Upload folder using huggingface_hub
Browse files- .gitattributes +16 -0
- 16Speakers.onnx +3 -0
- 16Speakers.onnx.json +514 -0
- README.md +130 -0
- jenny.onnx +3 -0
- jenny.onnx.json +497 -0
- kristin.onnx +3 -0
- kristin.onnx.json +497 -0
- preview-16speakers.sh +62 -0
- previews/speaker_0_Cori_Samuel.wav +3 -0
- previews/speaker_10_Steve_C.wav +3 -0
- previews/speaker_11_Owlivia.wav +3 -0
- previews/speaker_12_Paul_Hampton.wav +3 -0
- previews/speaker_13_Jennifer_Dorr.wav +3 -0
- previews/speaker_14_Emily_Cripps.wav +3 -0
- previews/speaker_15_Martin_Clifton.wav +3 -0
- previews/speaker_1_Kara_Shallenberg.wav +3 -0
- previews/speaker_2_Kristin_Hughes.wav +3 -0
- previews/speaker_3_Maria_Kasper.wav +3 -0
- previews/speaker_4_Mike_Pelton.wav +3 -0
- previews/speaker_5_Mark_Nelson.wav +3 -0
- previews/speaker_6_Michael_Scherer.wav +3 -0
- previews/speaker_7_James_K_White.wav +3 -0
- previews/speaker_8_Rose_Ibex.wav +3 -0
- previews/speaker_9_progressingamerica.wav +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
previews/speaker_0_Cori_Samuel.wav filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
previews/speaker_10_Steve_C.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
previews/speaker_11_Owlivia.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
previews/speaker_12_Paul_Hampton.wav filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
previews/speaker_13_Jennifer_Dorr.wav filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
previews/speaker_14_Emily_Cripps.wav filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
previews/speaker_15_Martin_Clifton.wav filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
previews/speaker_1_Kara_Shallenberg.wav filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
previews/speaker_2_Kristin_Hughes.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
previews/speaker_3_Maria_Kasper.wav filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
previews/speaker_4_Mike_Pelton.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
previews/speaker_5_Mark_Nelson.wav filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
previews/speaker_6_Michael_Scherer.wav filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
previews/speaker_7_James_K_White.wav filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
previews/speaker_8_Rose_Ibex.wav filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
previews/speaker_9_progressingamerica.wav filter=lfs diff=lfs merge=lfs -text
|
16Speakers.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cc7b8f55b82146c09265e909beaa539254a882b9a6ac915792cbfc7d41ba235
|
| 3 |
+
size 77100103
|
16Speakers.onnx.json
ADDED
|
@@ -0,0 +1,514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "training",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "mv2"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en"
|
| 12 |
+
},
|
| 13 |
+
"inference": {
|
| 14 |
+
"noise_scale": 0.667,
|
| 15 |
+
"length_scale": 1,
|
| 16 |
+
"noise_w": 0.8
|
| 17 |
+
},
|
| 18 |
+
"phoneme_type": "espeak",
|
| 19 |
+
"phoneme_map": {},
|
| 20 |
+
"phoneme_id_map": {
|
| 21 |
+
" ": [
|
| 22 |
+
3
|
| 23 |
+
],
|
| 24 |
+
"!": [
|
| 25 |
+
4
|
| 26 |
+
],
|
| 27 |
+
"\"": [
|
| 28 |
+
150
|
| 29 |
+
],
|
| 30 |
+
"#": [
|
| 31 |
+
149
|
| 32 |
+
],
|
| 33 |
+
"$": [
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"'": [
|
| 37 |
+
5
|
| 38 |
+
],
|
| 39 |
+
"(": [
|
| 40 |
+
6
|
| 41 |
+
],
|
| 42 |
+
")": [
|
| 43 |
+
7
|
| 44 |
+
],
|
| 45 |
+
",": [
|
| 46 |
+
8
|
| 47 |
+
],
|
| 48 |
+
"-": [
|
| 49 |
+
9
|
| 50 |
+
],
|
| 51 |
+
".": [
|
| 52 |
+
10
|
| 53 |
+
],
|
| 54 |
+
"0": [
|
| 55 |
+
130
|
| 56 |
+
],
|
| 57 |
+
"1": [
|
| 58 |
+
131
|
| 59 |
+
],
|
| 60 |
+
"2": [
|
| 61 |
+
132
|
| 62 |
+
],
|
| 63 |
+
"3": [
|
| 64 |
+
133
|
| 65 |
+
],
|
| 66 |
+
"4": [
|
| 67 |
+
134
|
| 68 |
+
],
|
| 69 |
+
"5": [
|
| 70 |
+
135
|
| 71 |
+
],
|
| 72 |
+
"6": [
|
| 73 |
+
136
|
| 74 |
+
],
|
| 75 |
+
"7": [
|
| 76 |
+
137
|
| 77 |
+
],
|
| 78 |
+
"8": [
|
| 79 |
+
138
|
| 80 |
+
],
|
| 81 |
+
"9": [
|
| 82 |
+
139
|
| 83 |
+
],
|
| 84 |
+
":": [
|
| 85 |
+
11
|
| 86 |
+
],
|
| 87 |
+
";": [
|
| 88 |
+
12
|
| 89 |
+
],
|
| 90 |
+
"?": [
|
| 91 |
+
13
|
| 92 |
+
],
|
| 93 |
+
"X": [
|
| 94 |
+
156
|
| 95 |
+
],
|
| 96 |
+
"^": [
|
| 97 |
+
1
|
| 98 |
+
],
|
| 99 |
+
"_": [
|
| 100 |
+
0
|
| 101 |
+
],
|
| 102 |
+
"a": [
|
| 103 |
+
14
|
| 104 |
+
],
|
| 105 |
+
"b": [
|
| 106 |
+
15
|
| 107 |
+
],
|
| 108 |
+
"c": [
|
| 109 |
+
16
|
| 110 |
+
],
|
| 111 |
+
"d": [
|
| 112 |
+
17
|
| 113 |
+
],
|
| 114 |
+
"e": [
|
| 115 |
+
18
|
| 116 |
+
],
|
| 117 |
+
"f": [
|
| 118 |
+
19
|
| 119 |
+
],
|
| 120 |
+
"g": [
|
| 121 |
+
154
|
| 122 |
+
],
|
| 123 |
+
"h": [
|
| 124 |
+
20
|
| 125 |
+
],
|
| 126 |
+
"i": [
|
| 127 |
+
21
|
| 128 |
+
],
|
| 129 |
+
"j": [
|
| 130 |
+
22
|
| 131 |
+
],
|
| 132 |
+
"k": [
|
| 133 |
+
23
|
| 134 |
+
],
|
| 135 |
+
"l": [
|
| 136 |
+
24
|
| 137 |
+
],
|
| 138 |
+
"m": [
|
| 139 |
+
25
|
| 140 |
+
],
|
| 141 |
+
"n": [
|
| 142 |
+
26
|
| 143 |
+
],
|
| 144 |
+
"o": [
|
| 145 |
+
27
|
| 146 |
+
],
|
| 147 |
+
"p": [
|
| 148 |
+
28
|
| 149 |
+
],
|
| 150 |
+
"q": [
|
| 151 |
+
29
|
| 152 |
+
],
|
| 153 |
+
"r": [
|
| 154 |
+
30
|
| 155 |
+
],
|
| 156 |
+
"s": [
|
| 157 |
+
31
|
| 158 |
+
],
|
| 159 |
+
"t": [
|
| 160 |
+
32
|
| 161 |
+
],
|
| 162 |
+
"u": [
|
| 163 |
+
33
|
| 164 |
+
],
|
| 165 |
+
"v": [
|
| 166 |
+
34
|
| 167 |
+
],
|
| 168 |
+
"w": [
|
| 169 |
+
35
|
| 170 |
+
],
|
| 171 |
+
"x": [
|
| 172 |
+
36
|
| 173 |
+
],
|
| 174 |
+
"y": [
|
| 175 |
+
37
|
| 176 |
+
],
|
| 177 |
+
"z": [
|
| 178 |
+
38
|
| 179 |
+
],
|
| 180 |
+
"æ": [
|
| 181 |
+
39
|
| 182 |
+
],
|
| 183 |
+
"ç": [
|
| 184 |
+
40
|
| 185 |
+
],
|
| 186 |
+
"ð": [
|
| 187 |
+
41
|
| 188 |
+
],
|
| 189 |
+
"ø": [
|
| 190 |
+
42
|
| 191 |
+
],
|
| 192 |
+
"ħ": [
|
| 193 |
+
43
|
| 194 |
+
],
|
| 195 |
+
"ŋ": [
|
| 196 |
+
44
|
| 197 |
+
],
|
| 198 |
+
"œ": [
|
| 199 |
+
45
|
| 200 |
+
],
|
| 201 |
+
"ǀ": [
|
| 202 |
+
46
|
| 203 |
+
],
|
| 204 |
+
"ǁ": [
|
| 205 |
+
47
|
| 206 |
+
],
|
| 207 |
+
"ǂ": [
|
| 208 |
+
48
|
| 209 |
+
],
|
| 210 |
+
"ǃ": [
|
| 211 |
+
49
|
| 212 |
+
],
|
| 213 |
+
"ɐ": [
|
| 214 |
+
50
|
| 215 |
+
],
|
| 216 |
+
"ɑ": [
|
| 217 |
+
51
|
| 218 |
+
],
|
| 219 |
+
"ɒ": [
|
| 220 |
+
52
|
| 221 |
+
],
|
| 222 |
+
"ɓ": [
|
| 223 |
+
53
|
| 224 |
+
],
|
| 225 |
+
"ɔ": [
|
| 226 |
+
54
|
| 227 |
+
],
|
| 228 |
+
"ɕ": [
|
| 229 |
+
55
|
| 230 |
+
],
|
| 231 |
+
"ɖ": [
|
| 232 |
+
56
|
| 233 |
+
],
|
| 234 |
+
"ɗ": [
|
| 235 |
+
57
|
| 236 |
+
],
|
| 237 |
+
"ɘ": [
|
| 238 |
+
58
|
| 239 |
+
],
|
| 240 |
+
"ə": [
|
| 241 |
+
59
|
| 242 |
+
],
|
| 243 |
+
"ɚ": [
|
| 244 |
+
60
|
| 245 |
+
],
|
| 246 |
+
"ɛ": [
|
| 247 |
+
61
|
| 248 |
+
],
|
| 249 |
+
"ɜ": [
|
| 250 |
+
62
|
| 251 |
+
],
|
| 252 |
+
"ɞ": [
|
| 253 |
+
63
|
| 254 |
+
],
|
| 255 |
+
"ɟ": [
|
| 256 |
+
64
|
| 257 |
+
],
|
| 258 |
+
"ɠ": [
|
| 259 |
+
65
|
| 260 |
+
],
|
| 261 |
+
"ɡ": [
|
| 262 |
+
66
|
| 263 |
+
],
|
| 264 |
+
"ɢ": [
|
| 265 |
+
67
|
| 266 |
+
],
|
| 267 |
+
"ɣ": [
|
| 268 |
+
68
|
| 269 |
+
],
|
| 270 |
+
"ɤ": [
|
| 271 |
+
69
|
| 272 |
+
],
|
| 273 |
+
"ɥ": [
|
| 274 |
+
70
|
| 275 |
+
],
|
| 276 |
+
"ɦ": [
|
| 277 |
+
71
|
| 278 |
+
],
|
| 279 |
+
"ɧ": [
|
| 280 |
+
72
|
| 281 |
+
],
|
| 282 |
+
"ɨ": [
|
| 283 |
+
73
|
| 284 |
+
],
|
| 285 |
+
"ɪ": [
|
| 286 |
+
74
|
| 287 |
+
],
|
| 288 |
+
"ɫ": [
|
| 289 |
+
75
|
| 290 |
+
],
|
| 291 |
+
"ɬ": [
|
| 292 |
+
76
|
| 293 |
+
],
|
| 294 |
+
"ɭ": [
|
| 295 |
+
77
|
| 296 |
+
],
|
| 297 |
+
"ɮ": [
|
| 298 |
+
78
|
| 299 |
+
],
|
| 300 |
+
"ɯ": [
|
| 301 |
+
79
|
| 302 |
+
],
|
| 303 |
+
"ɰ": [
|
| 304 |
+
80
|
| 305 |
+
],
|
| 306 |
+
"ɱ": [
|
| 307 |
+
81
|
| 308 |
+
],
|
| 309 |
+
"ɲ": [
|
| 310 |
+
82
|
| 311 |
+
],
|
| 312 |
+
"ɳ": [
|
| 313 |
+
83
|
| 314 |
+
],
|
| 315 |
+
"ɴ": [
|
| 316 |
+
84
|
| 317 |
+
],
|
| 318 |
+
"ɵ": [
|
| 319 |
+
85
|
| 320 |
+
],
|
| 321 |
+
"ɶ": [
|
| 322 |
+
86
|
| 323 |
+
],
|
| 324 |
+
"ɸ": [
|
| 325 |
+
87
|
| 326 |
+
],
|
| 327 |
+
"ɹ": [
|
| 328 |
+
88
|
| 329 |
+
],
|
| 330 |
+
"ɺ": [
|
| 331 |
+
89
|
| 332 |
+
],
|
| 333 |
+
"ɻ": [
|
| 334 |
+
90
|
| 335 |
+
],
|
| 336 |
+
"ɽ": [
|
| 337 |
+
91
|
| 338 |
+
],
|
| 339 |
+
"ɾ": [
|
| 340 |
+
92
|
| 341 |
+
],
|
| 342 |
+
"ʀ": [
|
| 343 |
+
93
|
| 344 |
+
],
|
| 345 |
+
"ʁ": [
|
| 346 |
+
94
|
| 347 |
+
],
|
| 348 |
+
"ʂ": [
|
| 349 |
+
95
|
| 350 |
+
],
|
| 351 |
+
"ʃ": [
|
| 352 |
+
96
|
| 353 |
+
],
|
| 354 |
+
"ʄ": [
|
| 355 |
+
97
|
| 356 |
+
],
|
| 357 |
+
"ʈ": [
|
| 358 |
+
98
|
| 359 |
+
],
|
| 360 |
+
"ʉ": [
|
| 361 |
+
99
|
| 362 |
+
],
|
| 363 |
+
"ʊ": [
|
| 364 |
+
100
|
| 365 |
+
],
|
| 366 |
+
"ʋ": [
|
| 367 |
+
101
|
| 368 |
+
],
|
| 369 |
+
"ʌ": [
|
| 370 |
+
102
|
| 371 |
+
],
|
| 372 |
+
"ʍ": [
|
| 373 |
+
103
|
| 374 |
+
],
|
| 375 |
+
"ʎ": [
|
| 376 |
+
104
|
| 377 |
+
],
|
| 378 |
+
"ʏ": [
|
| 379 |
+
105
|
| 380 |
+
],
|
| 381 |
+
"ʐ": [
|
| 382 |
+
106
|
| 383 |
+
],
|
| 384 |
+
"ʑ": [
|
| 385 |
+
107
|
| 386 |
+
],
|
| 387 |
+
"ʒ": [
|
| 388 |
+
108
|
| 389 |
+
],
|
| 390 |
+
"ʔ": [
|
| 391 |
+
109
|
| 392 |
+
],
|
| 393 |
+
"ʕ": [
|
| 394 |
+
110
|
| 395 |
+
],
|
| 396 |
+
"ʘ": [
|
| 397 |
+
111
|
| 398 |
+
],
|
| 399 |
+
"ʙ": [
|
| 400 |
+
112
|
| 401 |
+
],
|
| 402 |
+
"ʛ": [
|
| 403 |
+
113
|
| 404 |
+
],
|
| 405 |
+
"ʜ": [
|
| 406 |
+
114
|
| 407 |
+
],
|
| 408 |
+
"ʝ": [
|
| 409 |
+
115
|
| 410 |
+
],
|
| 411 |
+
"ʟ": [
|
| 412 |
+
116
|
| 413 |
+
],
|
| 414 |
+
"ʡ": [
|
| 415 |
+
117
|
| 416 |
+
],
|
| 417 |
+
"ʢ": [
|
| 418 |
+
118
|
| 419 |
+
],
|
| 420 |
+
"ʦ": [
|
| 421 |
+
155
|
| 422 |
+
],
|
| 423 |
+
"ʰ": [
|
| 424 |
+
145
|
| 425 |
+
],
|
| 426 |
+
"ʲ": [
|
| 427 |
+
119
|
| 428 |
+
],
|
| 429 |
+
"ˈ": [
|
| 430 |
+
120
|
| 431 |
+
],
|
| 432 |
+
"ˌ": [
|
| 433 |
+
121
|
| 434 |
+
],
|
| 435 |
+
"ː": [
|
| 436 |
+
122
|
| 437 |
+
],
|
| 438 |
+
"ˑ": [
|
| 439 |
+
123
|
| 440 |
+
],
|
| 441 |
+
"˞": [
|
| 442 |
+
124
|
| 443 |
+
],
|
| 444 |
+
"ˤ": [
|
| 445 |
+
146
|
| 446 |
+
],
|
| 447 |
+
"̃": [
|
| 448 |
+
141
|
| 449 |
+
],
|
| 450 |
+
"̧": [
|
| 451 |
+
140
|
| 452 |
+
],
|
| 453 |
+
"̩": [
|
| 454 |
+
144
|
| 455 |
+
],
|
| 456 |
+
"̪": [
|
| 457 |
+
142
|
| 458 |
+
],
|
| 459 |
+
"̯": [
|
| 460 |
+
143
|
| 461 |
+
],
|
| 462 |
+
"̺": [
|
| 463 |
+
152
|
| 464 |
+
],
|
| 465 |
+
"̻": [
|
| 466 |
+
153
|
| 467 |
+
],
|
| 468 |
+
"β": [
|
| 469 |
+
125
|
| 470 |
+
],
|
| 471 |
+
"ε": [
|
| 472 |
+
147
|
| 473 |
+
],
|
| 474 |
+
"θ": [
|
| 475 |
+
126
|
| 476 |
+
],
|
| 477 |
+
"χ": [
|
| 478 |
+
127
|
| 479 |
+
],
|
| 480 |
+
"ᵻ": [
|
| 481 |
+
128
|
| 482 |
+
],
|
| 483 |
+
"↑": [
|
| 484 |
+
151
|
| 485 |
+
],
|
| 486 |
+
"↓": [
|
| 487 |
+
148
|
| 488 |
+
],
|
| 489 |
+
"ⱱ": [
|
| 490 |
+
129
|
| 491 |
+
]
|
| 492 |
+
},
|
| 493 |
+
"num_symbols": 256,
|
| 494 |
+
"num_speakers": 16,
|
| 495 |
+
"speaker_id_map": {
|
| 496 |
+
"Cori_Samuel": 0,
|
| 497 |
+
"Kara_Shallenberg": 1,
|
| 498 |
+
"Kristin_Hughes": 2,
|
| 499 |
+
"Maria_Kasper": 3,
|
| 500 |
+
"Mike_Pelton": 4,
|
| 501 |
+
"Mark_Nelson": 5,
|
| 502 |
+
"Michael_Scherer": 6,
|
| 503 |
+
"James_K_White": 7,
|
| 504 |
+
"Rose_Ibex": 8,
|
| 505 |
+
"progressingamerica": 9,
|
| 506 |
+
"Steve_C": 10,
|
| 507 |
+
"Owlivia": 11,
|
| 508 |
+
"Paul_Hampton": 12,
|
| 509 |
+
"Jennifer_Dorr": 13,
|
| 510 |
+
"Emily_Cripps": 14,
|
| 511 |
+
"Martin_Clifton": 15
|
| 512 |
+
},
|
| 513 |
+
"piper_version": "1.0.0"
|
| 514 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- text-to-speech
|
| 5 |
+
- piper
|
| 6 |
+
- tts
|
| 7 |
+
- voice-synthesis
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# AgentVibes Custom Piper Voices
|
| 13 |
+
|
| 14 |
+
High-quality custom Piper TTS voices for the AgentVibes project.
|
| 15 |
+
|
| 16 |
+
## Voices Included
|
| 17 |
+
|
| 18 |
+
### 1. Kristin
|
| 19 |
+
- **Type:** US English female
|
| 20 |
+
- **License:** Public Domain
|
| 21 |
+
- **Quality:** Medium (2000 epochs)
|
| 22 |
+
- **Dataset:** ~11.5 hours from LibriVox.org
|
| 23 |
+
- **Creator:** Bryce Beattie
|
| 24 |
+
- **Source:** https://brycebeattie.com/files/tts/
|
| 25 |
+
|
| 26 |
+
### 2. Jenny
|
| 27 |
+
- **Type:** UK English female (Irish accent)
|
| 28 |
+
- **License:** CC BY (Attribution required)
|
| 29 |
+
- **Quality:** High
|
| 30 |
+
- **Dataset:** Dioco (Kaggle)
|
| 31 |
+
- **Creator:** Bryce Beattie
|
| 32 |
+
- **Source:** https://brycebeattie.com/files/tts/
|
| 33 |
+
|
| 34 |
+
### 3. Tracy (ManyVoice)
|
| 35 |
+
- **Type:** Multi-speaker (16 voices: 12 US English, 4 UK English)
|
| 36 |
+
- **License:** Public Domain
|
| 37 |
+
- **Quality:** Medium (400 epochs)
|
| 38 |
+
- **Dataset:** ~8 hours per voice from LibriVox.org
|
| 39 |
+
- **Creator:** Bryce Beattie
|
| 40 |
+
- **Source:** https://brycebeattie.com/files/tts/
|
| 41 |
+
|
| 42 |
+
## Usage
|
| 43 |
+
|
| 44 |
+
### With AgentVibes
|
| 45 |
+
|
| 46 |
+
These voices are automatically available when using AgentVibes with Piper TTS provider.
|
| 47 |
+
|
| 48 |
+
Install AgentVibes:
|
| 49 |
+
```bash
|
| 50 |
+
npx agentvibes@beta install
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
Switch to Piper provider:
|
| 54 |
+
```bash
|
| 55 |
+
/agent-vibes:provider switch piper
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
Use custom voices:
|
| 59 |
+
```bash
|
| 60 |
+
/agent-vibes:switch kristin
|
| 61 |
+
/agent-vibes:switch jenny
|
| 62 |
+
/agent-vibes:switch tracy
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
### Manual Download
|
| 66 |
+
|
| 67 |
+
```bash
|
| 68 |
+
# Download all voices
|
| 69 |
+
git clone https://huggingface.co/agentvibes/piper-custom-voices
|
| 70 |
+
|
| 71 |
+
# Or download individual voices
|
| 72 |
+
wget https://huggingface.co/agentvibes/piper-custom-voices/resolve/main/kristin.onnx
|
| 73 |
+
wget https://huggingface.co/agentvibes/piper-custom-voices/resolve/main/kristin.onnx.json
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
### With Piper TTS
|
| 77 |
+
|
| 78 |
+
```bash
|
| 79 |
+
echo "Hello from Kristin" | piper \
|
| 80 |
+
--model kristin.onnx \
|
| 81 |
+
--output_file output.wav
|
| 82 |
+
```
|
| 83 |
+
|
| 84 |
+
## File Sizes
|
| 85 |
+
|
| 86 |
+
- **kristin.onnx**: ~64MB
|
| 87 |
+
- **jenny.onnx**: ~64MB
|
| 88 |
+
- **tracy.onnx**: ~74MB
|
| 89 |
+
|
| 90 |
+
## Attribution
|
| 91 |
+
|
| 92 |
+
All voices created by **Bryce Beattie** (https://brycebeattie.com/files/tts/)
|
| 93 |
+
|
| 94 |
+
### Creator's Permission
|
| 95 |
+
|
| 96 |
+
> "Feel free to use these for any legal and ethical purpose. If somebody wants to upload these to HuggingFace or somewhere similar, you have my blessing."
|
| 97 |
+
>
|
| 98 |
+
> — Bryce Beattie, https://brycebeattie.com/files/tts/
|
| 99 |
+
|
| 100 |
+
### Voice Licenses
|
| 101 |
+
|
| 102 |
+
- **Kristin:** Public Domain (LibriVox recordings)
|
| 103 |
+
- **Jenny:** CC BY (Attribution required - Dioco dataset)
|
| 104 |
+
- **Tracy:** Public Domain (LibriVox recordings)
|
| 105 |
+
|
| 106 |
+
## License
|
| 107 |
+
|
| 108 |
+
- **Repository License:** Apache 2.0
|
| 109 |
+
- **Voice Licenses:** See individual voice descriptions above
|
| 110 |
+
- **Dataset Sources:** LibriVox.org (Public Domain), Dioco/Kaggle (CC BY)
|
| 111 |
+
|
| 112 |
+
## Links
|
| 113 |
+
|
| 114 |
+
- **AgentVibes:** https://github.com/paulpreibisch/AgentVibes
|
| 115 |
+
- **Piper TTS:** https://github.com/rhasspy/piper
|
| 116 |
+
- **Voice Creator:** https://brycebeattie.com/files/tts/
|
| 117 |
+
- **HuggingFace Voices:** https://huggingface.co/rhasspy/piper-voices
|
| 118 |
+
|
| 119 |
+
## Technical Details
|
| 120 |
+
|
| 121 |
+
- **Format:** ONNX (Open Neural Network Exchange)
|
| 122 |
+
- **Engine:** Piper TTS (https://github.com/rhasspy/piper)
|
| 123 |
+
- **Training:** LibriVox public domain audiobooks
|
| 124 |
+
- **Quality:** Medium to High (400-2000 epochs)
|
| 125 |
+
- **Enhancements:** Sound quality improvements applied during training
|
| 126 |
+
|
| 127 |
+
## Contributing
|
| 128 |
+
|
| 129 |
+
Found a bug or want to suggest a voice? Open an issue at:
|
| 130 |
+
https://github.com/paulpreibisch/AgentVibes/issues
|
jenny.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d33f72ffbabcbbcb673ff6fac06949e8b1a0e56fca0ffd97ae557ac614bab8f1
|
| 3 |
+
size 63531379
|
jenny.onnx.json
ADDED
|
@@ -0,0 +1,497 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "training",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "jenny"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en"
|
| 12 |
+
},
|
| 13 |
+
"inference": {
|
| 14 |
+
"noise_scale": 0.667,
|
| 15 |
+
"length_scale": 1,
|
| 16 |
+
"noise_w": 0.8
|
| 17 |
+
},
|
| 18 |
+
"phoneme_type": "espeak",
|
| 19 |
+
"phoneme_map": {},
|
| 20 |
+
"phoneme_id_map": {
|
| 21 |
+
" ": [
|
| 22 |
+
3
|
| 23 |
+
],
|
| 24 |
+
"!": [
|
| 25 |
+
4
|
| 26 |
+
],
|
| 27 |
+
"\"": [
|
| 28 |
+
150
|
| 29 |
+
],
|
| 30 |
+
"#": [
|
| 31 |
+
149
|
| 32 |
+
],
|
| 33 |
+
"$": [
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"'": [
|
| 37 |
+
5
|
| 38 |
+
],
|
| 39 |
+
"(": [
|
| 40 |
+
6
|
| 41 |
+
],
|
| 42 |
+
")": [
|
| 43 |
+
7
|
| 44 |
+
],
|
| 45 |
+
",": [
|
| 46 |
+
8
|
| 47 |
+
],
|
| 48 |
+
"-": [
|
| 49 |
+
9
|
| 50 |
+
],
|
| 51 |
+
".": [
|
| 52 |
+
10
|
| 53 |
+
],
|
| 54 |
+
"0": [
|
| 55 |
+
130
|
| 56 |
+
],
|
| 57 |
+
"1": [
|
| 58 |
+
131
|
| 59 |
+
],
|
| 60 |
+
"2": [
|
| 61 |
+
132
|
| 62 |
+
],
|
| 63 |
+
"3": [
|
| 64 |
+
133
|
| 65 |
+
],
|
| 66 |
+
"4": [
|
| 67 |
+
134
|
| 68 |
+
],
|
| 69 |
+
"5": [
|
| 70 |
+
135
|
| 71 |
+
],
|
| 72 |
+
"6": [
|
| 73 |
+
136
|
| 74 |
+
],
|
| 75 |
+
"7": [
|
| 76 |
+
137
|
| 77 |
+
],
|
| 78 |
+
"8": [
|
| 79 |
+
138
|
| 80 |
+
],
|
| 81 |
+
"9": [
|
| 82 |
+
139
|
| 83 |
+
],
|
| 84 |
+
":": [
|
| 85 |
+
11
|
| 86 |
+
],
|
| 87 |
+
";": [
|
| 88 |
+
12
|
| 89 |
+
],
|
| 90 |
+
"?": [
|
| 91 |
+
13
|
| 92 |
+
],
|
| 93 |
+
"X": [
|
| 94 |
+
156
|
| 95 |
+
],
|
| 96 |
+
"^": [
|
| 97 |
+
1
|
| 98 |
+
],
|
| 99 |
+
"_": [
|
| 100 |
+
0
|
| 101 |
+
],
|
| 102 |
+
"a": [
|
| 103 |
+
14
|
| 104 |
+
],
|
| 105 |
+
"b": [
|
| 106 |
+
15
|
| 107 |
+
],
|
| 108 |
+
"c": [
|
| 109 |
+
16
|
| 110 |
+
],
|
| 111 |
+
"d": [
|
| 112 |
+
17
|
| 113 |
+
],
|
| 114 |
+
"e": [
|
| 115 |
+
18
|
| 116 |
+
],
|
| 117 |
+
"f": [
|
| 118 |
+
19
|
| 119 |
+
],
|
| 120 |
+
"g": [
|
| 121 |
+
154
|
| 122 |
+
],
|
| 123 |
+
"h": [
|
| 124 |
+
20
|
| 125 |
+
],
|
| 126 |
+
"i": [
|
| 127 |
+
21
|
| 128 |
+
],
|
| 129 |
+
"j": [
|
| 130 |
+
22
|
| 131 |
+
],
|
| 132 |
+
"k": [
|
| 133 |
+
23
|
| 134 |
+
],
|
| 135 |
+
"l": [
|
| 136 |
+
24
|
| 137 |
+
],
|
| 138 |
+
"m": [
|
| 139 |
+
25
|
| 140 |
+
],
|
| 141 |
+
"n": [
|
| 142 |
+
26
|
| 143 |
+
],
|
| 144 |
+
"o": [
|
| 145 |
+
27
|
| 146 |
+
],
|
| 147 |
+
"p": [
|
| 148 |
+
28
|
| 149 |
+
],
|
| 150 |
+
"q": [
|
| 151 |
+
29
|
| 152 |
+
],
|
| 153 |
+
"r": [
|
| 154 |
+
30
|
| 155 |
+
],
|
| 156 |
+
"s": [
|
| 157 |
+
31
|
| 158 |
+
],
|
| 159 |
+
"t": [
|
| 160 |
+
32
|
| 161 |
+
],
|
| 162 |
+
"u": [
|
| 163 |
+
33
|
| 164 |
+
],
|
| 165 |
+
"v": [
|
| 166 |
+
34
|
| 167 |
+
],
|
| 168 |
+
"w": [
|
| 169 |
+
35
|
| 170 |
+
],
|
| 171 |
+
"x": [
|
| 172 |
+
36
|
| 173 |
+
],
|
| 174 |
+
"y": [
|
| 175 |
+
37
|
| 176 |
+
],
|
| 177 |
+
"z": [
|
| 178 |
+
38
|
| 179 |
+
],
|
| 180 |
+
"æ": [
|
| 181 |
+
39
|
| 182 |
+
],
|
| 183 |
+
"ç": [
|
| 184 |
+
40
|
| 185 |
+
],
|
| 186 |
+
"ð": [
|
| 187 |
+
41
|
| 188 |
+
],
|
| 189 |
+
"ø": [
|
| 190 |
+
42
|
| 191 |
+
],
|
| 192 |
+
"ħ": [
|
| 193 |
+
43
|
| 194 |
+
],
|
| 195 |
+
"ŋ": [
|
| 196 |
+
44
|
| 197 |
+
],
|
| 198 |
+
"œ": [
|
| 199 |
+
45
|
| 200 |
+
],
|
| 201 |
+
"ǀ": [
|
| 202 |
+
46
|
| 203 |
+
],
|
| 204 |
+
"ǁ": [
|
| 205 |
+
47
|
| 206 |
+
],
|
| 207 |
+
"ǂ": [
|
| 208 |
+
48
|
| 209 |
+
],
|
| 210 |
+
"ǃ": [
|
| 211 |
+
49
|
| 212 |
+
],
|
| 213 |
+
"ɐ": [
|
| 214 |
+
50
|
| 215 |
+
],
|
| 216 |
+
"ɑ": [
|
| 217 |
+
51
|
| 218 |
+
],
|
| 219 |
+
"ɒ": [
|
| 220 |
+
52
|
| 221 |
+
],
|
| 222 |
+
"ɓ": [
|
| 223 |
+
53
|
| 224 |
+
],
|
| 225 |
+
"ɔ": [
|
| 226 |
+
54
|
| 227 |
+
],
|
| 228 |
+
"ɕ": [
|
| 229 |
+
55
|
| 230 |
+
],
|
| 231 |
+
"ɖ": [
|
| 232 |
+
56
|
| 233 |
+
],
|
| 234 |
+
"ɗ": [
|
| 235 |
+
57
|
| 236 |
+
],
|
| 237 |
+
"ɘ": [
|
| 238 |
+
58
|
| 239 |
+
],
|
| 240 |
+
"ə": [
|
| 241 |
+
59
|
| 242 |
+
],
|
| 243 |
+
"ɚ": [
|
| 244 |
+
60
|
| 245 |
+
],
|
| 246 |
+
"ɛ": [
|
| 247 |
+
61
|
| 248 |
+
],
|
| 249 |
+
"ɜ": [
|
| 250 |
+
62
|
| 251 |
+
],
|
| 252 |
+
"ɞ": [
|
| 253 |
+
63
|
| 254 |
+
],
|
| 255 |
+
"ɟ": [
|
| 256 |
+
64
|
| 257 |
+
],
|
| 258 |
+
"ɠ": [
|
| 259 |
+
65
|
| 260 |
+
],
|
| 261 |
+
"ɡ": [
|
| 262 |
+
66
|
| 263 |
+
],
|
| 264 |
+
"ɢ": [
|
| 265 |
+
67
|
| 266 |
+
],
|
| 267 |
+
"ɣ": [
|
| 268 |
+
68
|
| 269 |
+
],
|
| 270 |
+
"ɤ": [
|
| 271 |
+
69
|
| 272 |
+
],
|
| 273 |
+
"ɥ": [
|
| 274 |
+
70
|
| 275 |
+
],
|
| 276 |
+
"ɦ": [
|
| 277 |
+
71
|
| 278 |
+
],
|
| 279 |
+
"ɧ": [
|
| 280 |
+
72
|
| 281 |
+
],
|
| 282 |
+
"ɨ": [
|
| 283 |
+
73
|
| 284 |
+
],
|
| 285 |
+
"ɪ": [
|
| 286 |
+
74
|
| 287 |
+
],
|
| 288 |
+
"ɫ": [
|
| 289 |
+
75
|
| 290 |
+
],
|
| 291 |
+
"ɬ": [
|
| 292 |
+
76
|
| 293 |
+
],
|
| 294 |
+
"ɭ": [
|
| 295 |
+
77
|
| 296 |
+
],
|
| 297 |
+
"ɮ": [
|
| 298 |
+
78
|
| 299 |
+
],
|
| 300 |
+
"ɯ": [
|
| 301 |
+
79
|
| 302 |
+
],
|
| 303 |
+
"ɰ": [
|
| 304 |
+
80
|
| 305 |
+
],
|
| 306 |
+
"ɱ": [
|
| 307 |
+
81
|
| 308 |
+
],
|
| 309 |
+
"ɲ": [
|
| 310 |
+
82
|
| 311 |
+
],
|
| 312 |
+
"ɳ": [
|
| 313 |
+
83
|
| 314 |
+
],
|
| 315 |
+
"ɴ": [
|
| 316 |
+
84
|
| 317 |
+
],
|
| 318 |
+
"ɵ": [
|
| 319 |
+
85
|
| 320 |
+
],
|
| 321 |
+
"ɶ": [
|
| 322 |
+
86
|
| 323 |
+
],
|
| 324 |
+
"ɸ": [
|
| 325 |
+
87
|
| 326 |
+
],
|
| 327 |
+
"ɹ": [
|
| 328 |
+
88
|
| 329 |
+
],
|
| 330 |
+
"ɺ": [
|
| 331 |
+
89
|
| 332 |
+
],
|
| 333 |
+
"ɻ": [
|
| 334 |
+
90
|
| 335 |
+
],
|
| 336 |
+
"ɽ": [
|
| 337 |
+
91
|
| 338 |
+
],
|
| 339 |
+
"ɾ": [
|
| 340 |
+
92
|
| 341 |
+
],
|
| 342 |
+
"ʀ": [
|
| 343 |
+
93
|
| 344 |
+
],
|
| 345 |
+
"ʁ": [
|
| 346 |
+
94
|
| 347 |
+
],
|
| 348 |
+
"ʂ": [
|
| 349 |
+
95
|
| 350 |
+
],
|
| 351 |
+
"ʃ": [
|
| 352 |
+
96
|
| 353 |
+
],
|
| 354 |
+
"ʄ": [
|
| 355 |
+
97
|
| 356 |
+
],
|
| 357 |
+
"ʈ": [
|
| 358 |
+
98
|
| 359 |
+
],
|
| 360 |
+
"ʉ": [
|
| 361 |
+
99
|
| 362 |
+
],
|
| 363 |
+
"ʊ": [
|
| 364 |
+
100
|
| 365 |
+
],
|
| 366 |
+
"ʋ": [
|
| 367 |
+
101
|
| 368 |
+
],
|
| 369 |
+
"ʌ": [
|
| 370 |
+
102
|
| 371 |
+
],
|
| 372 |
+
"ʍ": [
|
| 373 |
+
103
|
| 374 |
+
],
|
| 375 |
+
"ʎ": [
|
| 376 |
+
104
|
| 377 |
+
],
|
| 378 |
+
"ʏ": [
|
| 379 |
+
105
|
| 380 |
+
],
|
| 381 |
+
"ʐ": [
|
| 382 |
+
106
|
| 383 |
+
],
|
| 384 |
+
"ʑ": [
|
| 385 |
+
107
|
| 386 |
+
],
|
| 387 |
+
"ʒ": [
|
| 388 |
+
108
|
| 389 |
+
],
|
| 390 |
+
"ʔ": [
|
| 391 |
+
109
|
| 392 |
+
],
|
| 393 |
+
"ʕ": [
|
| 394 |
+
110
|
| 395 |
+
],
|
| 396 |
+
"ʘ": [
|
| 397 |
+
111
|
| 398 |
+
],
|
| 399 |
+
"ʙ": [
|
| 400 |
+
112
|
| 401 |
+
],
|
| 402 |
+
"ʛ": [
|
| 403 |
+
113
|
| 404 |
+
],
|
| 405 |
+
"ʜ": [
|
| 406 |
+
114
|
| 407 |
+
],
|
| 408 |
+
"ʝ": [
|
| 409 |
+
115
|
| 410 |
+
],
|
| 411 |
+
"ʟ": [
|
| 412 |
+
116
|
| 413 |
+
],
|
| 414 |
+
"ʡ": [
|
| 415 |
+
117
|
| 416 |
+
],
|
| 417 |
+
"ʢ": [
|
| 418 |
+
118
|
| 419 |
+
],
|
| 420 |
+
"ʦ": [
|
| 421 |
+
155
|
| 422 |
+
],
|
| 423 |
+
"ʰ": [
|
| 424 |
+
145
|
| 425 |
+
],
|
| 426 |
+
"ʲ": [
|
| 427 |
+
119
|
| 428 |
+
],
|
| 429 |
+
"ˈ": [
|
| 430 |
+
120
|
| 431 |
+
],
|
| 432 |
+
"ˌ": [
|
| 433 |
+
121
|
| 434 |
+
],
|
| 435 |
+
"ː": [
|
| 436 |
+
122
|
| 437 |
+
],
|
| 438 |
+
"ˑ": [
|
| 439 |
+
123
|
| 440 |
+
],
|
| 441 |
+
"˞": [
|
| 442 |
+
124
|
| 443 |
+
],
|
| 444 |
+
"ˤ": [
|
| 445 |
+
146
|
| 446 |
+
],
|
| 447 |
+
"̃": [
|
| 448 |
+
141
|
| 449 |
+
],
|
| 450 |
+
"̧": [
|
| 451 |
+
140
|
| 452 |
+
],
|
| 453 |
+
"̩": [
|
| 454 |
+
144
|
| 455 |
+
],
|
| 456 |
+
"̪": [
|
| 457 |
+
142
|
| 458 |
+
],
|
| 459 |
+
"̯": [
|
| 460 |
+
143
|
| 461 |
+
],
|
| 462 |
+
"̺": [
|
| 463 |
+
152
|
| 464 |
+
],
|
| 465 |
+
"̻": [
|
| 466 |
+
153
|
| 467 |
+
],
|
| 468 |
+
"β": [
|
| 469 |
+
125
|
| 470 |
+
],
|
| 471 |
+
"ε": [
|
| 472 |
+
147
|
| 473 |
+
],
|
| 474 |
+
"θ": [
|
| 475 |
+
126
|
| 476 |
+
],
|
| 477 |
+
"χ": [
|
| 478 |
+
127
|
| 479 |
+
],
|
| 480 |
+
"ᵻ": [
|
| 481 |
+
128
|
| 482 |
+
],
|
| 483 |
+
"↑": [
|
| 484 |
+
151
|
| 485 |
+
],
|
| 486 |
+
"↓": [
|
| 487 |
+
148
|
| 488 |
+
],
|
| 489 |
+
"ⱱ": [
|
| 490 |
+
129
|
| 491 |
+
]
|
| 492 |
+
},
|
| 493 |
+
"num_symbols": 256,
|
| 494 |
+
"num_speakers": 1,
|
| 495 |
+
"speaker_id_map": {},
|
| 496 |
+
"piper_version": "1.0.0"
|
| 497 |
+
}
|
kristin.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5849957f929cbf720c258f8458692d6103fff2f0e3d3b19c8259474bb06a18d4
|
| 3 |
+
size 63531379
|
kristin.onnx.json
ADDED
|
@@ -0,0 +1,497 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "training",
|
| 3 |
+
"audio": {
|
| 4 |
+
"sample_rate": 22050,
|
| 5 |
+
"quality": "kristin"
|
| 6 |
+
},
|
| 7 |
+
"espeak": {
|
| 8 |
+
"voice": "en"
|
| 9 |
+
},
|
| 10 |
+
"language": {
|
| 11 |
+
"code": "en"
|
| 12 |
+
},
|
| 13 |
+
"inference": {
|
| 14 |
+
"noise_scale": 0.667,
|
| 15 |
+
"length_scale": 1,
|
| 16 |
+
"noise_w": 0.8
|
| 17 |
+
},
|
| 18 |
+
"phoneme_type": "espeak",
|
| 19 |
+
"phoneme_map": {},
|
| 20 |
+
"phoneme_id_map": {
|
| 21 |
+
" ": [
|
| 22 |
+
3
|
| 23 |
+
],
|
| 24 |
+
"!": [
|
| 25 |
+
4
|
| 26 |
+
],
|
| 27 |
+
"\"": [
|
| 28 |
+
150
|
| 29 |
+
],
|
| 30 |
+
"#": [
|
| 31 |
+
149
|
| 32 |
+
],
|
| 33 |
+
"$": [
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"'": [
|
| 37 |
+
5
|
| 38 |
+
],
|
| 39 |
+
"(": [
|
| 40 |
+
6
|
| 41 |
+
],
|
| 42 |
+
")": [
|
| 43 |
+
7
|
| 44 |
+
],
|
| 45 |
+
",": [
|
| 46 |
+
8
|
| 47 |
+
],
|
| 48 |
+
"-": [
|
| 49 |
+
9
|
| 50 |
+
],
|
| 51 |
+
".": [
|
| 52 |
+
10
|
| 53 |
+
],
|
| 54 |
+
"0": [
|
| 55 |
+
130
|
| 56 |
+
],
|
| 57 |
+
"1": [
|
| 58 |
+
131
|
| 59 |
+
],
|
| 60 |
+
"2": [
|
| 61 |
+
132
|
| 62 |
+
],
|
| 63 |
+
"3": [
|
| 64 |
+
133
|
| 65 |
+
],
|
| 66 |
+
"4": [
|
| 67 |
+
134
|
| 68 |
+
],
|
| 69 |
+
"5": [
|
| 70 |
+
135
|
| 71 |
+
],
|
| 72 |
+
"6": [
|
| 73 |
+
136
|
| 74 |
+
],
|
| 75 |
+
"7": [
|
| 76 |
+
137
|
| 77 |
+
],
|
| 78 |
+
"8": [
|
| 79 |
+
138
|
| 80 |
+
],
|
| 81 |
+
"9": [
|
| 82 |
+
139
|
| 83 |
+
],
|
| 84 |
+
":": [
|
| 85 |
+
11
|
| 86 |
+
],
|
| 87 |
+
";": [
|
| 88 |
+
12
|
| 89 |
+
],
|
| 90 |
+
"?": [
|
| 91 |
+
13
|
| 92 |
+
],
|
| 93 |
+
"X": [
|
| 94 |
+
156
|
| 95 |
+
],
|
| 96 |
+
"^": [
|
| 97 |
+
1
|
| 98 |
+
],
|
| 99 |
+
"_": [
|
| 100 |
+
0
|
| 101 |
+
],
|
| 102 |
+
"a": [
|
| 103 |
+
14
|
| 104 |
+
],
|
| 105 |
+
"b": [
|
| 106 |
+
15
|
| 107 |
+
],
|
| 108 |
+
"c": [
|
| 109 |
+
16
|
| 110 |
+
],
|
| 111 |
+
"d": [
|
| 112 |
+
17
|
| 113 |
+
],
|
| 114 |
+
"e": [
|
| 115 |
+
18
|
| 116 |
+
],
|
| 117 |
+
"f": [
|
| 118 |
+
19
|
| 119 |
+
],
|
| 120 |
+
"g": [
|
| 121 |
+
154
|
| 122 |
+
],
|
| 123 |
+
"h": [
|
| 124 |
+
20
|
| 125 |
+
],
|
| 126 |
+
"i": [
|
| 127 |
+
21
|
| 128 |
+
],
|
| 129 |
+
"j": [
|
| 130 |
+
22
|
| 131 |
+
],
|
| 132 |
+
"k": [
|
| 133 |
+
23
|
| 134 |
+
],
|
| 135 |
+
"l": [
|
| 136 |
+
24
|
| 137 |
+
],
|
| 138 |
+
"m": [
|
| 139 |
+
25
|
| 140 |
+
],
|
| 141 |
+
"n": [
|
| 142 |
+
26
|
| 143 |
+
],
|
| 144 |
+
"o": [
|
| 145 |
+
27
|
| 146 |
+
],
|
| 147 |
+
"p": [
|
| 148 |
+
28
|
| 149 |
+
],
|
| 150 |
+
"q": [
|
| 151 |
+
29
|
| 152 |
+
],
|
| 153 |
+
"r": [
|
| 154 |
+
30
|
| 155 |
+
],
|
| 156 |
+
"s": [
|
| 157 |
+
31
|
| 158 |
+
],
|
| 159 |
+
"t": [
|
| 160 |
+
32
|
| 161 |
+
],
|
| 162 |
+
"u": [
|
| 163 |
+
33
|
| 164 |
+
],
|
| 165 |
+
"v": [
|
| 166 |
+
34
|
| 167 |
+
],
|
| 168 |
+
"w": [
|
| 169 |
+
35
|
| 170 |
+
],
|
| 171 |
+
"x": [
|
| 172 |
+
36
|
| 173 |
+
],
|
| 174 |
+
"y": [
|
| 175 |
+
37
|
| 176 |
+
],
|
| 177 |
+
"z": [
|
| 178 |
+
38
|
| 179 |
+
],
|
| 180 |
+
"æ": [
|
| 181 |
+
39
|
| 182 |
+
],
|
| 183 |
+
"ç": [
|
| 184 |
+
40
|
| 185 |
+
],
|
| 186 |
+
"ð": [
|
| 187 |
+
41
|
| 188 |
+
],
|
| 189 |
+
"ø": [
|
| 190 |
+
42
|
| 191 |
+
],
|
| 192 |
+
"ħ": [
|
| 193 |
+
43
|
| 194 |
+
],
|
| 195 |
+
"ŋ": [
|
| 196 |
+
44
|
| 197 |
+
],
|
| 198 |
+
"œ": [
|
| 199 |
+
45
|
| 200 |
+
],
|
| 201 |
+
"ǀ": [
|
| 202 |
+
46
|
| 203 |
+
],
|
| 204 |
+
"ǁ": [
|
| 205 |
+
47
|
| 206 |
+
],
|
| 207 |
+
"ǂ": [
|
| 208 |
+
48
|
| 209 |
+
],
|
| 210 |
+
"ǃ": [
|
| 211 |
+
49
|
| 212 |
+
],
|
| 213 |
+
"ɐ": [
|
| 214 |
+
50
|
| 215 |
+
],
|
| 216 |
+
"ɑ": [
|
| 217 |
+
51
|
| 218 |
+
],
|
| 219 |
+
"ɒ": [
|
| 220 |
+
52
|
| 221 |
+
],
|
| 222 |
+
"ɓ": [
|
| 223 |
+
53
|
| 224 |
+
],
|
| 225 |
+
"ɔ": [
|
| 226 |
+
54
|
| 227 |
+
],
|
| 228 |
+
"ɕ": [
|
| 229 |
+
55
|
| 230 |
+
],
|
| 231 |
+
"ɖ": [
|
| 232 |
+
56
|
| 233 |
+
],
|
| 234 |
+
"ɗ": [
|
| 235 |
+
57
|
| 236 |
+
],
|
| 237 |
+
"ɘ": [
|
| 238 |
+
58
|
| 239 |
+
],
|
| 240 |
+
"ə": [
|
| 241 |
+
59
|
| 242 |
+
],
|
| 243 |
+
"ɚ": [
|
| 244 |
+
60
|
| 245 |
+
],
|
| 246 |
+
"ɛ": [
|
| 247 |
+
61
|
| 248 |
+
],
|
| 249 |
+
"ɜ": [
|
| 250 |
+
62
|
| 251 |
+
],
|
| 252 |
+
"ɞ": [
|
| 253 |
+
63
|
| 254 |
+
],
|
| 255 |
+
"ɟ": [
|
| 256 |
+
64
|
| 257 |
+
],
|
| 258 |
+
"ɠ": [
|
| 259 |
+
65
|
| 260 |
+
],
|
| 261 |
+
"ɡ": [
|
| 262 |
+
66
|
| 263 |
+
],
|
| 264 |
+
"ɢ": [
|
| 265 |
+
67
|
| 266 |
+
],
|
| 267 |
+
"ɣ": [
|
| 268 |
+
68
|
| 269 |
+
],
|
| 270 |
+
"ɤ": [
|
| 271 |
+
69
|
| 272 |
+
],
|
| 273 |
+
"ɥ": [
|
| 274 |
+
70
|
| 275 |
+
],
|
| 276 |
+
"ɦ": [
|
| 277 |
+
71
|
| 278 |
+
],
|
| 279 |
+
"ɧ": [
|
| 280 |
+
72
|
| 281 |
+
],
|
| 282 |
+
"ɨ": [
|
| 283 |
+
73
|
| 284 |
+
],
|
| 285 |
+
"ɪ": [
|
| 286 |
+
74
|
| 287 |
+
],
|
| 288 |
+
"ɫ": [
|
| 289 |
+
75
|
| 290 |
+
],
|
| 291 |
+
"ɬ": [
|
| 292 |
+
76
|
| 293 |
+
],
|
| 294 |
+
"ɭ": [
|
| 295 |
+
77
|
| 296 |
+
],
|
| 297 |
+
"ɮ": [
|
| 298 |
+
78
|
| 299 |
+
],
|
| 300 |
+
"ɯ": [
|
| 301 |
+
79
|
| 302 |
+
],
|
| 303 |
+
"ɰ": [
|
| 304 |
+
80
|
| 305 |
+
],
|
| 306 |
+
"ɱ": [
|
| 307 |
+
81
|
| 308 |
+
],
|
| 309 |
+
"ɲ": [
|
| 310 |
+
82
|
| 311 |
+
],
|
| 312 |
+
"ɳ": [
|
| 313 |
+
83
|
| 314 |
+
],
|
| 315 |
+
"ɴ": [
|
| 316 |
+
84
|
| 317 |
+
],
|
| 318 |
+
"ɵ": [
|
| 319 |
+
85
|
| 320 |
+
],
|
| 321 |
+
"ɶ": [
|
| 322 |
+
86
|
| 323 |
+
],
|
| 324 |
+
"ɸ": [
|
| 325 |
+
87
|
| 326 |
+
],
|
| 327 |
+
"ɹ": [
|
| 328 |
+
88
|
| 329 |
+
],
|
| 330 |
+
"ɺ": [
|
| 331 |
+
89
|
| 332 |
+
],
|
| 333 |
+
"ɻ": [
|
| 334 |
+
90
|
| 335 |
+
],
|
| 336 |
+
"ɽ": [
|
| 337 |
+
91
|
| 338 |
+
],
|
| 339 |
+
"ɾ": [
|
| 340 |
+
92
|
| 341 |
+
],
|
| 342 |
+
"ʀ": [
|
| 343 |
+
93
|
| 344 |
+
],
|
| 345 |
+
"ʁ": [
|
| 346 |
+
94
|
| 347 |
+
],
|
| 348 |
+
"ʂ": [
|
| 349 |
+
95
|
| 350 |
+
],
|
| 351 |
+
"ʃ": [
|
| 352 |
+
96
|
| 353 |
+
],
|
| 354 |
+
"ʄ": [
|
| 355 |
+
97
|
| 356 |
+
],
|
| 357 |
+
"ʈ": [
|
| 358 |
+
98
|
| 359 |
+
],
|
| 360 |
+
"ʉ": [
|
| 361 |
+
99
|
| 362 |
+
],
|
| 363 |
+
"ʊ": [
|
| 364 |
+
100
|
| 365 |
+
],
|
| 366 |
+
"ʋ": [
|
| 367 |
+
101
|
| 368 |
+
],
|
| 369 |
+
"ʌ": [
|
| 370 |
+
102
|
| 371 |
+
],
|
| 372 |
+
"ʍ": [
|
| 373 |
+
103
|
| 374 |
+
],
|
| 375 |
+
"ʎ": [
|
| 376 |
+
104
|
| 377 |
+
],
|
| 378 |
+
"ʏ": [
|
| 379 |
+
105
|
| 380 |
+
],
|
| 381 |
+
"ʐ": [
|
| 382 |
+
106
|
| 383 |
+
],
|
| 384 |
+
"ʑ": [
|
| 385 |
+
107
|
| 386 |
+
],
|
| 387 |
+
"ʒ": [
|
| 388 |
+
108
|
| 389 |
+
],
|
| 390 |
+
"ʔ": [
|
| 391 |
+
109
|
| 392 |
+
],
|
| 393 |
+
"ʕ": [
|
| 394 |
+
110
|
| 395 |
+
],
|
| 396 |
+
"ʘ": [
|
| 397 |
+
111
|
| 398 |
+
],
|
| 399 |
+
"ʙ": [
|
| 400 |
+
112
|
| 401 |
+
],
|
| 402 |
+
"ʛ": [
|
| 403 |
+
113
|
| 404 |
+
],
|
| 405 |
+
"ʜ": [
|
| 406 |
+
114
|
| 407 |
+
],
|
| 408 |
+
"ʝ": [
|
| 409 |
+
115
|
| 410 |
+
],
|
| 411 |
+
"ʟ": [
|
| 412 |
+
116
|
| 413 |
+
],
|
| 414 |
+
"ʡ": [
|
| 415 |
+
117
|
| 416 |
+
],
|
| 417 |
+
"ʢ": [
|
| 418 |
+
118
|
| 419 |
+
],
|
| 420 |
+
"ʦ": [
|
| 421 |
+
155
|
| 422 |
+
],
|
| 423 |
+
"ʰ": [
|
| 424 |
+
145
|
| 425 |
+
],
|
| 426 |
+
"ʲ": [
|
| 427 |
+
119
|
| 428 |
+
],
|
| 429 |
+
"ˈ": [
|
| 430 |
+
120
|
| 431 |
+
],
|
| 432 |
+
"ˌ": [
|
| 433 |
+
121
|
| 434 |
+
],
|
| 435 |
+
"ː": [
|
| 436 |
+
122
|
| 437 |
+
],
|
| 438 |
+
"ˑ": [
|
| 439 |
+
123
|
| 440 |
+
],
|
| 441 |
+
"˞": [
|
| 442 |
+
124
|
| 443 |
+
],
|
| 444 |
+
"ˤ": [
|
| 445 |
+
146
|
| 446 |
+
],
|
| 447 |
+
"̃": [
|
| 448 |
+
141
|
| 449 |
+
],
|
| 450 |
+
"̧": [
|
| 451 |
+
140
|
| 452 |
+
],
|
| 453 |
+
"̩": [
|
| 454 |
+
144
|
| 455 |
+
],
|
| 456 |
+
"̪": [
|
| 457 |
+
142
|
| 458 |
+
],
|
| 459 |
+
"̯": [
|
| 460 |
+
143
|
| 461 |
+
],
|
| 462 |
+
"̺": [
|
| 463 |
+
152
|
| 464 |
+
],
|
| 465 |
+
"̻": [
|
| 466 |
+
153
|
| 467 |
+
],
|
| 468 |
+
"β": [
|
| 469 |
+
125
|
| 470 |
+
],
|
| 471 |
+
"ε": [
|
| 472 |
+
147
|
| 473 |
+
],
|
| 474 |
+
"θ": [
|
| 475 |
+
126
|
| 476 |
+
],
|
| 477 |
+
"χ": [
|
| 478 |
+
127
|
| 479 |
+
],
|
| 480 |
+
"ᵻ": [
|
| 481 |
+
128
|
| 482 |
+
],
|
| 483 |
+
"↑": [
|
| 484 |
+
151
|
| 485 |
+
],
|
| 486 |
+
"↓": [
|
| 487 |
+
148
|
| 488 |
+
],
|
| 489 |
+
"ⱱ": [
|
| 490 |
+
129
|
| 491 |
+
]
|
| 492 |
+
},
|
| 493 |
+
"num_symbols": 256,
|
| 494 |
+
"num_speakers": 1,
|
| 495 |
+
"speaker_id_map": {},
|
| 496 |
+
"piper_version": "1.0.0"
|
| 497 |
+
}
|
preview-16speakers.sh
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
#
|
| 3 |
+
# Preview all 16 speakers in the 16Speakers.onnx voice model
|
| 4 |
+
#
|
| 5 |
+
|
| 6 |
+
MODEL_PATH="/home/fire/claude/AgentVibes/mcp-server/voices/16Speakers.onnx"
|
| 7 |
+
OUTPUT_DIR="/home/fire/claude/AgentVibes/mcp-server/voices/previews"
|
| 8 |
+
SAMPLE_TEXT="Hello, this is speaker number"
|
| 9 |
+
|
| 10 |
+
# Create output directory
|
| 11 |
+
mkdir -p "$OUTPUT_DIR"
|
| 12 |
+
|
| 13 |
+
# Speaker names from the JSON file
|
| 14 |
+
declare -a SPEAKERS=(
|
| 15 |
+
"Cori_Samuel"
|
| 16 |
+
"Kara_Shallenberg"
|
| 17 |
+
"Kristin_Hughes"
|
| 18 |
+
"Maria_Kasper"
|
| 19 |
+
"Mike_Pelton"
|
| 20 |
+
"Mark_Nelson"
|
| 21 |
+
"Michael_Scherer"
|
| 22 |
+
"James_K_White"
|
| 23 |
+
"Rose_Ibex"
|
| 24 |
+
"progressingamerica"
|
| 25 |
+
"Steve_C"
|
| 26 |
+
"Owlivia"
|
| 27 |
+
"Paul_Hampton"
|
| 28 |
+
"Jennifer_Dorr"
|
| 29 |
+
"Emily_Cripps"
|
| 30 |
+
"Martin_Clifton"
|
| 31 |
+
)
|
| 32 |
+
|
| 33 |
+
echo "🎤 Generating voice previews for all 16 speakers..."
|
| 34 |
+
echo ""
|
| 35 |
+
|
| 36 |
+
# Generate preview for each speaker
|
| 37 |
+
for i in "${!SPEAKERS[@]}"; do
|
| 38 |
+
SPEAKER_NAME="${SPEAKERS[$i]}"
|
| 39 |
+
OUTPUT_FILE="$OUTPUT_DIR/speaker_${i}_${SPEAKER_NAME}.wav"
|
| 40 |
+
|
| 41 |
+
echo "[$((i+1))/16] Generating preview for: $SPEAKER_NAME (Speaker ID: $i)"
|
| 42 |
+
|
| 43 |
+
# Generate TTS with speaker ID
|
| 44 |
+
echo "$SAMPLE_TEXT $((i+1)), $SPEAKER_NAME." | piper \
|
| 45 |
+
--model "$MODEL_PATH" \
|
| 46 |
+
--speaker "$i" \
|
| 47 |
+
--output_file "$OUTPUT_FILE" 2>/dev/null
|
| 48 |
+
|
| 49 |
+
if [ -f "$OUTPUT_FILE" ]; then
|
| 50 |
+
echo " ✅ Saved to: $OUTPUT_FILE"
|
| 51 |
+
# Play the audio
|
| 52 |
+
paplay "$OUTPUT_FILE" 2>/dev/null || aplay "$OUTPUT_FILE" 2>/dev/null || afplay "$OUTPUT_FILE" 2>/dev/null
|
| 53 |
+
sleep 1
|
| 54 |
+
else
|
| 55 |
+
echo " ❌ Failed to generate"
|
| 56 |
+
fi
|
| 57 |
+
echo ""
|
| 58 |
+
done
|
| 59 |
+
|
| 60 |
+
echo "🎉 Preview generation complete!"
|
| 61 |
+
echo "📂 All previews saved to: $OUTPUT_DIR"
|
| 62 |
+
ls -lh "$OUTPUT_DIR"
|
previews/speaker_0_Cori_Samuel.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a56b0420fceb4ad8dfe052b662a8129de9307579a02507717ac658230d9ac9de
|
| 3 |
+
size 153132
|
previews/speaker_10_Steve_C.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e96b021bc92c0f246829ef36b828dc0b3aa5542ad243593da96628a31a1ed0cd
|
| 3 |
+
size 173612
|
previews/speaker_11_Owlivia.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e0def459c090d69e3e6856db143953eb40f650479ef3133f8fe1f0bc7ade0a
|
| 3 |
+
size 165420
|
previews/speaker_12_Paul_Hampton.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e46104ab01877472f0f2124f1a1c655eed542c3be4d709badfe57e77831efeb
|
| 3 |
+
size 185900
|
previews/speaker_13_Jennifer_Dorr.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:273645432e4a00b42268656b23d33bfc9acf86b3cd2e270c8d5a13e968aa4a9a
|
| 3 |
+
size 142380
|
previews/speaker_14_Emily_Cripps.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:087d518c370e96d9c21c7e32d00960b0bf1cc2a47aa2f2c73c0219576cddac76
|
| 3 |
+
size 143404
|
previews/speaker_15_Martin_Clifton.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb1aca541b7c55724152ad7d51f2a766ea13076384abe75be02243a4369b39ea
|
| 3 |
+
size 148524
|
previews/speaker_1_Kara_Shallenberg.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44f749d9cecdccada45fff86ebfeb6ffa76792afe4c2261a79ea6053456882e
|
| 3 |
+
size 142892
|
previews/speaker_2_Kristin_Hughes.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4322ee3663782414aae657a6993f56993f819faf13b21e2ce7e7e959dad0b7db
|
| 3 |
+
size 157740
|
previews/speaker_3_Maria_Kasper.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e314a275031f5338fc4ed9ad5e1761678b3fc1b6f1abfee2f1cdd99fa13cce41
|
| 3 |
+
size 181292
|
previews/speaker_4_Mike_Pelton.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d30d5ab05ab9d841762126ffcc662f676604e7ce654cfa9b2d05bdcde7d8f1
|
| 3 |
+
size 144940
|
previews/speaker_5_Mark_Nelson.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f090f14e265595c4b6fea0024df241362730c0ba61d084b75134914b1015218e
|
| 3 |
+
size 152108
|
previews/speaker_6_Michael_Scherer.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc59cb5b29f9dd013bb610379f9ce0996d8ad7415ad21ca96af324f84df288db
|
| 3 |
+
size 153644
|
previews/speaker_7_James_K_White.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1f8985092522977c116323570ff25203648f185a8b29fc3504b3ce2f71a5a85
|
| 3 |
+
size 158252
|
previews/speaker_8_Rose_Ibex.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa4755fe887077d9abefc704c9f46bb05ee37567b2edd2f02bd1402dadc5c25c
|
| 3 |
+
size 137260
|
previews/speaker_9_progressingamerica.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97361dd67c4a1a93249d55d583af2df47806c4f9b4041d79567cd413fe5e5e87
|
| 3 |
+
size 166956
|