 508 |
-
]
|
| 509 |
-
},
|
| 510 |
-
"speaker_id_map": {},
|
| 511 |
-
"hop_length": 256,
|
| 512 |
-
"piper_version": "1.3.0",
|
| 513 |
-
"dataset": "maider"
|
| 514 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eu/eu_ES/maider/medium/samples/speaker_0.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6ab9356afad3d48ddbd56e43fc6d480ac0fa2ab820d2e8e4b2f805bbf19b653e
|
| 3 |
-
size 132411
|
|
|
|
|
|
|
|
|
|
|
|
hu/hu_HU/anna/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
hu/hu_HU/berta/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
hu/hu_HU/imre/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
ku/ku_TR/berfin_renas/medium/MODEL_CARD
DELETED
|
@@ -1,142 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
language:
|
| 3 |
-
- ku
|
| 4 |
-
license: cc-by-nc-4.0
|
| 5 |
-
tags:
|
| 6 |
-
- text-to-speech
|
| 7 |
-
- tts
|
| 8 |
-
- piper
|
| 9 |
-
- kurdish
|
| 10 |
-
- kurmanji
|
| 11 |
-
- vits
|
| 12 |
-
datasets:
|
| 13 |
-
- berfin_renas
|
| 14 |
-
metrics:
|
| 15 |
-
- wer
|
| 16 |
-
base_model: rhasspy/piper-voices
|
| 17 |
-
pipeline_tag: text-to-speech
|
| 18 |
-
---
|
| 19 |
-
|
| 20 |
-
# Model Card for ku-berfin_renas-medium
|
| 21 |
-
|
| 22 |
-
A multi-speaker Kurmanji Kurdish (Kurmancî) text-to-speech model trained
|
| 23 |
-
with the [Piper TTS](https://github.com/OHF-Voice/piper1) framework.
|
| 24 |
-
Supports two speakers — **Berfin** (speaker 0) and **Renas** (speaker 1) —
|
| 25 |
-
at medium quality and 22,050 Hz sample rate.
|
| 26 |
-
|
| 27 |
-
## Model Details
|
| 28 |
-
|
| 29 |
-
### Model Description
|
| 30 |
-
|
| 31 |
-
- **Developed by:** rojanu
|
| 32 |
-
- **Model type:** VITS (Variational Inference with adversarial learning for
|
| 33 |
-
end-to-end Text-to-Speech)
|
| 34 |
-
- **Language(s):** Kurmanji Kurdish (`ku`)
|
| 35 |
-
- **License:** [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) — free for non-commercial use with attribution; commercial use restricted due to [Blizzard 2013 base model](https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/license.html)
|
| 36 |
-
- **Finetuned from model:** `en_US-lessac-medium` (Piper English vocoder
|
| 37 |
-
warm-start)
|
| 38 |
-
|
| 39 |
-
### Model Sources
|
| 40 |
-
|
| 41 |
-
- **Repository:** [rojanu/piper-ku-berfin-renas-medium](https://huggingface.co/rojanu/piper-ku-berfin-renas-medium)
|
| 42 |
-
- **Framework:** [OHF-Voice/piper1](https://github.com/OHF-Voice/piper1)
|
| 43 |
-
|
| 44 |
-
## Speakers
|
| 45 |
-
|
| 46 |
-
| Speaker ID | Name |
|
| 47 |
-
|------------|--------|
|
| 48 |
-
| 0 | Berfin |
|
| 49 |
-
| 1 | Renas |
|
| 50 |
-
|
| 51 |
-
## Uses
|
| 52 |
-
|
| 53 |
-
### Direct Use
|
| 54 |
-
|
| 55 |
-
Offline, on-device Kurmanji Kurdish speech synthesis. Designed for:
|
| 56 |
-
|
| 57 |
-
- Screen readers (e.g. NVDA with the [piper-nvda addon](https://github.com/mzanm/piper-nvda))
|
| 58 |
-
- Assistive technology
|
| 59 |
-
- Voice interfaces for Kurdish-language applications
|
| 60 |
-
|
| 61 |
-
### Out-of-Scope Use
|
| 62 |
-
|
| 63 |
-
- Languages other than Kurmanji Kurdish
|
| 64 |
-
- High-fidelity / broadcast-quality synthesis (this is a medium-quality model)
|
| 65 |
-
|
| 66 |
-
## How to Get Started with the Model
|
| 67 |
-
|
| 68 |
-
### With Piper CLI
|
| 69 |
-
|
| 70 |
-
```bash
|
| 71 |
-
echo "Silav û rêz ji hemûyan re." | piper \
|
| 72 |
-
--model ku-berfin_renas-medium.onnx \
|
| 73 |
-
--speaker 0 \
|
| 74 |
-
--output_file output.wav
|
| 75 |
-
```
|
| 76 |
-
|
| 77 |
-
### With NVDA
|
| 78 |
-
|
| 79 |
-
Install the [piper-nvda addon](https://github.com/mzanm/piper-nvda) and use
|
| 80 |
-
the direct download URL:
|
| 81 |
-
|
| 82 |
-
```
|
| 83 |
-
https://huggingface.co/rojanu/piper-ku-berfin-renas-medium/resolve/main/ku-berfin_renas-medium.tar.gz
|
| 84 |
-
```
|
| 85 |
-
|
| 86 |
-
## Training Details
|
| 87 |
-
|
| 88 |
-
### Training Data
|
| 89 |
-
|
| 90 |
-
A private dataset of two Kurmanji Kurdish speakers (**Berfin** and **Renas**),
|
| 91 |
-
approximately 2.72 hours total (1.32h Berfin, 1.40h Renas), recorded at
|
| 92 |
-
22,050 Hz.
|
| 93 |
-
|
| 94 |
-
| Speaker | Files | Duration |
|
| 95 |
-
|---------|-------|-----------|
|
| 96 |
-
| Berfin | 1,022 | 1.32 hours |
|
| 97 |
-
| Renas | 1,024 | 1.40 hours |
|
| 98 |
-
| **Total** | **2,046** | **2.72 hours** |
|
| 99 |
-
|
| 100 |
-
### Training Procedure
|
| 101 |
-
|
| 102 |
-
#### Preprocessing
|
| 103 |
-
|
| 104 |
-
- Audio normalised to 22,050 Hz mono WAV
|
| 105 |
-
- Text phonemized via `espeak-ng` with voice `ku`
|
| 106 |
-
- Average utterance duration: ~4.79 seconds
|
| 107 |
-
|
| 108 |
-
#### Training Hyperparameters
|
| 109 |
-
|
| 110 |
-
- **Training regime:** fp32
|
| 111 |
-
- **Framework:** Piper / PyTorch Lightning
|
| 112 |
-
- **Base checkpoint:** `en_US-lessac-medium` (vocoder warm-start)
|
| 113 |
-
- **Batch size:** 32
|
| 114 |
-
- **Max epochs:** 929 (training stopped; best validation at ~epoch 72)
|
| 115 |
-
- **Hardware:** AMD ROCm GPU
|
| 116 |
-
- **Validation split:** 5%
|
| 117 |
-
|
| 118 |
-
## Evaluation
|
| 119 |
-
|
| 120 |
-
### Results
|
| 121 |
-
|
| 122 |
-
The model shows signs of overfitting due to the small dataset (~2.7h total).
|
| 123 |
-
Best validation loss was achieved at approximately epoch 72. Audio quality is
|
| 124 |
-
intelligible but benefits from additional training data.
|
| 125 |
-
|
| 126 |
-
**Known limitations:**
|
| 127 |
-
- Dataset too small for high-quality multi-speaker TTS (recommend ≥ 3h per speaker)
|
| 128 |
-
- Overfitting observed after epoch ~72
|
| 129 |
-
|
| 130 |
-
## Technical Specifications
|
| 131 |
-
|
| 132 |
-
### Model Architecture
|
| 133 |
-
|
| 134 |
-
- **Architecture:** VITS medium
|
| 135 |
-
- **Sample rate:** 22,050 Hz
|
| 136 |
-
- **Phoneme type:** espeak (`ku`)
|
| 137 |
-
- **Number of speakers:** 2
|
| 138 |
-
- **Model size:** ~77 MB (ONNX)
|
| 139 |
-
|
| 140 |
-
## Model Card Authors
|
| 141 |
-
|
| 142 |
-
rojanu
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ku/ku_TR/berfin_renas/medium/ku_TR-berfin_renas-medium.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bc0b2cf086f9a33ca1d7ca2ca80b6f35f8917d0c89afe4a645c5b9d56ac355c4
|
| 3 |
-
size 77060307
|
|
|
|
|
|
|
|
|
|
|
|
ku/ku_TR/berfin_renas/medium/ku_TR-berfin_renas-medium.onnx.json
DELETED
|
@@ -1,517 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"audio": {
|
| 3 |
-
"sample_rate": 22050,
|
| 4 |
-
"quality": "medium"
|
| 5 |
-
},
|
| 6 |
-
"espeak": {
|
| 7 |
-
"voice": "ku"
|
| 8 |
-
},
|
| 9 |
-
"language": {
|
| 10 |
-
"code": "ku_TR",
|
| 11 |
-
"family": "ku",
|
| 12 |
-
"region": "KTR",
|
| 13 |
-
"name_native": "Kurmancî",
|
| 14 |
-
"name_english": "Kurmanji Kurdish",
|
| 15 |
-
"country_english": "Turkey"
|
| 16 |
-
},
|
| 17 |
-
"phoneme_type": "espeak",
|
| 18 |
-
"num_symbols": 256,
|
| 19 |
-
"num_speakers": 2,
|
| 20 |
-
"inference": {
|
| 21 |
-
"noise_scale": 0.667,
|
| 22 |
-
"length_scale": 1.0,
|
| 23 |
-
"noise_w": 0.8
|
| 24 |
-
},
|
| 25 |
-
"phoneme_id_map": {
|
| 26 |
-
"_": [
|
| 27 |
-
0
|
| 28 |
-
],
|
| 29 |
-
"^": [
|
| 30 |
-
1
|
| 31 |
-
],
|
| 32 |
-
"$": [
|
| 33 |
-
2
|
| 34 |
-
],
|
| 35 |
-
" ": [
|
| 36 |
-
3
|
| 37 |
-
],
|
| 38 |
-
"!": [
|
| 39 |
-
4
|
| 40 |
-
],
|
| 41 |
-
"'": [
|
| 42 |
-
5
|
| 43 |
-
],
|
| 44 |
-
"(": [
|
| 45 |
-
6
|
| 46 |
-
],
|
| 47 |
-
")": [
|
| 48 |
-
7
|
| 49 |
-
],
|
| 50 |
-
",": [
|
| 51 |
-
8
|
| 52 |
-
],
|
| 53 |
-
"-": [
|
| 54 |
-
9
|
| 55 |
-
],
|
| 56 |
-
".": [
|
| 57 |
-
10
|
| 58 |
-
],
|
| 59 |
-
":": [
|
| 60 |
-
11
|
| 61 |
-
],
|
| 62 |
-
";": [
|
| 63 |
-
12
|
| 64 |
-
],
|
| 65 |
-
"?": [
|
| 66 |
-
13
|
| 67 |
-
],
|
| 68 |
-
"a": [
|
| 69 |
-
14
|
| 70 |
-
],
|
| 71 |
-
"b": [
|
| 72 |
-
15
|
| 73 |
-
],
|
| 74 |
-
"c": [
|
| 75 |
-
16
|
| 76 |
-
],
|
| 77 |
-
"d": [
|
| 78 |
-
17
|
| 79 |
-
],
|
| 80 |
-
"e": [
|
| 81 |
-
18
|
| 82 |
-
],
|
| 83 |
-
"f": [
|
| 84 |
-
19
|
| 85 |
-
],
|
| 86 |
-
"h": [
|
| 87 |
-
20
|
| 88 |
-
],
|
| 89 |
-
"i": [
|
| 90 |
-
21
|
| 91 |
-
],
|
| 92 |
-
"j": [
|
| 93 |
-
22
|
| 94 |
-
],
|
| 95 |
-
"k": [
|
| 96 |
-
23
|
| 97 |
-
],
|
| 98 |
-
"l": [
|
| 99 |
-
24
|
| 100 |
-
],
|
| 101 |
-
"m": [
|
| 102 |
-
25
|
| 103 |
-
],
|
| 104 |
-
"n": [
|
| 105 |
-
26
|
| 106 |
-
],
|
| 107 |
-
"o": [
|
| 108 |
-
27
|
| 109 |
-
],
|
| 110 |
-
"p": [
|
| 111 |
-
28
|
| 112 |
-
],
|
| 113 |
-
"q": [
|
| 114 |
-
29
|
| 115 |
-
],
|
| 116 |
-
"r": [
|
| 117 |
-
30
|
| 118 |
-
],
|
| 119 |
-
"s": [
|
| 120 |
-
31
|
| 121 |
-
],
|
| 122 |
-
"t": [
|
| 123 |
-
32
|
| 124 |
-
],
|
| 125 |
-
"u": [
|
| 126 |
-
33
|
| 127 |
-
],
|
| 128 |
-
"v": [
|
| 129 |
-
34
|
| 130 |
-
],
|
| 131 |
-
"w": [
|
| 132 |
-
35
|
| 133 |
-
],
|
| 134 |
-
"x": [
|
| 135 |
-
36
|
| 136 |
-
],
|
| 137 |
-
"y": [
|
| 138 |
-
37
|
| 139 |
-
],
|
| 140 |
-
"z": [
|
| 141 |
-
38
|
| 142 |
-
],
|
| 143 |
-
"æ": [
|
| 144 |
-
39
|
| 145 |
-
],
|
| 146 |
-
"ç": [
|
| 147 |
-
40
|
| 148 |
-
],
|
| 149 |
-
"ð": [
|
| 150 |
-
41
|
| 151 |
-
],
|
| 152 |
-
"ø": [
|
| 153 |
-
42
|
| 154 |
-
],
|
| 155 |
-
"ħ": [
|
| 156 |
-
43
|
| 157 |
-
],
|
| 158 |
-
"ŋ": [
|
| 159 |
-
44
|
| 160 |
-
],
|
| 161 |
-
"œ": [
|
| 162 |
-
45
|
| 163 |
-
],
|
| 164 |
-
"ǀ": [
|
| 165 |
-
46
|
| 166 |
-
],
|
| 167 |
-
"ǁ": [
|
| 168 |
-
47
|
| 169 |
-
],
|
| 170 |
-
"ǂ": [
|
| 171 |
-
48
|
| 172 |
-
],
|
| 173 |
-
"ǃ": [
|
| 174 |
-
49
|
| 175 |
-
],
|
| 176 |
-
"ɐ": [
|
| 177 |
-
50
|
| 178 |
-
],
|
| 179 |
-
"ɑ": [
|
| 180 |
-
51
|
| 181 |
-
],
|
| 182 |
-
"ɒ": [
|
| 183 |
-
52
|
| 184 |
-
],
|
| 185 |
-
"ɓ": [
|
| 186 |
-
53
|
| 187 |
-
],
|
| 188 |
-
"ɔ": [
|
| 189 |
-
54
|
| 190 |
-
],
|
| 191 |
-
"ɕ": [
|
| 192 |
-
55
|
| 193 |
-
],
|
| 194 |
-
"ɖ": [
|
| 195 |
-
56
|
| 196 |
-
],
|
| 197 |
-
"ɗ": [
|
| 198 |
-
57
|
| 199 |
-
],
|
| 200 |
-
"ɘ": [
|
| 201 |
-
58
|
| 202 |
-
],
|
| 203 |
-
"ə": [
|
| 204 |
-
59
|
| 205 |
-
],
|
| 206 |
-
"ɚ": [
|
| 207 |
-
60
|
| 208 |
-
],
|
| 209 |
-
"ɛ": [
|
| 210 |
-
61
|
| 211 |
-
],
|
| 212 |
-
"ɜ": [
|
| 213 |
-
62
|
| 214 |
-
],
|
| 215 |
-
"ɞ": [
|
| 216 |
-
63
|
| 217 |
-
],
|
| 218 |
-
"ɟ": [
|
| 219 |
-
64
|
| 220 |
-
],
|
| 221 |
-
"ɠ": [
|
| 222 |
-
65
|
| 223 |
-
],
|
| 224 |
-
"ɡ": [
|
| 225 |
-
66
|
| 226 |
-
],
|
| 227 |
-
"ɢ": [
|
| 228 |
-
67
|
| 229 |
-
],
|
| 230 |
-
"ɣ": [
|
| 231 |
-
68
|
| 232 |
-
],
|
| 233 |
-
"ɤ": [
|
| 234 |
-
69
|
| 235 |
-
],
|
| 236 |
-
"ɥ": [
|
| 237 |
-
70
|
| 238 |
-
],
|
| 239 |
-
"ɦ": [
|
| 240 |
-
71
|
| 241 |
-
],
|
| 242 |
-
"ɧ": [
|
| 243 |
-
72
|
| 244 |
-
],
|
| 245 |
-
"ɨ": [
|
| 246 |
-
73
|
| 247 |
-
],
|
| 248 |
-
"ɪ": [
|
| 249 |
-
74
|
| 250 |
-
],
|
| 251 |
-
"ɫ": [
|
| 252 |
-
75
|
| 253 |
-
],
|
| 254 |
-
"ɬ": [
|
| 255 |
-
76
|
| 256 |
-
],
|
| 257 |
-
"ɭ": [
|
| 258 |
-
77
|
| 259 |
-
],
|
| 260 |
-
"ɮ": [
|
| 261 |
-
78
|
| 262 |
-
],
|
| 263 |
-
"ɯ": [
|
| 264 |
-
79
|
| 265 |
-
],
|
| 266 |
-
"ɰ": [
|
| 267 |
-
80
|
| 268 |
-
],
|
| 269 |
-
"ɱ": [
|
| 270 |
-
81
|
| 271 |
-
],
|
| 272 |
-
"ɲ": [
|
| 273 |
-
82
|
| 274 |
-
],
|
| 275 |
-
"ɳ": [
|
| 276 |
-
83
|
| 277 |
-
],
|
| 278 |
-
"ɴ": [
|
| 279 |
-
84
|
| 280 |
-
],
|
| 281 |
-
"ɵ": [
|
| 282 |
-
85
|
| 283 |
-
],
|
| 284 |
-
"ɶ": [
|
| 285 |
-
86
|
| 286 |
-
],
|
| 287 |
-
"ɸ": [
|
| 288 |
-
87
|
| 289 |
-
],
|
| 290 |
-
"ɹ": [
|
| 291 |
-
88
|
| 292 |
-
],
|
| 293 |
-
"ɺ": [
|
| 294 |
-
89
|
| 295 |
-
],
|
| 296 |
-
"ɻ": [
|
| 297 |
-
90
|
| 298 |
-
],
|
| 299 |
-
"ɽ": [
|
| 300 |
-
91
|
| 301 |
-
],
|
| 302 |
-
"ɾ": [
|
| 303 |
-
92
|
| 304 |
-
],
|
| 305 |
-
"ʀ": [
|
| 306 |
-
93
|
| 307 |
-
],
|
| 308 |
-
"ʁ": [
|
| 309 |
-
94
|
| 310 |
-
],
|
| 311 |
-
"ʂ": [
|
| 312 |
-
95
|
| 313 |
-
],
|
| 314 |
-
"ʃ": [
|
| 315 |
-
96
|
| 316 |
-
],
|
| 317 |
-
"ʄ": [
|
| 318 |
-
97
|
| 319 |
-
],
|
| 320 |
-
"ʈ": [
|
| 321 |
-
98
|
| 322 |
-
],
|
| 323 |
-
"ʉ": [
|
| 324 |
-
99
|
| 325 |
-
],
|
| 326 |
-
"ʊ": [
|
| 327 |
-
100
|
| 328 |
-
],
|
| 329 |
-
"ʋ": [
|
| 330 |
-
101
|
| 331 |
-
],
|
| 332 |
-
"ʌ": [
|
| 333 |
-
102
|
| 334 |
-
],
|
| 335 |
-
"ʍ": [
|
| 336 |
-
103
|
| 337 |
-
],
|
| 338 |
-
"ʎ": [
|
| 339 |
-
104
|
| 340 |
-
],
|
| 341 |
-
"ʏ": [
|
| 342 |
-
105
|
| 343 |
-
],
|
| 344 |
-
"ʐ": [
|
| 345 |
-
106
|
| 346 |
-
],
|
| 347 |
-
"ʑ": [
|
| 348 |
-
107
|
| 349 |
-
],
|
| 350 |
-
"ʒ": [
|
| 351 |
-
108
|
| 352 |
-
],
|
| 353 |
-
"ʔ": [
|
| 354 |
-
109
|
| 355 |
-
],
|
| 356 |
-
"ʕ": [
|
| 357 |
-
110
|
| 358 |
-
],
|
| 359 |
-
"ʘ": [
|
| 360 |
-
111
|
| 361 |
-
],
|
| 362 |
-
"ʙ": [
|
| 363 |
-
112
|
| 364 |
-
],
|
| 365 |
-
"ʛ": [
|
| 366 |
-
113
|
| 367 |
-
],
|
| 368 |
-
"ʜ": [
|
| 369 |
-
114
|
| 370 |
-
],
|
| 371 |
-
"ʝ": [
|
| 372 |
-
115
|
| 373 |
-
],
|
| 374 |
-
"ʟ": [
|
| 375 |
-
116
|
| 376 |
-
],
|
| 377 |
-
"ʡ": [
|
| 378 |
-
117
|
| 379 |
-
],
|
| 380 |
-
"ʢ": [
|
| 381 |
-
118
|
| 382 |
-
],
|
| 383 |
-
"ʲ": [
|
| 384 |
-
119
|
| 385 |
-
],
|
| 386 |
-
"ˈ": [
|
| 387 |
-
120
|
| 388 |
-
],
|
| 389 |
-
"ˌ": [
|
| 390 |
-
121
|
| 391 |
-
],
|
| 392 |
-
"ː": [
|
| 393 |
-
122
|
| 394 |
-
],
|
| 395 |
-
"ˑ": [
|
| 396 |
-
123
|
| 397 |
-
],
|
| 398 |
-
"˞": [
|
| 399 |
-
124
|
| 400 |
-
],
|
| 401 |
-
"β": [
|
| 402 |
-
125
|
| 403 |
-
],
|
| 404 |
-
"θ": [
|
| 405 |
-
126
|
| 406 |
-
],
|
| 407 |
-
"χ": [
|
| 408 |
-
127
|
| 409 |
-
],
|
| 410 |
-
"ᵻ": [
|
| 411 |
-
128
|
| 412 |
-
],
|
| 413 |
-
"ⱱ": [
|
| 414 |
-
129
|
| 415 |
-
],
|
| 416 |
-
"0": [
|
| 417 |
-
130
|
| 418 |
-
],
|
| 419 |
-
"1": [
|
| 420 |
-
131
|
| 421 |
-
],
|
| 422 |
-
"2": [
|
| 423 |
-
132
|
| 424 |
-
],
|
| 425 |
-
"3": [
|
| 426 |
-
133
|
| 427 |
-
],
|
| 428 |
-
"4": [
|
| 429 |
-
134
|
| 430 |
-
],
|
| 431 |
-
"5": [
|
| 432 |
-
135
|
| 433 |
-
],
|
| 434 |
-
"6": [
|
| 435 |
-
136
|
| 436 |
-
],
|
| 437 |
-
"7": [
|
| 438 |
-
137
|
| 439 |
-
],
|
| 440 |
-
"8": [
|
| 441 |
-
138
|
| 442 |
-
],
|
| 443 |
-
"9": [
|
| 444 |
-
139
|
| 445 |
-
],
|
| 446 |
-
"̧": [
|
| 447 |
-
140
|
| 448 |
-
],
|
| 449 |
-
"̃": [
|
| 450 |
-
141
|
| 451 |
-
],
|
| 452 |
-
"̪": [
|
| 453 |
-
142
|
| 454 |
-
],
|
| 455 |
-
"̯": [
|
| 456 |
-
143
|
| 457 |
-
],
|
| 458 |
-
"̩": [
|
| 459 |
-
144
|
| 460 |
-
],
|
| 461 |
-
"ʰ": [
|
| 462 |
-
145
|
| 463 |
-
],
|
| 464 |
-
"ˤ": [
|
| 465 |
-
146
|
| 466 |
-
],
|
| 467 |
-
"ε": [
|
| 468 |
-
147
|
| 469 |
-
],
|
| 470 |
-
"↓": [
|
| 471 |
-
148
|
| 472 |
-
],
|
| 473 |
-
"#": [
|
| 474 |
-
149
|
| 475 |
-
],
|
| 476 |
-
"\"": [
|
| 477 |
-
150
|
| 478 |
-
],
|
| 479 |
-
"↑": [
|
| 480 |
-
151
|
| 481 |
-
],
|
| 482 |
-
"̺": [
|
| 483 |
-
152
|
| 484 |
-
],
|
| 485 |
-
"̻": [
|
| 486 |
-
153
|
| 487 |
-
],
|
| 488 |
-
"g": [
|
| 489 |
-
154
|
| 490 |
-
],
|
| 491 |
-
"ʦ": [
|
| 492 |
-
155
|
| 493 |
-
],
|
| 494 |
-
"X": [
|
| 495 |
-
156
|
| 496 |
-
],
|
| 497 |
-
"̝": [
|
| 498 |
-
157
|
| 499 |
-
],
|
| 500 |
-
"̊": [
|
| 501 |
-
158
|
| 502 |
-
],
|
| 503 |
-
"ɝ": [
|
| 504 |
-
159
|
| 505 |
-
],
|
| 506 |
-
"ʷ": [
|
| 507 |
-
160
|
| 508 |
-
]
|
| 509 |
-
},
|
| 510 |
-
"speaker_id_map": {
|
| 511 |
-
"Berfin": 0,
|
| 512 |
-
"Renas": 1
|
| 513 |
-
},
|
| 514 |
-
"hop_length": 256,
|
| 515 |
-
"piper_version": "1.3.0",
|
| 516 |
-
"dataset": "berfin_renas"
|
| 517 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ku/ku_TR/berfin_renas/medium/samples/speaker_1.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f74e7cc9ceda8e5856c3e57c13591ac5f5d515bda017b66b9b38ff099f9ad343
|
| 3 |
-
size 239019
|
|
|
|
|
|
|
|
|
|
|
|
ne/ne_NP/chitwan/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
nl/nl_NL/alex/medium/MODEL_CARD
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
# Model card for alex (medium)
|
| 2 |
-
|
| 3 |
-
* Language: nl_NL (Dutch, Netherlands)
|
| 4 |
-
* Speakers: 1
|
| 5 |
-
* Quality: medium
|
| 6 |
-
* Samplerate: 22,050Hz
|
| 7 |
-
|
| 8 |
-
## Dataset
|
| 9 |
-
|
| 10 |
-
* URL: https://github.com/OHF-Voice/voice-datasets
|
| 11 |
-
* License: CC0
|
| 12 |
-
|
| 13 |
-
## Training
|
| 14 |
-
|
| 15 |
-
Finetuned from Dutch rdh voice (medium quality)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
nl/nl_NL/alex/medium/nl_NL-alex-medium.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:22f0497c4d895a09fbc6a469459aa8954ea0955d3c6e19dbcc2e23acbb93e30b
|
| 3 |
-
size 63531476
|
|
|
|
|
|
|
|
|
|
|
|
nl/nl_NL/alex/medium/samples/speaker_0.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:db2e16504081bd17b3b586144e7a655de0cbbc497c4ce80618d537feeff51eed
|
| 3 |
-
size 90673
|
|
|
|
|
|
|
|
|
|
|
|
nl/nl_NL/pim/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
nl/nl_NL/ronnie/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pl/pl_PL/bass/high/MODEL_CARD
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
# Model card for pl_PL-bass-high
|
| 2 |
-
|
| 3 |
-
Polish (pl_PL) male voice, high quality.
|
| 4 |
-
|
| 5 |
-
Fine-tuned from en_US-lessac-high on ~10,000 segments of Polish speech.
|
| 6 |
-
|
| 7 |
-
## Samples
|
| 8 |
-
|
| 9 |
-
https://huggingface.co/blackbartblues/piper-pl-bass-high
|
| 10 |
-
|
| 11 |
-
## License
|
| 12 |
-
|
| 13 |
-
[Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pl/pl_PL/bass/high/pl_PL-bass-high.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:73b8408967c58118700f21eb2413cd8b666c7844c6136cf674bf5dd56bde72c2
|
| 3 |
-
size 114204024
|
|
|
|
|
|
|
|
|
|
|
|
pl/pl_PL/bass/high/samples/speaker_0.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c8590a49267903f5011cbff5721f4058c3fa4c4829915d19283faa74c07717b1
|
| 3 |
-
size 175556
|
|
|
|
|
|
|
|
|
|
|
|
pl/pl_PL/darkman/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pl/pl_PL/gosia/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pt/pt_BR/cadu/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pt/pt_BR/faber/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pt/pt_BR/jeff/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
pt/pt_PT/tugão/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
ro/ro_RO/mihai/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
ru/ru_RU/denis/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
ru/ru_RU/dmitri/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
sk/sk_SK/lili/medium/MODEL_CARD
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
|
|
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
+
* URL: https://github.com/NabuCasa/voice-datasets
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
sq/sq_AL/edon/medium/samples/speaker_0.mp3
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8e18da8bd20ee3deb2a7ef1afc5fd36f6e2a073c24cfa81c032ea15d7b33fc51
|
| 3 |
-
size 166111
|
|
|
|
|
|
|
|
|
|
|
|
sq/sq_AL/edon/medium/sq_AL-edon-medium.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5d0ae8af36a00ac6813517b2af47bc4cda42e88ece04f6076ae3b0f5479c57c8
|
| 3 |
-
size 63511038
|
|
|
|
|
|
|
|
|
|
|
|
sq/sq_AL/edon/medium/sq_AL-edon-medium.onnx.json
DELETED
|
@@ -1,502 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"dataset": "edon",
|
| 3 |
-
"audio": {
|
| 4 |
-
"sample_rate": 22050,
|
| 5 |
-
"quality": "medium"
|
| 6 |
-
},
|
| 7 |
-
"espeak": {
|
| 8 |
-
"voice": "sq"
|
| 9 |
-
},
|
| 10 |
-
"language": {
|
| 11 |
-
"code": "sq_AL",
|
| 12 |
-
"family": "sq",
|
| 13 |
-
"region": "AL",
|
| 14 |
-
"name_native": "shqip",
|
| 15 |
-
"name_english": "Albanian",
|
| 16 |
-
"country_english": "Albania"
|
| 17 |
-
},
|
| 18 |
-
"inference": {
|
| 19 |
-
"noise_scale": 0.667,
|
| 20 |
-
"length_scale": 1.1,
|
| 21 |
-
"noise_w": 0.8
|
| 22 |
-
},
|
| 23 |
-
"phoneme_type": "espeak",
|
| 24 |
-
"phoneme_map": {},
|
| 25 |
-
"phoneme_id_map": {
|
| 26 |
-
" ": [
|
| 27 |
-
3
|
| 28 |
-
],
|
| 29 |
-
"!": [
|
| 30 |
-
4
|
| 31 |
-
],
|
| 32 |
-
"\"": [
|
| 33 |
-
150
|
| 34 |
-
],
|
| 35 |
-
"#": [
|
| 36 |
-
149
|
| 37 |
-
],
|
| 38 |
-
"$": [
|
| 39 |
-
2
|
| 40 |
-
],
|
| 41 |
-
"'": [
|
| 42 |
-
5
|
| 43 |
-
],
|
| 44 |
-
"(": [
|
| 45 |
-
6
|
| 46 |
-
],
|
| 47 |
-
")": [
|
| 48 |
-
7
|
| 49 |
-
],
|
| 50 |
-
",": [
|
| 51 |
-
8
|
| 52 |
-
],
|
| 53 |
-
"-": [
|
| 54 |
-
9
|
| 55 |
-
],
|
| 56 |
-
".": [
|
| 57 |
-
10
|
| 58 |
-
],
|
| 59 |
-
"0": [
|
| 60 |
-
130
|
| 61 |
-
],
|
| 62 |
-
"1": [
|
| 63 |
-
131
|
| 64 |
-
],
|
| 65 |
-
"2": [
|
| 66 |
-
132
|
| 67 |
-
],
|
| 68 |
-
"3": [
|
| 69 |
-
133
|
| 70 |
-
],
|
| 71 |
-
"4": [
|
| 72 |
-
134
|
| 73 |
-
],
|
| 74 |
-
"5": [
|
| 75 |
-
135
|
| 76 |
-
],
|
| 77 |
-
"6": [
|
| 78 |
-
136
|
| 79 |
-
],
|
| 80 |
-
"7": [
|
| 81 |
-
137
|
| 82 |
-
],
|
| 83 |
-
"8": [
|
| 84 |
-
138
|
| 85 |
-
],
|
| 86 |
-
"9": [
|
| 87 |
-
139
|
| 88 |
-
],
|
| 89 |
-
":": [
|
| 90 |
-
11
|
| 91 |
-
],
|
| 92 |
-
";": [
|
| 93 |
-
12
|
| 94 |
-
],
|
| 95 |
-
"?": [
|
| 96 |
-
13
|
| 97 |
-
],
|
| 98 |
-
"X": [
|
| 99 |
-
156
|
| 100 |
-
],
|
| 101 |
-
"^": [
|
| 102 |
-
1
|
| 103 |
-
],
|
| 104 |
-
"_": [
|
| 105 |
-
0
|
| 106 |
-
],
|
| 107 |
-
"a": [
|
| 108 |
-
14
|
| 109 |
-
],
|
| 110 |
-
"b": [
|
| 111 |
-
15
|
| 112 |
-
],
|
| 113 |
-
"c": [
|
| 114 |
-
16
|
| 115 |
-
],
|
| 116 |
-
"d": [
|
| 117 |
-
17
|
| 118 |
-
],
|
| 119 |
-
"e": [
|
| 120 |
-
18
|
| 121 |
-
],
|
| 122 |
-
"f": [
|
| 123 |
-
19
|
| 124 |
-
],
|
| 125 |
-
"g": [
|
| 126 |
-
154
|
| 127 |
-
],
|
| 128 |
-
"h": [
|
| 129 |
-
20
|
| 130 |
-
],
|
| 131 |
-
"i": [
|
| 132 |
-
21
|
| 133 |
-
],
|
| 134 |
-
"j": [
|
| 135 |
-
22
|
| 136 |
-
],
|
| 137 |
-
"k": [
|
| 138 |
-
23
|
| 139 |
-
],
|
| 140 |
-
"l": [
|
| 141 |
-
24
|
| 142 |
-
],
|
| 143 |
-
"m": [
|
| 144 |
-
25
|
| 145 |
-
],
|
| 146 |
-
"n": [
|
| 147 |
-
26
|
| 148 |
-
],
|
| 149 |
-
"o": [
|
| 150 |
-
27
|
| 151 |
-
],
|
| 152 |
-
"p": [
|
| 153 |
-
28
|
| 154 |
-
],
|
| 155 |
-
"q": [
|
| 156 |
-
29
|
| 157 |
-
],
|
| 158 |
-
"r": [
|
| 159 |
-
30
|
| 160 |
-
],
|
| 161 |
-
"s": [
|
| 162 |
-
31
|
| 163 |
-
],
|
| 164 |
-
"t": [
|
| 165 |
-
32
|
| 166 |
-
],
|
| 167 |
-
"u": [
|
| 168 |
-
33
|
| 169 |
-
],
|
| 170 |
-
"v": [
|
| 171 |
-
34
|
| 172 |
-
],
|
| 173 |
-
"w": [
|
| 174 |
-
35
|
| 175 |
-
],
|
| 176 |
-
"x": [
|
| 177 |
-
36
|
| 178 |
-
],
|
| 179 |
-
"y": [
|
| 180 |
-
37
|
| 181 |
-
],
|
| 182 |
-
"z": [
|
| 183 |
-
38
|
| 184 |
-
],
|
| 185 |
-
"æ": [
|
| 186 |
-
39
|
| 187 |
-
],
|
| 188 |
-
"ç": [
|
| 189 |
-
40
|
| 190 |
-
],
|
| 191 |
-
"ð": [
|
| 192 |
-
41
|
| 193 |
-
],
|
| 194 |
-
"ø": [
|
| 195 |
-
42
|
| 196 |
-
],
|
| 197 |
-
"ħ": [
|
| 198 |
-
43
|
| 199 |
-
],
|
| 200 |
-
"ŋ": [
|
| 201 |
-
44
|
| 202 |
-
],
|
| 203 |
-
"œ": [
|
| 204 |
-
45
|
| 205 |
-
],
|
| 206 |
-
"ǀ": [
|
| 207 |
-
46
|
| 208 |
-
],
|
| 209 |
-
"ǁ": [
|
| 210 |
-
47
|
| 211 |
-
],
|
| 212 |
-
"ǂ": [
|
| 213 |
-
48
|
| 214 |
-
],
|
| 215 |
-
"ǃ": [
|
| 216 |
-
49
|
| 217 |
-
],
|
| 218 |
-
"ɐ": [
|
| 219 |
-
50
|
| 220 |
-
],
|
| 221 |
-
"ɑ": [
|
| 222 |
-
51
|
| 223 |
-
],
|
| 224 |
-
"ɒ": [
|
| 225 |
-
52
|
| 226 |
-
],
|
| 227 |
-
"ɓ": [
|
| 228 |
-
53
|
| 229 |
-
],
|
| 230 |
-
"ɔ": [
|
| 231 |
-
54
|
| 232 |
-
],
|
| 233 |
-
"ɕ": [
|
| 234 |
-
55
|
| 235 |
-
],
|
| 236 |
-
"ɖ": [
|
| 237 |
-
56
|
| 238 |
-
],
|
| 239 |
-
"ɗ": [
|
| 240 |
-
57
|
| 241 |
-
],
|
| 242 |
-
"ɘ": [
|
| 243 |
-
58
|
| 244 |
-
],
|
| 245 |
-
"ə": [
|
| 246 |
-
59
|
| 247 |
-
],
|
| 248 |
-
"ɚ": [
|
| 249 |
-
60
|
| 250 |
-
],
|
| 251 |
-
"ɛ": [
|
| 252 |
-
61
|
| 253 |
-
],
|
| 254 |
-
"ɜ": [
|
| 255 |
-
62
|
| 256 |
-
],
|
| 257 |
-
"ɞ": [
|
| 258 |
-
63
|
| 259 |
-
],
|
| 260 |
-
"ɟ": [
|
| 261 |
-
64
|
| 262 |
-
],
|
| 263 |
-
"ɠ": [
|
| 264 |
-
65
|
| 265 |
-
],
|
| 266 |
-
"ɡ": [
|
| 267 |
-
66
|
| 268 |
-
],
|
| 269 |
-
"ɢ": [
|
| 270 |
-
67
|
| 271 |
-
],
|
| 272 |
-
"ɣ": [
|
| 273 |
-
68
|
| 274 |
-
],
|
| 275 |
-
"ɤ": [
|
| 276 |
-
69
|
| 277 |
-
],
|
| 278 |
-
"ɥ": [
|
| 279 |
-
70
|
| 280 |
-
],
|
| 281 |
-
"ɦ": [
|
| 282 |
-
71
|
| 283 |
-
],
|
| 284 |
-
"ɧ": [
|
| 285 |
-
72
|
| 286 |
-
],
|
| 287 |
-
"ɨ": [
|
| 288 |
-
73
|
| 289 |
-
],
|
| 290 |
-
"ɪ": [
|
| 291 |
-
74
|
| 292 |
-
],
|
| 293 |
-
"ɫ": [
|
| 294 |
-
75
|
| 295 |
-
],
|
| 296 |
-
"ɬ": [
|
| 297 |
-
76
|
| 298 |
-
],
|
| 299 |
-
"ɭ": [
|
| 300 |
-
77
|
| 301 |
-
],
|
| 302 |
-
"ɮ": [
|
| 303 |
-
78
|
| 304 |
-
],
|
| 305 |
-
"ɯ": [
|
| 306 |
-
79
|
| 307 |
-
],
|
| 308 |
-
"ɰ": [
|
| 309 |
-
80
|
| 310 |
-
],
|
| 311 |
-
"ɱ": [
|
| 312 |
-
81
|
| 313 |
-
],
|
| 314 |
-
"ɲ": [
|
| 315 |
-
82
|
| 316 |
-
],
|
| 317 |
-
"ɳ": [
|
| 318 |
-
83
|
| 319 |
-
],
|
| 320 |
-
"ɴ": [
|
| 321 |
-
84
|
| 322 |
-
],
|
| 323 |
-
"ɵ": [
|
| 324 |
-
85
|
| 325 |
-
],
|
| 326 |
-
"ɶ": [
|
| 327 |
-
86
|
| 328 |
-
],
|
| 329 |
-
"ɸ": [
|
| 330 |
-
87
|
| 331 |
-
],
|
| 332 |
-
"ɹ": [
|
| 333 |
-
88
|
| 334 |
-
],
|
| 335 |
-
"ɺ": [
|
| 336 |
-
89
|
| 337 |
-
],
|
| 338 |
-
"ɻ": [
|
| 339 |
-
90
|
| 340 |
-
],
|
| 341 |
-
"ɽ": [
|
| 342 |
-
91
|
| 343 |
-
],
|
| 344 |
-
"ɾ": [
|
| 345 |
-
92
|
| 346 |
-
],
|
| 347 |
-
"ʀ": [
|
| 348 |
-
93
|
| 349 |
-
],
|
| 350 |
-
"ʁ": [
|
| 351 |
-
94
|
| 352 |
-
],
|
| 353 |
-
"ʂ": [
|
| 354 |
-
95
|
| 355 |
-
],
|
| 356 |
-
"ʃ": [
|
| 357 |
-
96
|
| 358 |
-
],
|
| 359 |
-
"ʄ": [
|
| 360 |
-
97
|
| 361 |
-
],
|
| 362 |
-
"ʈ": [
|
| 363 |
-
98
|
| 364 |
-
],
|
| 365 |
-
"ʉ": [
|
| 366 |
-
99
|
| 367 |
-
],
|
| 368 |
-
"ʊ": [
|
| 369 |
-
100
|
| 370 |
-
],
|
| 371 |
-
"ʋ": [
|
| 372 |
-
101
|
| 373 |
-
],
|
| 374 |
-
"ʌ": [
|
| 375 |
-
102
|
| 376 |
-
],
|
| 377 |
-
"ʍ": [
|
| 378 |
-
103
|
| 379 |
-
],
|
| 380 |
-
"ʎ": [
|
| 381 |
-
104
|
| 382 |
-
],
|
| 383 |
-
"ʏ": [
|
| 384 |
-
105
|
| 385 |
-
],
|
| 386 |
-
"ʐ": [
|
| 387 |
-
106
|
| 388 |
-
],
|
| 389 |
-
"ʑ": [
|
| 390 |
-
107
|
| 391 |
-
],
|
| 392 |
-
"ʒ": [
|
| 393 |
-
108
|
| 394 |
-
],
|
| 395 |
-
"ʔ": [
|
| 396 |
-
109
|
| 397 |
-
],
|
| 398 |
-
"ʕ": [
|
| 399 |
-
110
|
| 400 |
-
],
|
| 401 |
-
"ʘ": [
|
| 402 |
-
111
|
| 403 |
-
],
|
| 404 |
-
"ʙ": [
|
| 405 |
-
112
|
| 406 |
-
],
|
| 407 |
-
"ʛ": [
|
| 408 |
-
113
|
| 409 |
-
],
|
| 410 |
-
"ʜ": [
|
| 411 |
-
114
|
| 412 |
-
],
|
| 413 |
-
"ʝ": [
|
| 414 |
-
115
|
| 415 |
-
],
|
| 416 |
-
"ʟ": [
|
| 417 |
-
116
|
| 418 |
-
],
|
| 419 |
-
"ʡ": [
|
| 420 |
-
117
|
| 421 |
-
],
|
| 422 |
-
"ʢ": [
|
| 423 |
-
118
|
| 424 |
-
],
|
| 425 |
-
"ʦ": [
|
| 426 |
-
155
|
| 427 |
-
],
|
| 428 |
-
"ʰ": [
|
| 429 |
-
145
|
| 430 |
-
],
|
| 431 |
-
"ʲ": [
|
| 432 |
-
119
|
| 433 |
-
],
|
| 434 |
-
"ˈ": [
|
| 435 |
-
120
|
| 436 |
-
],
|
| 437 |
-
"ˌ": [
|
| 438 |
-
121
|
| 439 |
-
],
|
| 440 |
-
"ː": [
|
| 441 |
-
122
|
| 442 |
-
],
|
| 443 |
-
"ˑ": [
|
| 444 |
-
123
|
| 445 |
-
],
|
| 446 |
-
"˞": [
|
| 447 |
-
124
|
| 448 |
-
],
|
| 449 |
-
"ˤ": [
|
| 450 |
-
146
|
| 451 |
-
],
|
| 452 |
-
"̃": [
|
| 453 |
-
141
|
| 454 |
-
],
|
| 455 |
-
"̧": [
|
| 456 |
-
140
|
| 457 |
-
],
|
| 458 |
-
"̩": [
|
| 459 |
-
144
|
| 460 |
-
],
|
| 461 |
-
"̪": [
|
| 462 |
-
142
|
| 463 |
-
],
|
| 464 |
-
"̯": [
|
| 465 |
-
143
|
| 466 |
-
],
|
| 467 |
-
"̺": [
|
| 468 |
-
152
|
| 469 |
-
],
|
| 470 |
-
"̻": [
|
| 471 |
-
153
|
| 472 |
-
],
|
| 473 |
-
"β": [
|
| 474 |
-
125
|
| 475 |
-
],
|
| 476 |
-
"ε": [
|
| 477 |
-
147
|
| 478 |
-
],
|
| 479 |
-
"θ": [
|
| 480 |
-
126
|
| 481 |
-
],
|
| 482 |
-
"χ": [
|
| 483 |
-
127
|
| 484 |
-
],
|
| 485 |
-
"ᵻ": [
|
| 486 |
-
128
|
| 487 |
-
],
|
| 488 |
-
"↑": [
|
| 489 |
-
151
|
| 490 |
-
],
|
| 491 |
-
"↓": [
|
| 492 |
-
148
|
| 493 |
-
],
|
| 494 |
-
"ⱱ": [
|
| 495 |
-
129
|
| 496 |
-
]
|
| 497 |
-
},
|
| 498 |
-
"num_symbols": 256,
|
| 499 |
-
"num_speakers": 1,
|
| 500 |
-
"speaker_id_map": {},
|
| 501 |
-
"piper_version": "1.0.0"
|
| 502 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sv/sv_SE/alma/medium/MODEL_CARD
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
# Model card for alma (medium)
|
| 2 |
-
|
| 3 |
-
* Language: sv_SE (Swedish, Sweden)
|
| 4 |
-
* Speakers: 1
|
| 5 |
-
* Quality: medium
|
| 6 |
-
* Samplerate: 22,050Hz
|
| 7 |
-
* URL: https://huggingface.co/yeagersthlm/piper-voice-sv-alma
|
| 8 |
-
|
| 9 |
-
## License
|
| 10 |
-
|
| 11 |
-
The model weights are released under CC BY 4.0, following the license of the NST training data.
|
| 12 |
-
|
| 13 |
-
## Training
|
| 14 |
-
|
| 15 |
-
Trained on the NST Swedish TTS Dataset (Språkbanken, National Library of Norway). The dataset contains high-quality studio recordings of Swedish speech.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f75455eb6afeb1db9e2905d5bd7e4115afcd3710e0d399b6a40981766d32fedc
|
| 3 |
-
size 63434611
|
|
|
|
|
|
|
|
|
|
|
|
sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx.json
DELETED
|
@@ -1,420 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"dataset": "alma",
|
| 3 |
-
"audio": {
|
| 4 |
-
"sample_rate": 22050,
|
| 5 |
-
"quality": "medium"
|
| 6 |
-
},
|
| 7 |
-
"espeak": {
|
| 8 |
-
"voice": "sv"
|
| 9 |
-
},
|
| 10 |
-
"language": {
|
| 11 |
-
"code": "sv_SE",
|
| 12 |
-
"family": "sv",
|
| 13 |
-
"region": "SE",
|
| 14 |
-
"name_native": "Svenska",
|
| 15 |
-
"name_english": "Swedish",
|
| 16 |
-
"country_english": "Sweden"
|
| 17 |
-
},
|
| 18 |
-
"inference": {
|
| 19 |
-
"noise_scale": 0.667,
|
| 20 |
-
"length_scale": 1,
|
| 21 |
-
"noise_w": 0.8
|
| 22 |
-
},
|
| 23 |
-
"phoneme_map": {},
|
| 24 |
-
"phoneme_id_map": {
|
| 25 |
-
"_": [
|
| 26 |
-
0
|
| 27 |
-
],
|
| 28 |
-
"^": [
|
| 29 |
-
1
|
| 30 |
-
],
|
| 31 |
-
"$": [
|
| 32 |
-
2
|
| 33 |
-
],
|
| 34 |
-
" ": [
|
| 35 |
-
3
|
| 36 |
-
],
|
| 37 |
-
"!": [
|
| 38 |
-
4
|
| 39 |
-
],
|
| 40 |
-
"'": [
|
| 41 |
-
5
|
| 42 |
-
],
|
| 43 |
-
"(": [
|
| 44 |
-
6
|
| 45 |
-
],
|
| 46 |
-
")": [
|
| 47 |
-
7
|
| 48 |
-
],
|
| 49 |
-
",": [
|
| 50 |
-
8
|
| 51 |
-
],
|
| 52 |
-
"-": [
|
| 53 |
-
9
|
| 54 |
-
],
|
| 55 |
-
".": [
|
| 56 |
-
10
|
| 57 |
-
],
|
| 58 |
-
":": [
|
| 59 |
-
11
|
| 60 |
-
],
|
| 61 |
-
";": [
|
| 62 |
-
12
|
| 63 |
-
],
|
| 64 |
-
"?": [
|
| 65 |
-
13
|
| 66 |
-
],
|
| 67 |
-
"a": [
|
| 68 |
-
14
|
| 69 |
-
],
|
| 70 |
-
"b": [
|
| 71 |
-
15
|
| 72 |
-
],
|
| 73 |
-
"c": [
|
| 74 |
-
16
|
| 75 |
-
],
|
| 76 |
-
"d": [
|
| 77 |
-
17
|
| 78 |
-
],
|
| 79 |
-
"e": [
|
| 80 |
-
18
|
| 81 |
-
],
|
| 82 |
-
"f": [
|
| 83 |
-
19
|
| 84 |
-
],
|
| 85 |
-
"h": [
|
| 86 |
-
20
|
| 87 |
-
],
|
| 88 |
-
"i": [
|
| 89 |
-
21
|
| 90 |
-
],
|
| 91 |
-
"j": [
|
| 92 |
-
22
|
| 93 |
-
],
|
| 94 |
-
"k": [
|
| 95 |
-
23
|
| 96 |
-
],
|
| 97 |
-
"l": [
|
| 98 |
-
24
|
| 99 |
-
],
|
| 100 |
-
"m": [
|
| 101 |
-
25
|
| 102 |
-
],
|
| 103 |
-
"n": [
|
| 104 |
-
26
|
| 105 |
-
],
|
| 106 |
-
"o": [
|
| 107 |
-
27
|
| 108 |
-
],
|
| 109 |
-
"p": [
|
| 110 |
-
28
|
| 111 |
-
],
|
| 112 |
-
"q": [
|
| 113 |
-
29
|
| 114 |
-
],
|
| 115 |
-
"r": [
|
| 116 |
-
30
|
| 117 |
-
],
|
| 118 |
-
"s": [
|
| 119 |
-
31
|
| 120 |
-
],
|
| 121 |
-
"t": [
|
| 122 |
-
32
|
| 123 |
-
],
|
| 124 |
-
"u": [
|
| 125 |
-
33
|
| 126 |
-
],
|
| 127 |
-
"v": [
|
| 128 |
-
34
|
| 129 |
-
],
|
| 130 |
-
"w": [
|
| 131 |
-
35
|
| 132 |
-
],
|
| 133 |
-
"x": [
|
| 134 |
-
36
|
| 135 |
-
],
|
| 136 |
-
"y": [
|
| 137 |
-
37
|
| 138 |
-
],
|
| 139 |
-
"z": [
|
| 140 |
-
38
|
| 141 |
-
],
|
| 142 |
-
"æ": [
|
| 143 |
-
39
|
| 144 |
-
],
|
| 145 |
-
"ç": [
|
| 146 |
-
40
|
| 147 |
-
],
|
| 148 |
-
"ð": [
|
| 149 |
-
41
|
| 150 |
-
],
|
| 151 |
-
"ø": [
|
| 152 |
-
42
|
| 153 |
-
],
|
| 154 |
-
"ħ": [
|
| 155 |
-
43
|
| 156 |
-
],
|
| 157 |
-
"ŋ": [
|
| 158 |
-
44
|
| 159 |
-
],
|
| 160 |
-
"œ": [
|
| 161 |
-
45
|
| 162 |
-
],
|
| 163 |
-
"ǀ": [
|
| 164 |
-
46
|
| 165 |
-
],
|
| 166 |
-
"ǁ": [
|
| 167 |
-
47
|
| 168 |
-
],
|
| 169 |
-
"ǂ": [
|
| 170 |
-
48
|
| 171 |
-
],
|
| 172 |
-
"ǃ": [
|
| 173 |
-
49
|
| 174 |
-
],
|
| 175 |
-
"ɐ": [
|
| 176 |
-
50
|
| 177 |
-
],
|
| 178 |
-
"ɑ": [
|
| 179 |
-
51
|
| 180 |
-
],
|
| 181 |
-
"ɒ": [
|
| 182 |
-
52
|
| 183 |
-
],
|
| 184 |
-
"ɓ": [
|
| 185 |
-
53
|
| 186 |
-
],
|
| 187 |
-
"ɔ": [
|
| 188 |
-
54
|
| 189 |
-
],
|
| 190 |
-
"ɕ": [
|
| 191 |
-
55
|
| 192 |
-
],
|
| 193 |
-
"ɖ": [
|
| 194 |
-
56
|
| 195 |
-
],
|
| 196 |
-
"ɗ": [
|
| 197 |
-
57
|
| 198 |
-
],
|
| 199 |
-
"ɘ": [
|
| 200 |
-
58
|
| 201 |
-
],
|
| 202 |
-
"ə": [
|
| 203 |
-
59
|
| 204 |
-
],
|
| 205 |
-
"ɚ": [
|
| 206 |
-
60
|
| 207 |
-
],
|
| 208 |
-
"ɛ": [
|
| 209 |
-
61
|
| 210 |
-
],
|
| 211 |
-
"ɜ": [
|
| 212 |
-
62
|
| 213 |
-
],
|
| 214 |
-
"ɞ": [
|
| 215 |
-
63
|
| 216 |
-
],
|
| 217 |
-
"ɟ": [
|
| 218 |
-
64
|
| 219 |
-
],
|
| 220 |
-
"ɠ": [
|
| 221 |
-
65
|
| 222 |
-
],
|
| 223 |
-
"ɡ": [
|
| 224 |
-
66
|
| 225 |
-
],
|
| 226 |
-
"ɢ": [
|
| 227 |
-
67
|
| 228 |
-
],
|
| 229 |
-
"ɣ": [
|
| 230 |
-
68
|
| 231 |
-
],
|
| 232 |
-
"ɤ": [
|
| 233 |
-
69
|
| 234 |
-
],
|
| 235 |
-
"ɥ": [
|
| 236 |
-
70
|
| 237 |
-
],
|
| 238 |
-
"ɦ": [
|
| 239 |
-
71
|
| 240 |
-
],
|
| 241 |
-
"ɧ": [
|
| 242 |
-
72
|
| 243 |
-
],
|
| 244 |
-
"ɨ": [
|
| 245 |
-
73
|
| 246 |
-
],
|
| 247 |
-
"ɪ": [
|
| 248 |
-
74
|
| 249 |
-
],
|
| 250 |
-
"ɫ": [
|
| 251 |
-
75
|
| 252 |
-
],
|
| 253 |
-
"ɬ": [
|
| 254 |
-
76
|
| 255 |
-
],
|
| 256 |
-
"ɭ": [
|
| 257 |
-
77
|
| 258 |
-
],
|
| 259 |
-
"ɮ": [
|
| 260 |
-
78
|
| 261 |
-
],
|
| 262 |
-
"ɯ": [
|
| 263 |
-
79
|
| 264 |
-
],
|
| 265 |
-
"ɰ": [
|
| 266 |
-
80
|
| 267 |
-
],
|
| 268 |
-
"ɱ": [
|
| 269 |
-
81
|
| 270 |
-
],
|
| 271 |
-
"ɲ": [
|
| 272 |
-
82
|
| 273 |
-
],
|
| 274 |
-
"ɳ": [
|
| 275 |
-
83
|
| 276 |
-
],
|
| 277 |
-
"ɴ": [
|
| 278 |
-
84
|
| 279 |
-
],
|
| 280 |
-
"ɵ": [
|
| 281 |
-
85
|
| 282 |
-
],
|
| 283 |
-
"ɶ": [
|
| 284 |
-
86
|
| 285 |
-
],
|
| 286 |
-
"ɸ": [
|
| 287 |
-
87
|
| 288 |
-
],
|
| 289 |
-
"ɹ": [
|
| 290 |
-
88
|
| 291 |
-
],
|
| 292 |
-
"ɺ": [
|
| 293 |
-
89
|
| 294 |
-
],
|
| 295 |
-
"ɻ": [
|
| 296 |
-
90
|
| 297 |
-
],
|
| 298 |
-
"ɽ": [
|
| 299 |
-
91
|
| 300 |
-
],
|
| 301 |
-
"ɾ": [
|
| 302 |
-
92
|
| 303 |
-
],
|
| 304 |
-
"ʀ": [
|
| 305 |
-
93
|
| 306 |
-
],
|
| 307 |
-
"ʁ": [
|
| 308 |
-
94
|
| 309 |
-
],
|
| 310 |
-
"ʂ": [
|
| 311 |
-
95
|
| 312 |
-
],
|
| 313 |
-
"ʃ": [
|
| 314 |
-
96
|
| 315 |
-
],
|
| 316 |
-
"ʄ": [
|
| 317 |
-
97
|
| 318 |
-
],
|
| 319 |
-
"ʈ": [
|
| 320 |
-
98
|
| 321 |
-
],
|
| 322 |
-
"ʉ": [
|
| 323 |
-
99
|
| 324 |
-
],
|
| 325 |
-
"ʊ": [
|
| 326 |
-
100
|
| 327 |
-
],
|
| 328 |
-
"ʋ": [
|
| 329 |
-
101
|
| 330 |
-
],
|
| 331 |
-
"ʌ": [
|
| 332 |
-
102
|
| 333 |
-
],
|
| 334 |
-
"ʍ": [
|
| 335 |
-
103
|
| 336 |
-
],
|
| 337 |
-
"ʎ": [
|
| 338 |
-
104
|
| 339 |
-
],
|
| 340 |
-
"ʏ": [
|
| 341 |
-
105
|
| 342 |
-
],
|
| 343 |
-
"ʐ": [
|
| 344 |
-
106
|
| 345 |
-
],
|
| 346 |
-
"ʑ": [
|
| 347 |
-
107
|
| 348 |
-
],
|
| 349 |
-
"ʒ": [
|
| 350 |
-
108
|
| 351 |
-
],
|
| 352 |
-
"ʔ": [
|
| 353 |
-
109
|
| 354 |
-
],
|
| 355 |
-
"ʕ": [
|
| 356 |
-
110
|
| 357 |
-
],
|
| 358 |
-
"ʘ": [
|
| 359 |
-
111
|
| 360 |
-
],
|
| 361 |
-
"ʙ": [
|
| 362 |
-
112
|
| 363 |
-
],
|
| 364 |
-
"ʛ": [
|
| 365 |
-
113
|
| 366 |
-
],
|
| 367 |
-
"ʜ": [
|
| 368 |
-
114
|
| 369 |
-
],
|
| 370 |
-
"ʝ": [
|
| 371 |
-
115
|
| 372 |
-
],
|
| 373 |
-
"ʟ": [
|
| 374 |
-
116
|
| 375 |
-
],
|
| 376 |
-
"ʡ": [
|
| 377 |
-
117
|
| 378 |
-
],
|
| 379 |
-
"ʢ": [
|
| 380 |
-
118
|
| 381 |
-
],
|
| 382 |
-
"ʲ": [
|
| 383 |
-
119
|
| 384 |
-
],
|
| 385 |
-
"ˈ": [
|
| 386 |
-
120
|
| 387 |
-
],
|
| 388 |
-
"ˌ": [
|
| 389 |
-
121
|
| 390 |
-
],
|
| 391 |
-
"ː": [
|
| 392 |
-
122
|
| 393 |
-
],
|
| 394 |
-
"ˑ": [
|
| 395 |
-
123
|
| 396 |
-
],
|
| 397 |
-
"˞": [
|
| 398 |
-
124
|
| 399 |
-
],
|
| 400 |
-
"β": [
|
| 401 |
-
125
|
| 402 |
-
],
|
| 403 |
-
"θ": [
|
| 404 |
-
126
|
| 405 |
-
],
|
| 406 |
-
"χ": [
|
| 407 |
-
127
|
| 408 |
-
],
|
| 409 |
-
"ᵻ": [
|
| 410 |
-
128
|
| 411 |
-
],
|
| 412 |
-
"ⱱ": [
|
| 413 |
-
129
|
| 414 |
-
]
|
| 415 |
-
},
|
| 416 |
-
"num_symbols": 130,
|
| 417 |
-
"num_speakers": 1,
|
| 418 |
-
"speaker_id_map": {},
|
| 419 |
-
"piper_version": "1.3.0"
|
| 420 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{sq/sq_AL/edon → tr/tr_TR/fahrettin}/medium/MODEL_CARD
RENAMED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
-
# Model card for
|
| 2 |
|
| 3 |
-
* Language:
|
| 4 |
* Speakers: 1
|
| 5 |
* Quality: medium
|
| 6 |
* Samplerate: 22,050Hz
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://
|
| 11 |
* License: CC0
|
| 12 |
|
| 13 |
## Training
|
| 14 |
|
| 15 |
-
Finetuned from U.S. English lessac voice (medium quality).
|
|
|
|
| 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).
|
{sv/sv_SE/alma → tr/tr_TR/fahrettin}/medium/samples/speaker_0.mp3
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45655ff7169b1682b42d013d7aaf17a2c7e0bd029b9075af652f7a7238776e9a
|
| 3 |
+
size 82858
|
eu/eu_ES/maider/medium/eu_ES-maider-medium.onnx → tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39081c47270180e8a0dfac69b07bf329fb6d039fcc1279dbe26c2daf2848b190
|
| 3 |
+
size 63201294
|
nl/nl_NL/alex/medium/nl_NL-alex-medium.onnx.json → tr/tr_TR/fahrettin/medium/tr_TR-fahrettin-medium.onnx.json
RENAMED
|
@@ -1,19 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"dataset": "alex",
|
| 3 |
"audio": {
|
| 4 |
"sample_rate": 22050,
|
| 5 |
"quality": "medium"
|
| 6 |
},
|
| 7 |
"espeak": {
|
| 8 |
-
"voice": "
|
| 9 |
-
},
|
| 10 |
-
"language": {
|
| 11 |
-
"code": "nl_NL",
|
| 12 |
-
"family": "nl",
|
| 13 |
-
"region": "NL",
|
| 14 |
-
"name_native": "Nederlands",
|
| 15 |
-
"name_english": "Dutch",
|
| 16 |
-
"country_english": "Netherlands"
|
| 17 |
},
|
| 18 |
"inference": {
|
| 19 |
"noise_scale": 0.667,
|
|
@@ -452,6 +443,12 @@
|
|
| 452 |
"̃": [
|
| 453 |
141
|
| 454 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 455 |
"̧": [
|
| 456 |
140
|
| 457 |
],
|
|
@@ -498,5 +495,14 @@
|
|
| 498 |
"num_symbols": 256,
|
| 499 |
"num_speakers": 1,
|
| 500 |
"speaker_id_map": {},
|
| 501 |
-
"piper_version": "1.0.0"
|
| 502 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"audio": {
|
| 3 |
"sample_rate": 22050,
|
| 4 |
"quality": "medium"
|
| 5 |
},
|
| 6 |
"espeak": {
|
| 7 |
+
"voice": "tr"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
},
|
| 9 |
"inference": {
|
| 10 |
"noise_scale": 0.667,
|
|
|
|
| 443 |
"̃": [
|
| 444 |
141
|
| 445 |
],
|
| 446 |
+
"̊": [
|
| 447 |
+
158
|
| 448 |
+
],
|
| 449 |
+
"̝": [
|
| 450 |
+
157
|
| 451 |
+
],
|
| 452 |
"̧": [
|
| 453 |
140
|
| 454 |
],
|
|
|
|
| 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 |
+
}
|
{zh/zh_CN/chaowen → tr/tr_TR/fettah}/medium/MODEL_CARD
RENAMED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
-
# Model card for
|
| 2 |
|
| 3 |
-
* Language:
|
| 4 |
* Speakers: 1
|
| 5 |
* Quality: medium
|
| 6 |
* Samplerate: 22,050Hz
|
| 7 |
|
| 8 |
## Dataset
|
| 9 |
|
| 10 |
-
* URL: https://github.com/
|
| 11 |
-
* License:
|
| 12 |
|
| 13 |
## Training
|
| 14 |
|
| 15 |
-
Finetuned from
|
|
|
|
| 1 |
+
# Model card for fettah (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).
|
{ku/ku_TR/berfin_renas → tr/tr_TR/fettah}/medium/samples/speaker_0.mp3
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:804e799c7a204761bd77dabb1c6c170e1301edab36a9d858ec0e3e196cf62724
|
| 3 |
+
size 113653
|