Michael Hansen
commited on
Commit
·
bae641d
1
Parent(s):
7e8200c
Add cori, kristin, ljspeech, claude
Browse files- en/en_GB/cori/high/MODEL_CARD +17 -0
- en/en_GB/cori/high/en_GB-cori-high.onnx +3 -0
- en/en_GB/cori/high/en_GB-cori-high.onnx.json +502 -0
- en/en_US/kristin/medium/MODEL_CARD +17 -0
- en/en_US/kristin/medium/en_US-kristin-medium.onnx +3 -0
- en/en_US/kristin/medium/en_US-kristin-medium.onnx.json +502 -0
- en/en_US/ljspeech/high/MODEL_CARD +17 -0
- en/en_US/ljspeech/high/en_US-ljspeech-high.onnx +3 -0
- en/en_US/ljspeech/high/en_US-ljspeech-high.onnx.json +502 -0
- en/en_US/ljspeech/medium/MODEL_CARD +17 -0
- en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx +3 -0
- en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx.json +502 -0
- es/es_MX/claude/high/MODEL_CARD +15 -0
- es/es_MX/claude/high/es_MX-claude-high.onnx +3 -0
- es/es_MX/claude/high/es_MX-claude-high.onnx.json +502 -0
- voices.json +150 -0
en/en_GB/cori/high/MODEL_CARD
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model card for cori (high)
|
| 2 |
+
|
| 3 |
+
* Language: en_GB (English, Great Britain)
|
| 4 |
+
* Speakers: 1
|
| 5 |
+
* Quality: medium
|
| 6 |
+
* Samplerate: 22,050Hz
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
|
| 10 |
+
* URL: https://librivox.org
|
| 11 |
+
* License: public domain
|
| 12 |
+
|
| 13 |
+
## Training
|
| 14 |
+
|
| 15 |
+
See: https://brycebeattie.com/files/tts/
|
| 16 |
+
|
| 17 |
+
UK English female voice. Single Speaker. Trained from scratch on high quality settings for 500 epochs. I put together the dataset, which ended up with about 24 hours of recordings. All recordings came from LibriVox.org.
|
en/en_GB/cori/high/en_GB-cori-high.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:470b4dd634c98f8a4850d7626ffc3dfc90774628eeef6605a6dd8f88f30a5903
|
| 3 |
+
size 114219352
|
en/en_GB/cori/high/en_GB-cori-high.onnx.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "cori",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "high"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en_GB",
|
| 12 |
+
"family": "en",
|
| 13 |
+
"region": "GB",
|
| 14 |
+
"name_native": "English",
|
| 15 |
+
"name_english": "English",
|
| 16 |
+
"country_english": "Great Britain"
|
| 17 |
+
},
|
| 18 |
+
"inference": {
|
| 19 |
+
"noise_scale": 0.667,
|
| 20 |
+
"length_scale": 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 |
+
}
|
en/en_US/kristin/medium/MODEL_CARD
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model card for kristin (medium)
|
| 2 |
+
|
| 3 |
+
* Language: en_US(English, United States)
|
| 4 |
+
* Speakers: 1
|
| 5 |
+
* Quality: medium
|
| 6 |
+
* Samplerate: 22,050Hz
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
|
| 10 |
+
* URL: https://librivox.org
|
| 11 |
+
* License: public domain
|
| 12 |
+
|
| 13 |
+
## Training
|
| 14 |
+
|
| 15 |
+
See: https://brycebeattie.com/files/tts/
|
| 16 |
+
|
| 17 |
+
US English female voice. Single Speaker. Trained from scratch on medium quality settings for 2000 epochs. I put together the dataset, which ended up with about 11.5 hours of recordings. All recordings came from LibriVox.org.
|
en/en_US/kristin/medium/en_US-kristin-medium.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5849957f929cbf720c258f8458692d6103fff2f0e3d3b19c8259474bb06a18d4
|
| 3 |
+
size 63531379
|
en/en_US/kristin/medium/en_US-kristin-medium.onnx.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "kristin",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "medium"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en_US",
|
| 12 |
+
"family": "en",
|
| 13 |
+
"region": "US",
|
| 14 |
+
"name_native": "English",
|
| 15 |
+
"name_english": "English",
|
| 16 |
+
"country_english": "United States"
|
| 17 |
+
},
|
| 18 |
+
"inference": {
|
| 19 |
+
"noise_scale": 0.667,
|
| 20 |
+
"length_scale": 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 |
+
}
|
en/en_US/ljspeech/high/MODEL_CARD
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model card for ljspeech (high)
|
| 2 |
+
|
| 3 |
+
* Language: en_US (English, United States)
|
| 4 |
+
* Speakers: 1
|
| 5 |
+
* Quality: medium
|
| 6 |
+
* Samplerate: 22,050Hz
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
|
| 10 |
+
* URL: https://keithito.com/LJ-Speech-Dataset/
|
| 11 |
+
* License: public domain
|
| 12 |
+
|
| 13 |
+
## Training
|
| 14 |
+
|
| 15 |
+
See: https://brycebeattie.com/files/tts/
|
| 16 |
+
|
| 17 |
+
US English female voice. Single speaker. Trained from scratch for 1000 epochs on medium quality settings using the LJ Speech dataset. I reencoded the recordings to a bit rate of 22500 Hz so it would match other voices released for Piper TTS.
|
en/en_US/ljspeech/high/en_US-ljspeech-high.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d4f08ba6a2a48c44592eed3ce56bf85e9de3dd4e20df90541ae68a8310c029a
|
| 3 |
+
size 114199011
|
en/en_US/ljspeech/high/en_US-ljspeech-high.onnx.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "ljspeech",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "high"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en_US",
|
| 12 |
+
"family": "en",
|
| 13 |
+
"region": "US",
|
| 14 |
+
"name_native": "English",
|
| 15 |
+
"name_english": "English",
|
| 16 |
+
"country_english": "United States"
|
| 17 |
+
},
|
| 18 |
+
"inference": {
|
| 19 |
+
"noise_scale": 0.667,
|
| 20 |
+
"length_scale": 1,
|
| 21 |
+
"noise_w": 0.333
|
| 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 |
+
}
|
en/en_US/ljspeech/medium/MODEL_CARD
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model card for ljspeech (medium)
|
| 2 |
+
|
| 3 |
+
* Language: en_US (English, United States)
|
| 4 |
+
* Speakers: 1
|
| 5 |
+
* Quality: medium
|
| 6 |
+
* Samplerate: 22,050Hz
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
|
| 10 |
+
* URL: https://keithito.com/LJ-Speech-Dataset/
|
| 11 |
+
* License: public domain
|
| 12 |
+
|
| 13 |
+
## Training
|
| 14 |
+
|
| 15 |
+
See: https://brycebeattie.com/files/tts/
|
| 16 |
+
|
| 17 |
+
US English female voice. Single speaker. Trained from scratch for 1000 epochs on medium quality settings using the LJ Speech dataset. I reencoded the recordings to a bit rate of 22500 Hz so it would match other voices released for Piper TTS.
|
en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f52a751e2349abe7a76735eb09dc1875298c77ea2342ffd2fef79ff81b87f22
|
| 3 |
+
size 63531379
|
en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "ljspeech",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "medium"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en_US",
|
| 12 |
+
"family": "en",
|
| 13 |
+
"region": "US",
|
| 14 |
+
"name_native": "English",
|
| 15 |
+
"name_english": "English",
|
| 16 |
+
"country_english": "United States"
|
| 17 |
+
},
|
| 18 |
+
"inference": {
|
| 19 |
+
"noise_scale": 0.667,
|
| 20 |
+
"length_scale": 1,
|
| 21 |
+
"noise_w": 0.333
|
| 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 |
+
}
|
es/es_MX/claude/high/MODEL_CARD
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Model card for claude (high)
|
| 2 |
+
|
| 3 |
+
* Language: es_MX (Spanish, Mexico)
|
| 4 |
+
* Speakers: 1
|
| 5 |
+
* Quality: high
|
| 6 |
+
* Samplerate: 22,050Hz
|
| 7 |
+
|
| 8 |
+
## Dataset
|
| 9 |
+
|
| 10 |
+
* URL: https://huggingface.co/spaces/HirCoir/Piper-TTS-Spanish
|
| 11 |
+
* License: apache-2.0
|
| 12 |
+
|
| 13 |
+
## Training
|
| 14 |
+
|
| 15 |
+
See URL above
|
es/es_MX/claude/high/es_MX-claude-high.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef40a71ea63852cd8ab7e6fa7d2ecdcfa67a0b47c9c48e3f10e02ee02083ea0
|
| 3 |
+
size 63122309
|
es/es_MX/claude/high/es_MX-claude-high.onnx.json
ADDED
|
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "claude",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "high"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "es-419"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "es_MX",
|
| 12 |
+
"family": "es",
|
| 13 |
+
"region": "MX",
|
| 14 |
+
"name_native": "Español",
|
| 15 |
+
"name_english": "Spanish",
|
| 16 |
+
"country_english": "Mexico"
|
| 17 |
+
},
|
| 18 |
+
"inference": {
|
| 19 |
+
"noise_scale": 0.667,
|
| 20 |
+
"length_scale": 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 |
+
}
|
voices.json
CHANGED
|
@@ -968,6 +968,36 @@
|
|
| 968 |
},
|
| 969 |
"aliases": []
|
| 970 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 971 |
"en_GB-jenny_dioco-medium": {
|
| 972 |
"key": "en_GB-jenny_dioco-medium",
|
| 973 |
"name": "jenny_dioco",
|
|
@@ -1498,6 +1528,36 @@
|
|
| 1498 |
"en-us-kathleen-low"
|
| 1499 |
]
|
| 1500 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1501 |
"en_US-kusal-medium": {
|
| 1502 |
"key": "en_US-kusal-medium",
|
| 1503 |
"name": "kusal",
|
|
@@ -3549,6 +3609,66 @@
|
|
| 3549 |
},
|
| 3550 |
"aliases": []
|
| 3551 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3552 |
"en_US-ryan-high": {
|
| 3553 |
"key": "en_US-ryan-high",
|
| 3554 |
"name": "ryan",
|
|
@@ -3834,6 +3954,36 @@
|
|
| 3834 |
},
|
| 3835 |
"aliases": []
|
| 3836 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3837 |
"fa_IR-amir-medium": {
|
| 3838 |
"key": "fa_IR-amir-medium",
|
| 3839 |
"name": "amir",
|
|
|
|
| 968 |
},
|
| 969 |
"aliases": []
|
| 970 |
},
|
| 971 |
+
"en_GB-cori-high": {
|
| 972 |
+
"key": "en_GB-cori-high",
|
| 973 |
+
"name": "cori",
|
| 974 |
+
"language": {
|
| 975 |
+
"code": "en_GB",
|
| 976 |
+
"family": "en",
|
| 977 |
+
"region": "GB",
|
| 978 |
+
"name_native": "English",
|
| 979 |
+
"name_english": "English",
|
| 980 |
+
"country_english": "Great Britain"
|
| 981 |
+
},
|
| 982 |
+
"quality": "high",
|
| 983 |
+
"num_speakers": 1,
|
| 984 |
+
"speaker_id_map": {},
|
| 985 |
+
"files": {
|
| 986 |
+
"en/en_GB/cori/high/en_GB-cori-high.onnx": {
|
| 987 |
+
"size_bytes": 114219352,
|
| 988 |
+
"md5_digest": "3474a80133d9a03e6870d2ac42c18806"
|
| 989 |
+
},
|
| 990 |
+
"en/en_GB/cori/high/en_GB-cori-high.onnx.json": {
|
| 991 |
+
"size_bytes": 4963,
|
| 992 |
+
"md5_digest": "0f7d42e77a99193006aa34a34442f5e0"
|
| 993 |
+
},
|
| 994 |
+
"en/en_GB/cori/high/MODEL_CARD": {
|
| 995 |
+
"size_bytes": 470,
|
| 996 |
+
"md5_digest": "93702d22a081e5efe612625f2a9d6d51"
|
| 997 |
+
}
|
| 998 |
+
},
|
| 999 |
+
"aliases": []
|
| 1000 |
+
},
|
| 1001 |
"en_GB-jenny_dioco-medium": {
|
| 1002 |
"key": "en_GB-jenny_dioco-medium",
|
| 1003 |
"name": "jenny_dioco",
|
|
|
|
| 1528 |
"en-us-kathleen-low"
|
| 1529 |
]
|
| 1530 |
},
|
| 1531 |
+
"en_US-kristin-medium": {
|
| 1532 |
+
"key": "en_US-kristin-medium",
|
| 1533 |
+
"name": "kristin",
|
| 1534 |
+
"language": {
|
| 1535 |
+
"code": "en_US",
|
| 1536 |
+
"family": "en",
|
| 1537 |
+
"region": "US",
|
| 1538 |
+
"name_native": "English",
|
| 1539 |
+
"name_english": "English",
|
| 1540 |
+
"country_english": "United States"
|
| 1541 |
+
},
|
| 1542 |
+
"quality": "medium",
|
| 1543 |
+
"num_speakers": 1,
|
| 1544 |
+
"speaker_id_map": {},
|
| 1545 |
+
"files": {
|
| 1546 |
+
"en/en_US/kristin/medium/en_US-kristin-medium.onnx": {
|
| 1547 |
+
"size_bytes": 63531379,
|
| 1548 |
+
"md5_digest": "5fed42d2296baca042e2bf74785db725"
|
| 1549 |
+
},
|
| 1550 |
+
"en/en_US/kristin/medium/en_US-kristin-medium.onnx.json": {
|
| 1551 |
+
"size_bytes": 4968,
|
| 1552 |
+
"md5_digest": "70bc97d350c796c64ea5e4d08241afac"
|
| 1553 |
+
},
|
| 1554 |
+
"en/en_US/kristin/medium/MODEL_CARD": {
|
| 1555 |
+
"size_bytes": 479,
|
| 1556 |
+
"md5_digest": "9bfb8192299b34cddf76455f04cb8cd2"
|
| 1557 |
+
}
|
| 1558 |
+
},
|
| 1559 |
+
"aliases": []
|
| 1560 |
+
},
|
| 1561 |
"en_US-kusal-medium": {
|
| 1562 |
"key": "en_US-kusal-medium",
|
| 1563 |
"name": "kusal",
|
|
|
|
| 3609 |
},
|
| 3610 |
"aliases": []
|
| 3611 |
},
|
| 3612 |
+
"en_US-ljspeech-high": {
|
| 3613 |
+
"key": "en_US-ljspeech-high",
|
| 3614 |
+
"name": "ljspeech",
|
| 3615 |
+
"language": {
|
| 3616 |
+
"code": "en_US",
|
| 3617 |
+
"family": "en",
|
| 3618 |
+
"region": "US",
|
| 3619 |
+
"name_native": "English",
|
| 3620 |
+
"name_english": "English",
|
| 3621 |
+
"country_english": "United States"
|
| 3622 |
+
},
|
| 3623 |
+
"quality": "high",
|
| 3624 |
+
"num_speakers": 1,
|
| 3625 |
+
"speaker_id_map": {},
|
| 3626 |
+
"files": {
|
| 3627 |
+
"en/en_US/ljspeech/high/en_US-ljspeech-high.onnx": {
|
| 3628 |
+
"size_bytes": 114199011,
|
| 3629 |
+
"md5_digest": "dad093b5d2cff6a5fda99883ceda09d1"
|
| 3630 |
+
},
|
| 3631 |
+
"en/en_US/ljspeech/high/en_US-ljspeech-high.onnx.json": {
|
| 3632 |
+
"size_bytes": 4967,
|
| 3633 |
+
"md5_digest": "1f93986f7c39647383f2a0b1471f30aa"
|
| 3634 |
+
},
|
| 3635 |
+
"en/en_US/ljspeech/high/MODEL_CARD": {
|
| 3636 |
+
"size_bytes": 515,
|
| 3637 |
+
"md5_digest": "59322a9a8d2c0e556f0be1171cd54ea7"
|
| 3638 |
+
}
|
| 3639 |
+
},
|
| 3640 |
+
"aliases": []
|
| 3641 |
+
},
|
| 3642 |
+
"en_US-ljspeech-medium": {
|
| 3643 |
+
"key": "en_US-ljspeech-medium",
|
| 3644 |
+
"name": "ljspeech",
|
| 3645 |
+
"language": {
|
| 3646 |
+
"code": "en_US",
|
| 3647 |
+
"family": "en",
|
| 3648 |
+
"region": "US",
|
| 3649 |
+
"name_native": "English",
|
| 3650 |
+
"name_english": "English",
|
| 3651 |
+
"country_english": "United States"
|
| 3652 |
+
},
|
| 3653 |
+
"quality": "medium",
|
| 3654 |
+
"num_speakers": 1,
|
| 3655 |
+
"speaker_id_map": {},
|
| 3656 |
+
"files": {
|
| 3657 |
+
"en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx": {
|
| 3658 |
+
"size_bytes": 63531379,
|
| 3659 |
+
"md5_digest": "109d552e9dd78d92d1169a7edd6de38d"
|
| 3660 |
+
},
|
| 3661 |
+
"en/en_US/ljspeech/medium/en_US-ljspeech-medium.onnx.json": {
|
| 3662 |
+
"size_bytes": 4969,
|
| 3663 |
+
"md5_digest": "ae02d7c3f01e9606dcac4668e58720c9"
|
| 3664 |
+
},
|
| 3665 |
+
"en/en_US/ljspeech/medium/MODEL_CARD": {
|
| 3666 |
+
"size_bytes": 517,
|
| 3667 |
+
"md5_digest": "5ad31d314786587d4f97effb0b716d61"
|
| 3668 |
+
}
|
| 3669 |
+
},
|
| 3670 |
+
"aliases": []
|
| 3671 |
+
},
|
| 3672 |
"en_US-ryan-high": {
|
| 3673 |
"key": "en_US-ryan-high",
|
| 3674 |
"name": "ryan",
|
|
|
|
| 3954 |
},
|
| 3955 |
"aliases": []
|
| 3956 |
},
|
| 3957 |
+
"es_MX-claude-high": {
|
| 3958 |
+
"key": "es_MX-claude-high",
|
| 3959 |
+
"name": "claude",
|
| 3960 |
+
"language": {
|
| 3961 |
+
"code": "es_MX",
|
| 3962 |
+
"family": "es",
|
| 3963 |
+
"region": "MX",
|
| 3964 |
+
"name_native": "Español",
|
| 3965 |
+
"name_english": "Spanish",
|
| 3966 |
+
"country_english": "Mexico"
|
| 3967 |
+
},
|
| 3968 |
+
"quality": "high",
|
| 3969 |
+
"num_speakers": 1,
|
| 3970 |
+
"speaker_id_map": {},
|
| 3971 |
+
"files": {
|
| 3972 |
+
"es/es_MX/claude/high/es_MX-claude-high.onnx": {
|
| 3973 |
+
"size_bytes": 63122309,
|
| 3974 |
+
"md5_digest": "cb1966e0ff20ca3aa010f6c9a0ce296a"
|
| 3975 |
+
},
|
| 3976 |
+
"es/es_MX/claude/high/es_MX-claude-high.onnx.json": {
|
| 3977 |
+
"size_bytes": 4963,
|
| 3978 |
+
"md5_digest": "36882201922fabb409f18d284af3eddd"
|
| 3979 |
+
},
|
| 3980 |
+
"es/es_MX/claude/high/MODEL_CARD": {
|
| 3981 |
+
"size_bytes": 247,
|
| 3982 |
+
"md5_digest": "bca99dc9b9a6c8f2f8563d73d52c4a3b"
|
| 3983 |
+
}
|
| 3984 |
+
},
|
| 3985 |
+
"aliases": []
|
| 3986 |
+
},
|
| 3987 |
"fa_IR-amir-medium": {
|
| 3988 |
"key": "fa_IR-amir-medium",
|
| 3989 |
"name": "amir",
|