Upload 69 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +14 -0
- piper_models/en-us-amy-low/MODEL_CARD +15 -0
- piper_models/en-us-amy-low/en-us-amy-low.onnx +3 -0
- piper_models/en-us-amy-low/en-us-amy-low.onnx.json +409 -0
- piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_MODEL_CARD +15 -0
- piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_ru_RU-ruslan-medium.onnx +3 -0
- piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_ru_RU-ruslan-medium.onnx.json +493 -0
- piper_models/voice-kk-issai-high/MODEL_CARD +15 -0
- piper_models/voice-kk-issai-high/kk-issai-high.onnx +3 -0
- piper_models/voice-kk-issai-high/kk-issai-high.onnx.json +416 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/README +5 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/am/final.mdl +3 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/am/tree +0 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/conf/mfcc.conf +9 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/conf/model.conf +10 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/Gr.fst +3 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/HCLr.fst +3 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/disambig_tid.int +39 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/phones.txt +267 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/phones/word_boundary.int +227 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/graph/words.txt +0 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.dubm +0 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.ie +3 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.mat +0 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/global_cmvn.stats +3 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/online_cmvn.conf +1 -0
- vosk_models/vosk-model-en-us-0.22-lgraph/ivector/splice.conf +2 -0
- vosk_models/vosk-model-kz-0.15/README +18 -0
- vosk_models/vosk-model-kz-0.15/am/final.mdl +3 -0
- vosk_models/vosk-model-kz-0.15/am/frame_subsampling_factor +1 -0
- vosk_models/vosk-model-kz-0.15/am/tree +0 -0
- vosk_models/vosk-model-kz-0.15/conf/mfcc.conf +7 -0
- vosk_models/vosk-model-kz-0.15/conf/model.conf +10 -0
- vosk_models/vosk-model-kz-0.15/graph/HCLG.fst +3 -0
- vosk_models/vosk-model-kz-0.15/graph/disambig_tid.int +4 -0
- vosk_models/vosk-model-kz-0.15/graph/num_pdfs +1 -0
- vosk_models/vosk-model-kz-0.15/graph/phones.txt +175 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/align_lexicon.int +0 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/align_lexicon.txt +3 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/disambig.int +4 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/disambig.txt +4 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.csl +1 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.int +1 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.txt +1 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/silence.csl +1 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/word_boundary.int +170 -0
- vosk_models/vosk-model-kz-0.15/graph/phones/word_boundary.txt +170 -0
- vosk_models/vosk-model-kz-0.15/graph/words.txt +0 -0
- vosk_models/vosk-model-kz-0.15/ivector/final.dubm +0 -0
- vosk_models/vosk-model-kz-0.15/ivector/final.ie +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,17 @@ 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 |
+
vosk_models/vosk-model-en-us-0.22-lgraph/am/final.mdl filter=lfs diff=lfs merge=lfs -text
|
37 |
+
vosk_models/vosk-model-en-us-0.22-lgraph/graph/Gr.fst filter=lfs diff=lfs merge=lfs -text
|
38 |
+
vosk_models/vosk-model-en-us-0.22-lgraph/graph/HCLr.fst filter=lfs diff=lfs merge=lfs -text
|
39 |
+
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.ie filter=lfs diff=lfs merge=lfs -text
|
40 |
+
vosk_models/vosk-model-kz-0.15/am/final.mdl filter=lfs diff=lfs merge=lfs -text
|
41 |
+
vosk_models/vosk-model-kz-0.15/graph/HCLG.fst filter=lfs diff=lfs merge=lfs -text
|
42 |
+
vosk_models/vosk-model-kz-0.15/graph/phones/align_lexicon.txt filter=lfs diff=lfs merge=lfs -text
|
43 |
+
vosk_models/vosk-model-kz-0.15/ivector/final.ie filter=lfs diff=lfs merge=lfs -text
|
44 |
+
vosk_models/vosk-model-kz-0.15/rescore/G.carpa filter=lfs diff=lfs merge=lfs -text
|
45 |
+
vosk_models/vosk-model-kz-0.15/rescore/G.fst filter=lfs diff=lfs merge=lfs -text
|
46 |
+
vosk_models/vosk-model-small-ru-0.22/am/final.mdl filter=lfs diff=lfs merge=lfs -text
|
47 |
+
vosk_models/vosk-model-small-ru-0.22/graph/Gr.fst filter=lfs diff=lfs merge=lfs -text
|
48 |
+
vosk_models/vosk-model-small-ru-0.22/graph/HCLr.fst filter=lfs diff=lfs merge=lfs -text
|
49 |
+
vosk_models/vosk-model-small-ru-0.22/ivector/final.ie filter=lfs diff=lfs merge=lfs -text
|
piper_models/en-us-amy-low/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for Amy (low)
|
2 |
+
|
3 |
+
* Language: en-us (U.S. English)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: low
|
6 |
+
* Samplerate: 16,000Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/MycroftAI/mimic3-voices
|
11 |
+
* License: See URL
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English Ryan voice (low quality).
|
piper_models/en-us-amy-low/en-us-amy-low.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a91abb7de0f104358a25aded480ddacf1ff0762886325886ec406a2e86aab3
|
3 |
+
size 63104526
|
piper_models/en-us-amy-low/en-us-amy-low.onnx.json
ADDED
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 16000
|
4 |
+
},
|
5 |
+
"espeak": {
|
6 |
+
"voice": "en-us"
|
7 |
+
},
|
8 |
+
"inference": {
|
9 |
+
"noise_scale": 0.667,
|
10 |
+
"length_scale": 1,
|
11 |
+
"noise_w": 0.8
|
12 |
+
},
|
13 |
+
"phoneme_map": {},
|
14 |
+
"phoneme_id_map": {
|
15 |
+
"_": [
|
16 |
+
0
|
17 |
+
],
|
18 |
+
"^": [
|
19 |
+
1
|
20 |
+
],
|
21 |
+
"$": [
|
22 |
+
2
|
23 |
+
],
|
24 |
+
" ": [
|
25 |
+
3
|
26 |
+
],
|
27 |
+
"!": [
|
28 |
+
4
|
29 |
+
],
|
30 |
+
"'": [
|
31 |
+
5
|
32 |
+
],
|
33 |
+
"(": [
|
34 |
+
6
|
35 |
+
],
|
36 |
+
")": [
|
37 |
+
7
|
38 |
+
],
|
39 |
+
",": [
|
40 |
+
8
|
41 |
+
],
|
42 |
+
"-": [
|
43 |
+
9
|
44 |
+
],
|
45 |
+
".": [
|
46 |
+
10
|
47 |
+
],
|
48 |
+
":": [
|
49 |
+
11
|
50 |
+
],
|
51 |
+
";": [
|
52 |
+
12
|
53 |
+
],
|
54 |
+
"?": [
|
55 |
+
13
|
56 |
+
],
|
57 |
+
"a": [
|
58 |
+
14
|
59 |
+
],
|
60 |
+
"b": [
|
61 |
+
15
|
62 |
+
],
|
63 |
+
"c": [
|
64 |
+
16
|
65 |
+
],
|
66 |
+
"d": [
|
67 |
+
17
|
68 |
+
],
|
69 |
+
"e": [
|
70 |
+
18
|
71 |
+
],
|
72 |
+
"f": [
|
73 |
+
19
|
74 |
+
],
|
75 |
+
"h": [
|
76 |
+
20
|
77 |
+
],
|
78 |
+
"i": [
|
79 |
+
21
|
80 |
+
],
|
81 |
+
"j": [
|
82 |
+
22
|
83 |
+
],
|
84 |
+
"k": [
|
85 |
+
23
|
86 |
+
],
|
87 |
+
"l": [
|
88 |
+
24
|
89 |
+
],
|
90 |
+
"m": [
|
91 |
+
25
|
92 |
+
],
|
93 |
+
"n": [
|
94 |
+
26
|
95 |
+
],
|
96 |
+
"o": [
|
97 |
+
27
|
98 |
+
],
|
99 |
+
"p": [
|
100 |
+
28
|
101 |
+
],
|
102 |
+
"q": [
|
103 |
+
29
|
104 |
+
],
|
105 |
+
"r": [
|
106 |
+
30
|
107 |
+
],
|
108 |
+
"s": [
|
109 |
+
31
|
110 |
+
],
|
111 |
+
"t": [
|
112 |
+
32
|
113 |
+
],
|
114 |
+
"u": [
|
115 |
+
33
|
116 |
+
],
|
117 |
+
"v": [
|
118 |
+
34
|
119 |
+
],
|
120 |
+
"w": [
|
121 |
+
35
|
122 |
+
],
|
123 |
+
"x": [
|
124 |
+
36
|
125 |
+
],
|
126 |
+
"y": [
|
127 |
+
37
|
128 |
+
],
|
129 |
+
"z": [
|
130 |
+
38
|
131 |
+
],
|
132 |
+
"æ": [
|
133 |
+
39
|
134 |
+
],
|
135 |
+
"ç": [
|
136 |
+
40
|
137 |
+
],
|
138 |
+
"ð": [
|
139 |
+
41
|
140 |
+
],
|
141 |
+
"ø": [
|
142 |
+
42
|
143 |
+
],
|
144 |
+
"ħ": [
|
145 |
+
43
|
146 |
+
],
|
147 |
+
"ŋ": [
|
148 |
+
44
|
149 |
+
],
|
150 |
+
"œ": [
|
151 |
+
45
|
152 |
+
],
|
153 |
+
"ǀ": [
|
154 |
+
46
|
155 |
+
],
|
156 |
+
"ǁ": [
|
157 |
+
47
|
158 |
+
],
|
159 |
+
"ǂ": [
|
160 |
+
48
|
161 |
+
],
|
162 |
+
"ǃ": [
|
163 |
+
49
|
164 |
+
],
|
165 |
+
"ɐ": [
|
166 |
+
50
|
167 |
+
],
|
168 |
+
"ɑ": [
|
169 |
+
51
|
170 |
+
],
|
171 |
+
"ɒ": [
|
172 |
+
52
|
173 |
+
],
|
174 |
+
"ɓ": [
|
175 |
+
53
|
176 |
+
],
|
177 |
+
"ɔ": [
|
178 |
+
54
|
179 |
+
],
|
180 |
+
"ɕ": [
|
181 |
+
55
|
182 |
+
],
|
183 |
+
"ɖ": [
|
184 |
+
56
|
185 |
+
],
|
186 |
+
"ɗ": [
|
187 |
+
57
|
188 |
+
],
|
189 |
+
"ɘ": [
|
190 |
+
58
|
191 |
+
],
|
192 |
+
"ə": [
|
193 |
+
59
|
194 |
+
],
|
195 |
+
"ɚ": [
|
196 |
+
60
|
197 |
+
],
|
198 |
+
"ɛ": [
|
199 |
+
61
|
200 |
+
],
|
201 |
+
"ɜ": [
|
202 |
+
62
|
203 |
+
],
|
204 |
+
"ɞ": [
|
205 |
+
63
|
206 |
+
],
|
207 |
+
"ɟ": [
|
208 |
+
64
|
209 |
+
],
|
210 |
+
"ɠ": [
|
211 |
+
65
|
212 |
+
],
|
213 |
+
"ɡ": [
|
214 |
+
66
|
215 |
+
],
|
216 |
+
"ɢ": [
|
217 |
+
67
|
218 |
+
],
|
219 |
+
"ɣ": [
|
220 |
+
68
|
221 |
+
],
|
222 |
+
"ɤ": [
|
223 |
+
69
|
224 |
+
],
|
225 |
+
"ɥ": [
|
226 |
+
70
|
227 |
+
],
|
228 |
+
"ɦ": [
|
229 |
+
71
|
230 |
+
],
|
231 |
+
"ɧ": [
|
232 |
+
72
|
233 |
+
],
|
234 |
+
"ɨ": [
|
235 |
+
73
|
236 |
+
],
|
237 |
+
"ɪ": [
|
238 |
+
74
|
239 |
+
],
|
240 |
+
"ɫ": [
|
241 |
+
75
|
242 |
+
],
|
243 |
+
"ɬ": [
|
244 |
+
76
|
245 |
+
],
|
246 |
+
"ɭ": [
|
247 |
+
77
|
248 |
+
],
|
249 |
+
"ɮ": [
|
250 |
+
78
|
251 |
+
],
|
252 |
+
"ɯ": [
|
253 |
+
79
|
254 |
+
],
|
255 |
+
"ɰ": [
|
256 |
+
80
|
257 |
+
],
|
258 |
+
"ɱ": [
|
259 |
+
81
|
260 |
+
],
|
261 |
+
"ɲ": [
|
262 |
+
82
|
263 |
+
],
|
264 |
+
"ɳ": [
|
265 |
+
83
|
266 |
+
],
|
267 |
+
"ɴ": [
|
268 |
+
84
|
269 |
+
],
|
270 |
+
"ɵ": [
|
271 |
+
85
|
272 |
+
],
|
273 |
+
"ɶ": [
|
274 |
+
86
|
275 |
+
],
|
276 |
+
"ɸ": [
|
277 |
+
87
|
278 |
+
],
|
279 |
+
"ɹ": [
|
280 |
+
88
|
281 |
+
],
|
282 |
+
"ɺ": [
|
283 |
+
89
|
284 |
+
],
|
285 |
+
"ɻ": [
|
286 |
+
90
|
287 |
+
],
|
288 |
+
"ɽ": [
|
289 |
+
91
|
290 |
+
],
|
291 |
+
"ɾ": [
|
292 |
+
92
|
293 |
+
],
|
294 |
+
"ʀ": [
|
295 |
+
93
|
296 |
+
],
|
297 |
+
"ʁ": [
|
298 |
+
94
|
299 |
+
],
|
300 |
+
"ʂ": [
|
301 |
+
95
|
302 |
+
],
|
303 |
+
"ʃ": [
|
304 |
+
96
|
305 |
+
],
|
306 |
+
"ʄ": [
|
307 |
+
97
|
308 |
+
],
|
309 |
+
"ʈ": [
|
310 |
+
98
|
311 |
+
],
|
312 |
+
"ʉ": [
|
313 |
+
99
|
314 |
+
],
|
315 |
+
"ʊ": [
|
316 |
+
100
|
317 |
+
],
|
318 |
+
"ʋ": [
|
319 |
+
101
|
320 |
+
],
|
321 |
+
"ʌ": [
|
322 |
+
102
|
323 |
+
],
|
324 |
+
"ʍ": [
|
325 |
+
103
|
326 |
+
],
|
327 |
+
"ʎ": [
|
328 |
+
104
|
329 |
+
],
|
330 |
+
"ʏ": [
|
331 |
+
105
|
332 |
+
],
|
333 |
+
"ʐ": [
|
334 |
+
106
|
335 |
+
],
|
336 |
+
"ʑ": [
|
337 |
+
107
|
338 |
+
],
|
339 |
+
"ʒ": [
|
340 |
+
108
|
341 |
+
],
|
342 |
+
"ʔ": [
|
343 |
+
109
|
344 |
+
],
|
345 |
+
"ʕ": [
|
346 |
+
110
|
347 |
+
],
|
348 |
+
"ʘ": [
|
349 |
+
111
|
350 |
+
],
|
351 |
+
"ʙ": [
|
352 |
+
112
|
353 |
+
],
|
354 |
+
"ʛ": [
|
355 |
+
113
|
356 |
+
],
|
357 |
+
"ʜ": [
|
358 |
+
114
|
359 |
+
],
|
360 |
+
"ʝ": [
|
361 |
+
115
|
362 |
+
],
|
363 |
+
"ʟ": [
|
364 |
+
116
|
365 |
+
],
|
366 |
+
"ʡ": [
|
367 |
+
117
|
368 |
+
],
|
369 |
+
"ʢ": [
|
370 |
+
118
|
371 |
+
],
|
372 |
+
"ʲ": [
|
373 |
+
119
|
374 |
+
],
|
375 |
+
"ˈ": [
|
376 |
+
120
|
377 |
+
],
|
378 |
+
"ˌ": [
|
379 |
+
121
|
380 |
+
],
|
381 |
+
"ː": [
|
382 |
+
122
|
383 |
+
],
|
384 |
+
"ˑ": [
|
385 |
+
123
|
386 |
+
],
|
387 |
+
"˞": [
|
388 |
+
124
|
389 |
+
],
|
390 |
+
"β": [
|
391 |
+
125
|
392 |
+
],
|
393 |
+
"θ": [
|
394 |
+
126
|
395 |
+
],
|
396 |
+
"χ": [
|
397 |
+
127
|
398 |
+
],
|
399 |
+
"ᵻ": [
|
400 |
+
128
|
401 |
+
],
|
402 |
+
"ⱱ": [
|
403 |
+
129
|
404 |
+
]
|
405 |
+
},
|
406 |
+
"num_symbols": 130,
|
407 |
+
"num_speakers": 1,
|
408 |
+
"speaker_id_map": {}
|
409 |
+
}
|
piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for ruslan (medium)
|
2 |
+
|
3 |
+
* Language: ru_RU (Russian, Russia)
|
4 |
+
* Speakers: 1
|
5 |
+
* Quality: medium
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://ruslan-corpus.github.io/
|
11 |
+
* License: https://creativecommons.org/licenses/by-nc-sa/4.0/
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Finetuned from U.S. English lessac voice (medium quality).
|
piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_ru_RU-ruslan-medium.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72a5f88e0b20928064eb45d88e1daa21f8af62d18613580d32cbb4aed48dcf7f
|
3 |
+
size 63201294
|
piper_models/ru-ruslan-medium/ru_ru_RU_ruslan_medium_ru_RU-ruslan-medium.onnx.json
ADDED
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050,
|
4 |
+
"quality": "medium"
|
5 |
+
},
|
6 |
+
"espeak": {
|
7 |
+
"voice": "ru"
|
8 |
+
},
|
9 |
+
"inference": {
|
10 |
+
"noise_scale": 0.667,
|
11 |
+
"length_scale": 1,
|
12 |
+
"noise_w": 0.8
|
13 |
+
},
|
14 |
+
"phoneme_type": "espeak",
|
15 |
+
"phoneme_map": {},
|
16 |
+
"phoneme_id_map": {
|
17 |
+
"_": [
|
18 |
+
0
|
19 |
+
],
|
20 |
+
"^": [
|
21 |
+
1
|
22 |
+
],
|
23 |
+
"$": [
|
24 |
+
2
|
25 |
+
],
|
26 |
+
" ": [
|
27 |
+
3
|
28 |
+
],
|
29 |
+
"!": [
|
30 |
+
4
|
31 |
+
],
|
32 |
+
"'": [
|
33 |
+
5
|
34 |
+
],
|
35 |
+
"(": [
|
36 |
+
6
|
37 |
+
],
|
38 |
+
")": [
|
39 |
+
7
|
40 |
+
],
|
41 |
+
",": [
|
42 |
+
8
|
43 |
+
],
|
44 |
+
"-": [
|
45 |
+
9
|
46 |
+
],
|
47 |
+
".": [
|
48 |
+
10
|
49 |
+
],
|
50 |
+
":": [
|
51 |
+
11
|
52 |
+
],
|
53 |
+
";": [
|
54 |
+
12
|
55 |
+
],
|
56 |
+
"?": [
|
57 |
+
13
|
58 |
+
],
|
59 |
+
"a": [
|
60 |
+
14
|
61 |
+
],
|
62 |
+
"b": [
|
63 |
+
15
|
64 |
+
],
|
65 |
+
"c": [
|
66 |
+
16
|
67 |
+
],
|
68 |
+
"d": [
|
69 |
+
17
|
70 |
+
],
|
71 |
+
"e": [
|
72 |
+
18
|
73 |
+
],
|
74 |
+
"f": [
|
75 |
+
19
|
76 |
+
],
|
77 |
+
"h": [
|
78 |
+
20
|
79 |
+
],
|
80 |
+
"i": [
|
81 |
+
21
|
82 |
+
],
|
83 |
+
"j": [
|
84 |
+
22
|
85 |
+
],
|
86 |
+
"k": [
|
87 |
+
23
|
88 |
+
],
|
89 |
+
"l": [
|
90 |
+
24
|
91 |
+
],
|
92 |
+
"m": [
|
93 |
+
25
|
94 |
+
],
|
95 |
+
"n": [
|
96 |
+
26
|
97 |
+
],
|
98 |
+
"o": [
|
99 |
+
27
|
100 |
+
],
|
101 |
+
"p": [
|
102 |
+
28
|
103 |
+
],
|
104 |
+
"q": [
|
105 |
+
29
|
106 |
+
],
|
107 |
+
"r": [
|
108 |
+
30
|
109 |
+
],
|
110 |
+
"s": [
|
111 |
+
31
|
112 |
+
],
|
113 |
+
"t": [
|
114 |
+
32
|
115 |
+
],
|
116 |
+
"u": [
|
117 |
+
33
|
118 |
+
],
|
119 |
+
"v": [
|
120 |
+
34
|
121 |
+
],
|
122 |
+
"w": [
|
123 |
+
35
|
124 |
+
],
|
125 |
+
"x": [
|
126 |
+
36
|
127 |
+
],
|
128 |
+
"y": [
|
129 |
+
37
|
130 |
+
],
|
131 |
+
"z": [
|
132 |
+
38
|
133 |
+
],
|
134 |
+
"æ": [
|
135 |
+
39
|
136 |
+
],
|
137 |
+
"ç": [
|
138 |
+
40
|
139 |
+
],
|
140 |
+
"ð": [
|
141 |
+
41
|
142 |
+
],
|
143 |
+
"ø": [
|
144 |
+
42
|
145 |
+
],
|
146 |
+
"ħ": [
|
147 |
+
43
|
148 |
+
],
|
149 |
+
"ŋ": [
|
150 |
+
44
|
151 |
+
],
|
152 |
+
"œ": [
|
153 |
+
45
|
154 |
+
],
|
155 |
+
"ǀ": [
|
156 |
+
46
|
157 |
+
],
|
158 |
+
"ǁ": [
|
159 |
+
47
|
160 |
+
],
|
161 |
+
"ǂ": [
|
162 |
+
48
|
163 |
+
],
|
164 |
+
"ǃ": [
|
165 |
+
49
|
166 |
+
],
|
167 |
+
"ɐ": [
|
168 |
+
50
|
169 |
+
],
|
170 |
+
"ɑ": [
|
171 |
+
51
|
172 |
+
],
|
173 |
+
"ɒ": [
|
174 |
+
52
|
175 |
+
],
|
176 |
+
"ɓ": [
|
177 |
+
53
|
178 |
+
],
|
179 |
+
"ɔ": [
|
180 |
+
54
|
181 |
+
],
|
182 |
+
"ɕ": [
|
183 |
+
55
|
184 |
+
],
|
185 |
+
"ɖ": [
|
186 |
+
56
|
187 |
+
],
|
188 |
+
"ɗ": [
|
189 |
+
57
|
190 |
+
],
|
191 |
+
"ɘ": [
|
192 |
+
58
|
193 |
+
],
|
194 |
+
"ə": [
|
195 |
+
59
|
196 |
+
],
|
197 |
+
"ɚ": [
|
198 |
+
60
|
199 |
+
],
|
200 |
+
"ɛ": [
|
201 |
+
61
|
202 |
+
],
|
203 |
+
"ɜ": [
|
204 |
+
62
|
205 |
+
],
|
206 |
+
"ɞ": [
|
207 |
+
63
|
208 |
+
],
|
209 |
+
"ɟ": [
|
210 |
+
64
|
211 |
+
],
|
212 |
+
"ɠ": [
|
213 |
+
65
|
214 |
+
],
|
215 |
+
"ɡ": [
|
216 |
+
66
|
217 |
+
],
|
218 |
+
"ɢ": [
|
219 |
+
67
|
220 |
+
],
|
221 |
+
"ɣ": [
|
222 |
+
68
|
223 |
+
],
|
224 |
+
"ɤ": [
|
225 |
+
69
|
226 |
+
],
|
227 |
+
"ɥ": [
|
228 |
+
70
|
229 |
+
],
|
230 |
+
"ɦ": [
|
231 |
+
71
|
232 |
+
],
|
233 |
+
"ɧ": [
|
234 |
+
72
|
235 |
+
],
|
236 |
+
"ɨ": [
|
237 |
+
73
|
238 |
+
],
|
239 |
+
"ɪ": [
|
240 |
+
74
|
241 |
+
],
|
242 |
+
"ɫ": [
|
243 |
+
75
|
244 |
+
],
|
245 |
+
"ɬ": [
|
246 |
+
76
|
247 |
+
],
|
248 |
+
"ɭ": [
|
249 |
+
77
|
250 |
+
],
|
251 |
+
"ɮ": [
|
252 |
+
78
|
253 |
+
],
|
254 |
+
"ɯ": [
|
255 |
+
79
|
256 |
+
],
|
257 |
+
"ɰ": [
|
258 |
+
80
|
259 |
+
],
|
260 |
+
"ɱ": [
|
261 |
+
81
|
262 |
+
],
|
263 |
+
"ɲ": [
|
264 |
+
82
|
265 |
+
],
|
266 |
+
"ɳ": [
|
267 |
+
83
|
268 |
+
],
|
269 |
+
"ɴ": [
|
270 |
+
84
|
271 |
+
],
|
272 |
+
"ɵ": [
|
273 |
+
85
|
274 |
+
],
|
275 |
+
"ɶ": [
|
276 |
+
86
|
277 |
+
],
|
278 |
+
"ɸ": [
|
279 |
+
87
|
280 |
+
],
|
281 |
+
"ɹ": [
|
282 |
+
88
|
283 |
+
],
|
284 |
+
"ɺ": [
|
285 |
+
89
|
286 |
+
],
|
287 |
+
"ɻ": [
|
288 |
+
90
|
289 |
+
],
|
290 |
+
"ɽ": [
|
291 |
+
91
|
292 |
+
],
|
293 |
+
"ɾ": [
|
294 |
+
92
|
295 |
+
],
|
296 |
+
"ʀ": [
|
297 |
+
93
|
298 |
+
],
|
299 |
+
"ʁ": [
|
300 |
+
94
|
301 |
+
],
|
302 |
+
"ʂ": [
|
303 |
+
95
|
304 |
+
],
|
305 |
+
"ʃ": [
|
306 |
+
96
|
307 |
+
],
|
308 |
+
"ʄ": [
|
309 |
+
97
|
310 |
+
],
|
311 |
+
"ʈ": [
|
312 |
+
98
|
313 |
+
],
|
314 |
+
"ʉ": [
|
315 |
+
99
|
316 |
+
],
|
317 |
+
"ʊ": [
|
318 |
+
100
|
319 |
+
],
|
320 |
+
"ʋ": [
|
321 |
+
101
|
322 |
+
],
|
323 |
+
"ʌ": [
|
324 |
+
102
|
325 |
+
],
|
326 |
+
"ʍ": [
|
327 |
+
103
|
328 |
+
],
|
329 |
+
"ʎ": [
|
330 |
+
104
|
331 |
+
],
|
332 |
+
"ʏ": [
|
333 |
+
105
|
334 |
+
],
|
335 |
+
"ʐ": [
|
336 |
+
106
|
337 |
+
],
|
338 |
+
"ʑ": [
|
339 |
+
107
|
340 |
+
],
|
341 |
+
"ʒ": [
|
342 |
+
108
|
343 |
+
],
|
344 |
+
"ʔ": [
|
345 |
+
109
|
346 |
+
],
|
347 |
+
"ʕ": [
|
348 |
+
110
|
349 |
+
],
|
350 |
+
"ʘ": [
|
351 |
+
111
|
352 |
+
],
|
353 |
+
"ʙ": [
|
354 |
+
112
|
355 |
+
],
|
356 |
+
"ʛ": [
|
357 |
+
113
|
358 |
+
],
|
359 |
+
"ʜ": [
|
360 |
+
114
|
361 |
+
],
|
362 |
+
"ʝ": [
|
363 |
+
115
|
364 |
+
],
|
365 |
+
"ʟ": [
|
366 |
+
116
|
367 |
+
],
|
368 |
+
"ʡ": [
|
369 |
+
117
|
370 |
+
],
|
371 |
+
"ʢ": [
|
372 |
+
118
|
373 |
+
],
|
374 |
+
"ʲ": [
|
375 |
+
119
|
376 |
+
],
|
377 |
+
"ˈ": [
|
378 |
+
120
|
379 |
+
],
|
380 |
+
"ˌ": [
|
381 |
+
121
|
382 |
+
],
|
383 |
+
"ː": [
|
384 |
+
122
|
385 |
+
],
|
386 |
+
"ˑ": [
|
387 |
+
123
|
388 |
+
],
|
389 |
+
"˞": [
|
390 |
+
124
|
391 |
+
],
|
392 |
+
"β": [
|
393 |
+
125
|
394 |
+
],
|
395 |
+
"θ": [
|
396 |
+
126
|
397 |
+
],
|
398 |
+
"χ": [
|
399 |
+
127
|
400 |
+
],
|
401 |
+
"ᵻ": [
|
402 |
+
128
|
403 |
+
],
|
404 |
+
"ⱱ": [
|
405 |
+
129
|
406 |
+
],
|
407 |
+
"0": [
|
408 |
+
130
|
409 |
+
],
|
410 |
+
"1": [
|
411 |
+
131
|
412 |
+
],
|
413 |
+
"2": [
|
414 |
+
132
|
415 |
+
],
|
416 |
+
"3": [
|
417 |
+
133
|
418 |
+
],
|
419 |
+
"4": [
|
420 |
+
134
|
421 |
+
],
|
422 |
+
"5": [
|
423 |
+
135
|
424 |
+
],
|
425 |
+
"6": [
|
426 |
+
136
|
427 |
+
],
|
428 |
+
"7": [
|
429 |
+
137
|
430 |
+
],
|
431 |
+
"8": [
|
432 |
+
138
|
433 |
+
],
|
434 |
+
"9": [
|
435 |
+
139
|
436 |
+
],
|
437 |
+
"̧": [
|
438 |
+
140
|
439 |
+
],
|
440 |
+
"̃": [
|
441 |
+
141
|
442 |
+
],
|
443 |
+
"̪": [
|
444 |
+
142
|
445 |
+
],
|
446 |
+
"̯": [
|
447 |
+
143
|
448 |
+
],
|
449 |
+
"̩": [
|
450 |
+
144
|
451 |
+
],
|
452 |
+
"ʰ": [
|
453 |
+
145
|
454 |
+
],
|
455 |
+
"ˤ": [
|
456 |
+
146
|
457 |
+
],
|
458 |
+
"ε": [
|
459 |
+
147
|
460 |
+
],
|
461 |
+
"↓": [
|
462 |
+
148
|
463 |
+
],
|
464 |
+
"#": [
|
465 |
+
149
|
466 |
+
],
|
467 |
+
"\"": [
|
468 |
+
150
|
469 |
+
],
|
470 |
+
"↑": [
|
471 |
+
151
|
472 |
+
],
|
473 |
+
"̺": [
|
474 |
+
152
|
475 |
+
],
|
476 |
+
"̻": [
|
477 |
+
153
|
478 |
+
]
|
479 |
+
},
|
480 |
+
"num_symbols": 256,
|
481 |
+
"num_speakers": 1,
|
482 |
+
"speaker_id_map": {},
|
483 |
+
"piper_version": "1.0.0",
|
484 |
+
"language": {
|
485 |
+
"code": "ru_RU",
|
486 |
+
"family": "ru",
|
487 |
+
"region": "RU",
|
488 |
+
"name_native": "Русский",
|
489 |
+
"name_english": "Russian",
|
490 |
+
"country_english": "Russia"
|
491 |
+
},
|
492 |
+
"dataset": "ruslan"
|
493 |
+
}
|
piper_models/voice-kk-issai-high/MODEL_CARD
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Model card for ISSAI (high)
|
2 |
+
|
3 |
+
* Language: kk (Kazakh)
|
4 |
+
* Speakers: 6
|
5 |
+
* Quality: x-low
|
6 |
+
* Samplerate: 22,050Hz
|
7 |
+
|
8 |
+
## Dataset
|
9 |
+
|
10 |
+
* URL: https://github.com/IS2AI/Kazakh_TTS
|
11 |
+
* License: CC-BY-4.0
|
12 |
+
|
13 |
+
## Training
|
14 |
+
|
15 |
+
Trained from scratch.
|
piper_models/voice-kk-issai-high/kk-issai-high.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dee767c893e8535da821447d12cb030e3569e11254c14030a1da5d8b2222c16
|
3 |
+
size 127864258
|
piper_models/voice-kk-issai-high/kk-issai-high.onnx.json
ADDED
@@ -0,0 +1,416 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"audio": {
|
3 |
+
"sample_rate": 22050
|
4 |
+
},
|
5 |
+
"espeak": {
|
6 |
+
"voice": "kk"
|
7 |
+
},
|
8 |
+
"inference": {
|
9 |
+
"noise_scale": 0.667,
|
10 |
+
"length_scale": 1,
|
11 |
+
"noise_w": 0.8
|
12 |
+
},
|
13 |
+
"phoneme_map": {},
|
14 |
+
"phoneme_id_map": {
|
15 |
+
"_": [
|
16 |
+
0
|
17 |
+
],
|
18 |
+
"^": [
|
19 |
+
1
|
20 |
+
],
|
21 |
+
"$": [
|
22 |
+
2
|
23 |
+
],
|
24 |
+
" ": [
|
25 |
+
3
|
26 |
+
],
|
27 |
+
"!": [
|
28 |
+
4
|
29 |
+
],
|
30 |
+
"'": [
|
31 |
+
5
|
32 |
+
],
|
33 |
+
"(": [
|
34 |
+
6
|
35 |
+
],
|
36 |
+
")": [
|
37 |
+
7
|
38 |
+
],
|
39 |
+
",": [
|
40 |
+
8
|
41 |
+
],
|
42 |
+
"-": [
|
43 |
+
9
|
44 |
+
],
|
45 |
+
".": [
|
46 |
+
10
|
47 |
+
],
|
48 |
+
":": [
|
49 |
+
11
|
50 |
+
],
|
51 |
+
";": [
|
52 |
+
12
|
53 |
+
],
|
54 |
+
"?": [
|
55 |
+
13
|
56 |
+
],
|
57 |
+
"a": [
|
58 |
+
14
|
59 |
+
],
|
60 |
+
"b": [
|
61 |
+
15
|
62 |
+
],
|
63 |
+
"c": [
|
64 |
+
16
|
65 |
+
],
|
66 |
+
"d": [
|
67 |
+
17
|
68 |
+
],
|
69 |
+
"e": [
|
70 |
+
18
|
71 |
+
],
|
72 |
+
"f": [
|
73 |
+
19
|
74 |
+
],
|
75 |
+
"h": [
|
76 |
+
20
|
77 |
+
],
|
78 |
+
"i": [
|
79 |
+
21
|
80 |
+
],
|
81 |
+
"j": [
|
82 |
+
22
|
83 |
+
],
|
84 |
+
"k": [
|
85 |
+
23
|
86 |
+
],
|
87 |
+
"l": [
|
88 |
+
24
|
89 |
+
],
|
90 |
+
"m": [
|
91 |
+
25
|
92 |
+
],
|
93 |
+
"n": [
|
94 |
+
26
|
95 |
+
],
|
96 |
+
"o": [
|
97 |
+
27
|
98 |
+
],
|
99 |
+
"p": [
|
100 |
+
28
|
101 |
+
],
|
102 |
+
"q": [
|
103 |
+
29
|
104 |
+
],
|
105 |
+
"r": [
|
106 |
+
30
|
107 |
+
],
|
108 |
+
"s": [
|
109 |
+
31
|
110 |
+
],
|
111 |
+
"t": [
|
112 |
+
32
|
113 |
+
],
|
114 |
+
"u": [
|
115 |
+
33
|
116 |
+
],
|
117 |
+
"v": [
|
118 |
+
34
|
119 |
+
],
|
120 |
+
"w": [
|
121 |
+
35
|
122 |
+
],
|
123 |
+
"x": [
|
124 |
+
36
|
125 |
+
],
|
126 |
+
"y": [
|
127 |
+
37
|
128 |
+
],
|
129 |
+
"z": [
|
130 |
+
38
|
131 |
+
],
|
132 |
+
"æ": [
|
133 |
+
39
|
134 |
+
],
|
135 |
+
"ç": [
|
136 |
+
40
|
137 |
+
],
|
138 |
+
"ð": [
|
139 |
+
41
|
140 |
+
],
|
141 |
+
"ø": [
|
142 |
+
42
|
143 |
+
],
|
144 |
+
"ħ": [
|
145 |
+
43
|
146 |
+
],
|
147 |
+
"ŋ": [
|
148 |
+
44
|
149 |
+
],
|
150 |
+
"œ": [
|
151 |
+
45
|
152 |
+
],
|
153 |
+
"ǀ": [
|
154 |
+
46
|
155 |
+
],
|
156 |
+
"ǁ": [
|
157 |
+
47
|
158 |
+
],
|
159 |
+
"ǂ": [
|
160 |
+
48
|
161 |
+
],
|
162 |
+
"ǃ": [
|
163 |
+
49
|
164 |
+
],
|
165 |
+
"ɐ": [
|
166 |
+
50
|
167 |
+
],
|
168 |
+
"ɑ": [
|
169 |
+
51
|
170 |
+
],
|
171 |
+
"ɒ": [
|
172 |
+
52
|
173 |
+
],
|
174 |
+
"ɓ": [
|
175 |
+
53
|
176 |
+
],
|
177 |
+
"ɔ": [
|
178 |
+
54
|
179 |
+
],
|
180 |
+
"ɕ": [
|
181 |
+
55
|
182 |
+
],
|
183 |
+
"ɖ": [
|
184 |
+
56
|
185 |
+
],
|
186 |
+
"ɗ": [
|
187 |
+
57
|
188 |
+
],
|
189 |
+
"ɘ": [
|
190 |
+
58
|
191 |
+
],
|
192 |
+
"ə": [
|
193 |
+
59
|
194 |
+
],
|
195 |
+
"ɚ": [
|
196 |
+
60
|
197 |
+
],
|
198 |
+
"ɛ": [
|
199 |
+
61
|
200 |
+
],
|
201 |
+
"ɜ": [
|
202 |
+
62
|
203 |
+
],
|
204 |
+
"ɞ": [
|
205 |
+
63
|
206 |
+
],
|
207 |
+
"ɟ": [
|
208 |
+
64
|
209 |
+
],
|
210 |
+
"ɠ": [
|
211 |
+
65
|
212 |
+
],
|
213 |
+
"ɡ": [
|
214 |
+
66
|
215 |
+
],
|
216 |
+
"ɢ": [
|
217 |
+
67
|
218 |
+
],
|
219 |
+
"ɣ": [
|
220 |
+
68
|
221 |
+
],
|
222 |
+
"ɤ": [
|
223 |
+
69
|
224 |
+
],
|
225 |
+
"ɥ": [
|
226 |
+
70
|
227 |
+
],
|
228 |
+
"ɦ": [
|
229 |
+
71
|
230 |
+
],
|
231 |
+
"ɧ": [
|
232 |
+
72
|
233 |
+
],
|
234 |
+
"ɨ": [
|
235 |
+
73
|
236 |
+
],
|
237 |
+
"ɪ": [
|
238 |
+
74
|
239 |
+
],
|
240 |
+
"ɫ": [
|
241 |
+
75
|
242 |
+
],
|
243 |
+
"ɬ": [
|
244 |
+
76
|
245 |
+
],
|
246 |
+
"ɭ": [
|
247 |
+
77
|
248 |
+
],
|
249 |
+
"ɮ": [
|
250 |
+
78
|
251 |
+
],
|
252 |
+
"ɯ": [
|
253 |
+
79
|
254 |
+
],
|
255 |
+
"ɰ": [
|
256 |
+
80
|
257 |
+
],
|
258 |
+
"ɱ": [
|
259 |
+
81
|
260 |
+
],
|
261 |
+
"ɲ": [
|
262 |
+
82
|
263 |
+
],
|
264 |
+
"ɳ": [
|
265 |
+
83
|
266 |
+
],
|
267 |
+
"ɴ": [
|
268 |
+
84
|
269 |
+
],
|
270 |
+
"ɵ": [
|
271 |
+
85
|
272 |
+
],
|
273 |
+
"ɶ": [
|
274 |
+
86
|
275 |
+
],
|
276 |
+
"ɸ": [
|
277 |
+
87
|
278 |
+
],
|
279 |
+
"ɹ": [
|
280 |
+
88
|
281 |
+
],
|
282 |
+
"ɺ": [
|
283 |
+
89
|
284 |
+
],
|
285 |
+
"ɻ": [
|
286 |
+
90
|
287 |
+
],
|
288 |
+
"ɽ": [
|
289 |
+
91
|
290 |
+
],
|
291 |
+
"ɾ": [
|
292 |
+
92
|
293 |
+
],
|
294 |
+
"ʀ": [
|
295 |
+
93
|
296 |
+
],
|
297 |
+
"ʁ": [
|
298 |
+
94
|
299 |
+
],
|
300 |
+
"ʂ": [
|
301 |
+
95
|
302 |
+
],
|
303 |
+
"ʃ": [
|
304 |
+
96
|
305 |
+
],
|
306 |
+
"ʄ": [
|
307 |
+
97
|
308 |
+
],
|
309 |
+
"ʈ": [
|
310 |
+
98
|
311 |
+
],
|
312 |
+
"ʉ": [
|
313 |
+
99
|
314 |
+
],
|
315 |
+
"ʊ": [
|
316 |
+
100
|
317 |
+
],
|
318 |
+
"ʋ": [
|
319 |
+
101
|
320 |
+
],
|
321 |
+
"ʌ": [
|
322 |
+
102
|
323 |
+
],
|
324 |
+
"ʍ": [
|
325 |
+
103
|
326 |
+
],
|
327 |
+
"ʎ": [
|
328 |
+
104
|
329 |
+
],
|
330 |
+
"ʏ": [
|
331 |
+
105
|
332 |
+
],
|
333 |
+
"ʐ": [
|
334 |
+
106
|
335 |
+
],
|
336 |
+
"ʑ": [
|
337 |
+
107
|
338 |
+
],
|
339 |
+
"ʒ": [
|
340 |
+
108
|
341 |
+
],
|
342 |
+
"ʔ": [
|
343 |
+
109
|
344 |
+
],
|
345 |
+
"ʕ": [
|
346 |
+
110
|
347 |
+
],
|
348 |
+
"ʘ": [
|
349 |
+
111
|
350 |
+
],
|
351 |
+
"ʙ": [
|
352 |
+
112
|
353 |
+
],
|
354 |
+
"ʛ": [
|
355 |
+
113
|
356 |
+
],
|
357 |
+
"ʜ": [
|
358 |
+
114
|
359 |
+
],
|
360 |
+
"ʝ": [
|
361 |
+
115
|
362 |
+
],
|
363 |
+
"ʟ": [
|
364 |
+
116
|
365 |
+
],
|
366 |
+
"ʡ": [
|
367 |
+
117
|
368 |
+
],
|
369 |
+
"ʢ": [
|
370 |
+
118
|
371 |
+
],
|
372 |
+
"ʲ": [
|
373 |
+
119
|
374 |
+
],
|
375 |
+
"ˈ": [
|
376 |
+
120
|
377 |
+
],
|
378 |
+
"ˌ": [
|
379 |
+
121
|
380 |
+
],
|
381 |
+
"ː": [
|
382 |
+
122
|
383 |
+
],
|
384 |
+
"ˑ": [
|
385 |
+
123
|
386 |
+
],
|
387 |
+
"˞": [
|
388 |
+
124
|
389 |
+
],
|
390 |
+
"β": [
|
391 |
+
125
|
392 |
+
],
|
393 |
+
"θ": [
|
394 |
+
126
|
395 |
+
],
|
396 |
+
"χ": [
|
397 |
+
127
|
398 |
+
],
|
399 |
+
"ᵻ": [
|
400 |
+
128
|
401 |
+
],
|
402 |
+
"ⱱ": [
|
403 |
+
129
|
404 |
+
]
|
405 |
+
},
|
406 |
+
"num_symbols": 130,
|
407 |
+
"num_speakers": 6,
|
408 |
+
"speaker_id_map": {
|
409 |
+
"ISSAI_KazakhTTS2_M2": 0,
|
410 |
+
"ISSAI_KazakhTTS_M1_Iseke": 1,
|
411 |
+
"ISSAI_KazakhTTS2_F3": 2,
|
412 |
+
"ISSAI_KazakhTTS_F1_Raya": 3,
|
413 |
+
"ISSAI_KazakhTTS2_F1": 4,
|
414 |
+
"ISSAI_KazakhTTS2_F2": 5
|
415 |
+
}
|
416 |
+
}
|
vosk_models/vosk-model-en-us-0.22-lgraph/README
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Accurate universal English model (both for callcenter and wideband)
|
2 |
+
|
3 |
+
Based on Appen Kaldi model https://github.com/Appen/UHV-OTS-Speech
|
4 |
+
|
5 |
+
Dynamic graph version
|
vosk_models/vosk-model-en-us-0.22-lgraph/am/final.mdl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8586dfa7f571b8b01bac8217ef96493690c65aa512b72e6ce5acde39c262afe
|
3 |
+
size 73728293
|
vosk_models/vosk-model-en-us-0.22-lgraph/am/tree
ADDED
Binary file (881 kB). View file
|
|
vosk_models/vosk-model-en-us-0.22-lgraph/conf/mfcc.conf
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
--sample-frequency=16000
|
2 |
+
--use-energy=false
|
3 |
+
--num-mel-bins=40
|
4 |
+
--num-ceps=40
|
5 |
+
--low-freq=20
|
6 |
+
--high-freq=7600
|
7 |
+
--allow-upsample=true
|
8 |
+
--allow-downsample=true
|
9 |
+
|
vosk_models/vosk-model-en-us-0.22-lgraph/conf/model.conf
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
--min-active=200
|
2 |
+
--max-active=7000
|
3 |
+
--beam=13.0
|
4 |
+
--lattice-beam=6.0
|
5 |
+
--acoustic-scale=1.0
|
6 |
+
--frame-subsampling-factor=3
|
7 |
+
--endpoint.silence-phones=1:2:3:4:5:11:12:13:14:15
|
8 |
+
--endpoint.rule2.min-trailing-silence=0.5
|
9 |
+
--endpoint.rule3.min-trailing-silence=1.0
|
10 |
+
--endpoint.rule4.min-trailing-silence=2.0
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/Gr.fst
ADDED
Git LFS Details
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/HCLr.fst
ADDED
Git LFS Details
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/disambig_tid.int
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
23613
|
2 |
+
23614
|
3 |
+
23615
|
4 |
+
23616
|
5 |
+
23617
|
6 |
+
23618
|
7 |
+
23619
|
8 |
+
23620
|
9 |
+
23621
|
10 |
+
23622
|
11 |
+
23623
|
12 |
+
23624
|
13 |
+
23625
|
14 |
+
23626
|
15 |
+
23627
|
16 |
+
23628
|
17 |
+
23629
|
18 |
+
23630
|
19 |
+
23631
|
20 |
+
23632
|
21 |
+
23633
|
22 |
+
23634
|
23 |
+
23635
|
24 |
+
23636
|
25 |
+
23637
|
26 |
+
23638
|
27 |
+
23639
|
28 |
+
23640
|
29 |
+
23641
|
30 |
+
23642
|
31 |
+
23643
|
32 |
+
23644
|
33 |
+
23645
|
34 |
+
23646
|
35 |
+
23647
|
36 |
+
23648
|
37 |
+
23649
|
38 |
+
23650
|
39 |
+
23651
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/phones.txt
ADDED
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<eps> 0
|
2 |
+
SIL 1
|
3 |
+
SIL_B 2
|
4 |
+
SIL_E 3
|
5 |
+
SIL_I 4
|
6 |
+
SIL_S 5
|
7 |
+
LAUGHTER 6
|
8 |
+
LAUGHTER_B 7
|
9 |
+
LAUGHTER_E 8
|
10 |
+
LAUGHTER_I 9
|
11 |
+
LAUGHTER_S 10
|
12 |
+
NOISE 11
|
13 |
+
NOISE_B 12
|
14 |
+
NOISE_E 13
|
15 |
+
NOISE_I 14
|
16 |
+
NOISE_S 15
|
17 |
+
OOV 16
|
18 |
+
OOV_B 17
|
19 |
+
OOV_E 18
|
20 |
+
OOV_I 19
|
21 |
+
OOV_S 20
|
22 |
+
SPN 21
|
23 |
+
SPN_B 22
|
24 |
+
SPN_E 23
|
25 |
+
SPN_I 24
|
26 |
+
SPN_S 25
|
27 |
+
BRH 26
|
28 |
+
BRH_B 27
|
29 |
+
BRH_E 28
|
30 |
+
BRH_I 29
|
31 |
+
BRH_S 30
|
32 |
+
CGH 31
|
33 |
+
CGH_B 32
|
34 |
+
CGH_E 33
|
35 |
+
CGH_I 34
|
36 |
+
CGH_S 35
|
37 |
+
NSN 36
|
38 |
+
NSN_B 37
|
39 |
+
NSN_E 38
|
40 |
+
NSN_I 39
|
41 |
+
NSN_S 40
|
42 |
+
SMK 41
|
43 |
+
SMK_B 42
|
44 |
+
SMK_E 43
|
45 |
+
SMK_I 44
|
46 |
+
SMK_S 45
|
47 |
+
UHH 46
|
48 |
+
UHH_B 47
|
49 |
+
UHH_E 48
|
50 |
+
UHH_I 49
|
51 |
+
UHH_S 50
|
52 |
+
UM 51
|
53 |
+
UM_B 52
|
54 |
+
UM_E 53
|
55 |
+
UM_I 54
|
56 |
+
UM_S 55
|
57 |
+
3`_B 56
|
58 |
+
3`_E 57
|
59 |
+
3`_I 58
|
60 |
+
3`_S 59
|
61 |
+
4_B 60
|
62 |
+
4_E 61
|
63 |
+
4_I 62
|
64 |
+
4_S 63
|
65 |
+
@_B 64
|
66 |
+
@_E 65
|
67 |
+
@_I 66
|
68 |
+
@_S 67
|
69 |
+
@`_B 68
|
70 |
+
@`_E 69
|
71 |
+
@`_I 70
|
72 |
+
@`_S 71
|
73 |
+
A_B 72
|
74 |
+
A_E 73
|
75 |
+
A_I 74
|
76 |
+
A_S 75
|
77 |
+
D_B 76
|
78 |
+
D_E 77
|
79 |
+
D_I 78
|
80 |
+
D_S 79
|
81 |
+
E_B 80
|
82 |
+
E_E 81
|
83 |
+
E_I 82
|
84 |
+
E_S 83
|
85 |
+
E:_B 84
|
86 |
+
E:_E 85
|
87 |
+
E:_I 86
|
88 |
+
E:_S 87
|
89 |
+
I_B 88
|
90 |
+
I_E 89
|
91 |
+
I_I 90
|
92 |
+
I_S 91
|
93 |
+
N_B 92
|
94 |
+
N_E 93
|
95 |
+
N_I 94
|
96 |
+
N_S 95
|
97 |
+
O_B 96
|
98 |
+
O_E 97
|
99 |
+
O_I 98
|
100 |
+
O_S 99
|
101 |
+
OI_B 100
|
102 |
+
OI_E 101
|
103 |
+
OI_I 102
|
104 |
+
OI_S 103
|
105 |
+
S_B 104
|
106 |
+
S_E 105
|
107 |
+
S_I 106
|
108 |
+
S_S 107
|
109 |
+
T_B 108
|
110 |
+
T_E 109
|
111 |
+
T_I 110
|
112 |
+
T_S 111
|
113 |
+
U_B 112
|
114 |
+
U_E 113
|
115 |
+
U_I 114
|
116 |
+
U_S 115
|
117 |
+
V_B 116
|
118 |
+
V_E 117
|
119 |
+
V_I 118
|
120 |
+
V_S 119
|
121 |
+
Z_B 120
|
122 |
+
Z_E 121
|
123 |
+
Z_I 122
|
124 |
+
Z_S 123
|
125 |
+
aI_B 124
|
126 |
+
aI_E 125
|
127 |
+
aI_I 126
|
128 |
+
aI_S 127
|
129 |
+
aU_B 128
|
130 |
+
aU_E 129
|
131 |
+
aU_I 130
|
132 |
+
aU_S 131
|
133 |
+
b_B 132
|
134 |
+
b_E 133
|
135 |
+
b_I 134
|
136 |
+
b_S 135
|
137 |
+
d_B 136
|
138 |
+
d_E 137
|
139 |
+
d_I 138
|
140 |
+
d_S 139
|
141 |
+
dZ_B 140
|
142 |
+
dZ_E 141
|
143 |
+
dZ_I 142
|
144 |
+
dZ_S 143
|
145 |
+
eI_B 144
|
146 |
+
eI_E 145
|
147 |
+
eI_I 146
|
148 |
+
eI_S 147
|
149 |
+
f_B 148
|
150 |
+
f_E 149
|
151 |
+
f_I 150
|
152 |
+
f_S 151
|
153 |
+
g_B 152
|
154 |
+
g_E 153
|
155 |
+
g_I 154
|
156 |
+
g_S 155
|
157 |
+
h_B 156
|
158 |
+
h_E 157
|
159 |
+
h_I 158
|
160 |
+
h_S 159
|
161 |
+
i_B 160
|
162 |
+
i_E 161
|
163 |
+
i_I 162
|
164 |
+
i_S 163
|
165 |
+
j_B 164
|
166 |
+
j_E 165
|
167 |
+
j_I 166
|
168 |
+
j_S 167
|
169 |
+
k_B 168
|
170 |
+
k_E 169
|
171 |
+
k_I 170
|
172 |
+
k_S 171
|
173 |
+
l_B 172
|
174 |
+
l_E 173
|
175 |
+
l_I 174
|
176 |
+
l_S 175
|
177 |
+
m_B 176
|
178 |
+
m_E 177
|
179 |
+
m_I 178
|
180 |
+
m_S 179
|
181 |
+
n_B 180
|
182 |
+
n_E 181
|
183 |
+
n_I 182
|
184 |
+
n_S 183
|
185 |
+
oU_B 184
|
186 |
+
oU_E 185
|
187 |
+
oU_I 186
|
188 |
+
oU_S 187
|
189 |
+
p_B 188
|
190 |
+
p_E 189
|
191 |
+
p_I 190
|
192 |
+
p_S 191
|
193 |
+
r_B 192
|
194 |
+
r_E 193
|
195 |
+
r_I 194
|
196 |
+
r_S 195
|
197 |
+
s_B 196
|
198 |
+
s_E 197
|
199 |
+
s_I 198
|
200 |
+
s_S 199
|
201 |
+
t_B 200
|
202 |
+
t_E 201
|
203 |
+
t_I 202
|
204 |
+
t_S 203
|
205 |
+
tS_B 204
|
206 |
+
tS_E 205
|
207 |
+
tS_I 206
|
208 |
+
tS_S 207
|
209 |
+
u_B 208
|
210 |
+
u_E 209
|
211 |
+
u_I 210
|
212 |
+
u_S 211
|
213 |
+
v_B 212
|
214 |
+
v_E 213
|
215 |
+
v_I 214
|
216 |
+
v_S 215
|
217 |
+
w_B 216
|
218 |
+
w_E 217
|
219 |
+
w_I 218
|
220 |
+
w_S 219
|
221 |
+
z_B 220
|
222 |
+
z_E 221
|
223 |
+
z_I 222
|
224 |
+
z_S 223
|
225 |
+
{_B 224
|
226 |
+
{_E 225
|
227 |
+
{_I 226
|
228 |
+
{_S 227
|
229 |
+
#0 228
|
230 |
+
#1 229
|
231 |
+
#2 230
|
232 |
+
#3 231
|
233 |
+
#4 232
|
234 |
+
#5 233
|
235 |
+
#6 234
|
236 |
+
#7 235
|
237 |
+
#8 236
|
238 |
+
#9 237
|
239 |
+
#10 238
|
240 |
+
#11 239
|
241 |
+
#12 240
|
242 |
+
#13 241
|
243 |
+
#14 242
|
244 |
+
#15 243
|
245 |
+
#16 244
|
246 |
+
#17 245
|
247 |
+
#18 246
|
248 |
+
#19 247
|
249 |
+
#20 248
|
250 |
+
#21 249
|
251 |
+
#22 250
|
252 |
+
#23 251
|
253 |
+
#24 252
|
254 |
+
#25 253
|
255 |
+
#26 254
|
256 |
+
#27 255
|
257 |
+
#28 256
|
258 |
+
#29 257
|
259 |
+
#30 258
|
260 |
+
#31 259
|
261 |
+
#32 260
|
262 |
+
#33 261
|
263 |
+
#34 262
|
264 |
+
#35 263
|
265 |
+
#36 264
|
266 |
+
#37 265
|
267 |
+
#38 266
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/phones/word_boundary.int
ADDED
@@ -0,0 +1,227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
1 nonword
|
2 |
+
2 begin
|
3 |
+
3 end
|
4 |
+
4 internal
|
5 |
+
5 singleton
|
6 |
+
6 nonword
|
7 |
+
7 begin
|
8 |
+
8 end
|
9 |
+
9 internal
|
10 |
+
10 singleton
|
11 |
+
11 nonword
|
12 |
+
12 begin
|
13 |
+
13 end
|
14 |
+
14 internal
|
15 |
+
15 singleton
|
16 |
+
16 nonword
|
17 |
+
17 begin
|
18 |
+
18 end
|
19 |
+
19 internal
|
20 |
+
20 singleton
|
21 |
+
21 nonword
|
22 |
+
22 begin
|
23 |
+
23 end
|
24 |
+
24 internal
|
25 |
+
25 singleton
|
26 |
+
26 nonword
|
27 |
+
27 begin
|
28 |
+
28 end
|
29 |
+
29 internal
|
30 |
+
30 singleton
|
31 |
+
31 nonword
|
32 |
+
32 begin
|
33 |
+
33 end
|
34 |
+
34 internal
|
35 |
+
35 singleton
|
36 |
+
36 nonword
|
37 |
+
37 begin
|
38 |
+
38 end
|
39 |
+
39 internal
|
40 |
+
40 singleton
|
41 |
+
41 nonword
|
42 |
+
42 begin
|
43 |
+
43 end
|
44 |
+
44 internal
|
45 |
+
45 singleton
|
46 |
+
46 nonword
|
47 |
+
47 begin
|
48 |
+
48 end
|
49 |
+
49 internal
|
50 |
+
50 singleton
|
51 |
+
51 nonword
|
52 |
+
52 begin
|
53 |
+
53 end
|
54 |
+
54 internal
|
55 |
+
55 singleton
|
56 |
+
56 begin
|
57 |
+
57 end
|
58 |
+
58 internal
|
59 |
+
59 singleton
|
60 |
+
60 begin
|
61 |
+
61 end
|
62 |
+
62 internal
|
63 |
+
63 singleton
|
64 |
+
64 begin
|
65 |
+
65 end
|
66 |
+
66 internal
|
67 |
+
67 singleton
|
68 |
+
68 begin
|
69 |
+
69 end
|
70 |
+
70 internal
|
71 |
+
71 singleton
|
72 |
+
72 begin
|
73 |
+
73 end
|
74 |
+
74 internal
|
75 |
+
75 singleton
|
76 |
+
76 begin
|
77 |
+
77 end
|
78 |
+
78 internal
|
79 |
+
79 singleton
|
80 |
+
80 begin
|
81 |
+
81 end
|
82 |
+
82 internal
|
83 |
+
83 singleton
|
84 |
+
84 begin
|
85 |
+
85 end
|
86 |
+
86 internal
|
87 |
+
87 singleton
|
88 |
+
88 begin
|
89 |
+
89 end
|
90 |
+
90 internal
|
91 |
+
91 singleton
|
92 |
+
92 begin
|
93 |
+
93 end
|
94 |
+
94 internal
|
95 |
+
95 singleton
|
96 |
+
96 begin
|
97 |
+
97 end
|
98 |
+
98 internal
|
99 |
+
99 singleton
|
100 |
+
100 begin
|
101 |
+
101 end
|
102 |
+
102 internal
|
103 |
+
103 singleton
|
104 |
+
104 begin
|
105 |
+
105 end
|
106 |
+
106 internal
|
107 |
+
107 singleton
|
108 |
+
108 begin
|
109 |
+
109 end
|
110 |
+
110 internal
|
111 |
+
111 singleton
|
112 |
+
112 begin
|
113 |
+
113 end
|
114 |
+
114 internal
|
115 |
+
115 singleton
|
116 |
+
116 begin
|
117 |
+
117 end
|
118 |
+
118 internal
|
119 |
+
119 singleton
|
120 |
+
120 begin
|
121 |
+
121 end
|
122 |
+
122 internal
|
123 |
+
123 singleton
|
124 |
+
124 begin
|
125 |
+
125 end
|
126 |
+
126 internal
|
127 |
+
127 singleton
|
128 |
+
128 begin
|
129 |
+
129 end
|
130 |
+
130 internal
|
131 |
+
131 singleton
|
132 |
+
132 begin
|
133 |
+
133 end
|
134 |
+
134 internal
|
135 |
+
135 singleton
|
136 |
+
136 begin
|
137 |
+
137 end
|
138 |
+
138 internal
|
139 |
+
139 singleton
|
140 |
+
140 begin
|
141 |
+
141 end
|
142 |
+
142 internal
|
143 |
+
143 singleton
|
144 |
+
144 begin
|
145 |
+
145 end
|
146 |
+
146 internal
|
147 |
+
147 singleton
|
148 |
+
148 begin
|
149 |
+
149 end
|
150 |
+
150 internal
|
151 |
+
151 singleton
|
152 |
+
152 begin
|
153 |
+
153 end
|
154 |
+
154 internal
|
155 |
+
155 singleton
|
156 |
+
156 begin
|
157 |
+
157 end
|
158 |
+
158 internal
|
159 |
+
159 singleton
|
160 |
+
160 begin
|
161 |
+
161 end
|
162 |
+
162 internal
|
163 |
+
163 singleton
|
164 |
+
164 begin
|
165 |
+
165 end
|
166 |
+
166 internal
|
167 |
+
167 singleton
|
168 |
+
168 begin
|
169 |
+
169 end
|
170 |
+
170 internal
|
171 |
+
171 singleton
|
172 |
+
172 begin
|
173 |
+
173 end
|
174 |
+
174 internal
|
175 |
+
175 singleton
|
176 |
+
176 begin
|
177 |
+
177 end
|
178 |
+
178 internal
|
179 |
+
179 singleton
|
180 |
+
180 begin
|
181 |
+
181 end
|
182 |
+
182 internal
|
183 |
+
183 singleton
|
184 |
+
184 begin
|
185 |
+
185 end
|
186 |
+
186 internal
|
187 |
+
187 singleton
|
188 |
+
188 begin
|
189 |
+
189 end
|
190 |
+
190 internal
|
191 |
+
191 singleton
|
192 |
+
192 begin
|
193 |
+
193 end
|
194 |
+
194 internal
|
195 |
+
195 singleton
|
196 |
+
196 begin
|
197 |
+
197 end
|
198 |
+
198 internal
|
199 |
+
199 singleton
|
200 |
+
200 begin
|
201 |
+
201 end
|
202 |
+
202 internal
|
203 |
+
203 singleton
|
204 |
+
204 begin
|
205 |
+
205 end
|
206 |
+
206 internal
|
207 |
+
207 singleton
|
208 |
+
208 begin
|
209 |
+
209 end
|
210 |
+
210 internal
|
211 |
+
211 singleton
|
212 |
+
212 begin
|
213 |
+
213 end
|
214 |
+
214 internal
|
215 |
+
215 singleton
|
216 |
+
216 begin
|
217 |
+
217 end
|
218 |
+
218 internal
|
219 |
+
219 singleton
|
220 |
+
220 begin
|
221 |
+
221 end
|
222 |
+
222 internal
|
223 |
+
223 singleton
|
224 |
+
224 begin
|
225 |
+
225 end
|
226 |
+
226 internal
|
227 |
+
227 singleton
|
vosk_models/vosk-model-en-us-0.22-lgraph/graph/words.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.dubm
ADDED
Binary file (168 kB). View file
|
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.ie
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed35fa2f46d8853370f89480a53d3e0184ceaab9afef7f112b43cdda492e5326
|
3 |
+
size 19757687
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/final.mat
ADDED
Binary file (45 kB). View file
|
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/global_cmvn.stats
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
2.74606e+11 7.912398e+09 -1.038969e+11 1.317063e+10 -5.916838e+10 -9.741645e+10 -2.601366e+10 -7.401961e+10 -2.684753e+10 -1.58957e+10 -4.96366e+10 -8.033801e+09 -3.074859e+10 -1.707706e+10 -1.639996e+10 -1.829851e+10 -1.09582e+10 -5.920052e+09 -7.745878e+09 -1.833566e+09 -2.802531e+09 -7.583578e+08 -3.994372e+08 6.940003e+07 8.935535e+08 2.282279e+08 1.745994e+09 -6.372821e+07 8.785109e+08 -1.030507e+08 8.091005e+08 4.407504e+08 1.859903e+09 1.753656e+09 2.066627e+09 1.37222e+09 1.386451e+09 -1.142544e+09 -2.51193e+08 -9.788437e+08 3.129497e+09
|
3 |
+
2.54123e+13 1.928342e+12 6.751519e+12 1.637428e+12 3.016774e+12 5.912373e+12 1.868079e+12 3.886044e+12 1.841588e+12 1.633684e+12 2.137614e+12 1.072133e+12 1.296519e+12 1.00067e+12 8.062336e+11 6.591713e+11 4.603988e+11 3.121481e+11 2.243611e+11 1.153531e+11 6.293688e+10 2.146548e+10 2.735945e+09 7.957589e+08 1.053802e+10 2.59947e+10 4.301262e+10 5.558657e+10 7.239489e+10 8.546533e+10 8.436563e+10 7.792829e+10 8.569881e+10 9.576342e+10 7.780419e+10 5.335785e+10 5.166593e+10 4.813119e+10 3.81959e+10 2.395734e+10 0 ]
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/online_cmvn.conf
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
# configuration file for apply-cmvn-online, used in the script ../local/run_online_decoding.sh
|
vosk_models/vosk-model-en-us-0.22-lgraph/ivector/splice.conf
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
--left-context=3
|
2 |
+
--right-context=3
|
vosk_models/vosk-model-kz-0.15/README
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Kazakh model trained from https://github.com/IS2AI/ISSAI_SAIDA_Kazakh_ASR
|
2 |
+
|
3 |
+
Thanks to
|
4 |
+
|
5 |
+
A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline
|
6 |
+
Yerbolat Khassanov, Saida Mussakhojayeva, Almas Mirzakhmetov, Alen Adiyev, Mukhamet Nurpeiissov, Huseyin Atakan Varol
|
7 |
+
https://arxiv.org/abs/2009.10334
|
8 |
+
|
9 |
+
See also
|
10 |
+
|
11 |
+
A baseline model for computationally inexpensive speech recognition for Kazakh using the Coqui STT framework
|
12 |
+
Ilnar Salimzianov
|
13 |
+
https://arxiv.org/abs/2107.10637
|
14 |
+
|
15 |
+
WER:
|
16 |
+
|
17 |
+
%WER 8.06 [ 2844 / 35275, 437 ins, 358 del, 2049 sub ] exp/chain_a/tdnn/decode_dev_rescore/wer_10_0.0
|
18 |
+
%WER 6.81 [ 2444 / 35884, 309 ins, 398 del, 1737 sub ] exp/chain_a/tdnn/decode_test_rescore/wer_10_1.0
|
vosk_models/vosk-model-kz-0.15/am/final.mdl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0437812b2175b7cd337b400632ac9913d13a66c8b784ce17f17f5b16afe06e57
|
3 |
+
size 16086187
|
vosk_models/vosk-model-kz-0.15/am/frame_subsampling_factor
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
3
|
vosk_models/vosk-model-kz-0.15/am/tree
ADDED
Binary file (312 kB). View file
|
|
vosk_models/vosk-model-kz-0.15/conf/mfcc.conf
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
--use-energy=false
|
2 |
+
--num-mel-bins=40
|
3 |
+
--num-ceps=40
|
4 |
+
--low-freq=20
|
5 |
+
--high-freq=7600
|
6 |
+
--allow-upsample=true
|
7 |
+
--allow-downsample=true
|
vosk_models/vosk-model-kz-0.15/conf/model.conf
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
--min-active=200
|
2 |
+
--max-active=7000
|
3 |
+
--beam=13.0
|
4 |
+
--lattice-beam=6.0
|
5 |
+
--acoustic-scale=1.0
|
6 |
+
--frame-subsampling-factor=3
|
7 |
+
--endpoint.silence-phones=1:2:3:4:5:6:7:8:9:10
|
8 |
+
--endpoint.rule2.min-trailing-silence=0.5
|
9 |
+
--endpoint.rule3.min-trailing-silence=1.0
|
10 |
+
--endpoint.rule4.min-trailing-silence=2.0
|
vosk_models/vosk-model-kz-0.15/graph/HCLG.fst
ADDED
Git LFS Details
|
vosk_models/vosk-model-kz-0.15/graph/disambig_tid.int
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
9937
|
2 |
+
9938
|
3 |
+
9939
|
4 |
+
9940
|
vosk_models/vosk-model-kz-0.15/graph/num_pdfs
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2256
|
vosk_models/vosk-model-kz-0.15/graph/phones.txt
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<eps> 0
|
2 |
+
SIL 1
|
3 |
+
SIL_B 2
|
4 |
+
SIL_E 3
|
5 |
+
SIL_I 4
|
6 |
+
SIL_S 5
|
7 |
+
GBG 6
|
8 |
+
GBG_B 7
|
9 |
+
GBG_E 8
|
10 |
+
GBG_I 9
|
11 |
+
GBG_S 10
|
12 |
+
а_B 11
|
13 |
+
а_E 12
|
14 |
+
а_I 13
|
15 |
+
а_S 14
|
16 |
+
б_B 15
|
17 |
+
б_E 16
|
18 |
+
б_I 17
|
19 |
+
б_S 18
|
20 |
+
в_B 19
|
21 |
+
в_E 20
|
22 |
+
в_I 21
|
23 |
+
в_S 22
|
24 |
+
г_B 23
|
25 |
+
г_E 24
|
26 |
+
г_I 25
|
27 |
+
г_S 26
|
28 |
+
д_B 27
|
29 |
+
д_E 28
|
30 |
+
д_I 29
|
31 |
+
д_S 30
|
32 |
+
е_B 31
|
33 |
+
е_E 32
|
34 |
+
е_I 33
|
35 |
+
е_S 34
|
36 |
+
ж_B 35
|
37 |
+
ж_E 36
|
38 |
+
ж_I 37
|
39 |
+
ж_S 38
|
40 |
+
з_B 39
|
41 |
+
з_E 40
|
42 |
+
з_I 41
|
43 |
+
з_S 42
|
44 |
+
и_B 43
|
45 |
+
и_E 44
|
46 |
+
и_I 45
|
47 |
+
и_S 46
|
48 |
+
й_B 47
|
49 |
+
й_E 48
|
50 |
+
й_I 49
|
51 |
+
й_S 50
|
52 |
+
к_B 51
|
53 |
+
к_E 52
|
54 |
+
к_I 53
|
55 |
+
к_S 54
|
56 |
+
л_B 55
|
57 |
+
л_E 56
|
58 |
+
л_I 57
|
59 |
+
л_S 58
|
60 |
+
м_B 59
|
61 |
+
м_E 60
|
62 |
+
м_I 61
|
63 |
+
м_S 62
|
64 |
+
н_B 63
|
65 |
+
н_E 64
|
66 |
+
н_I 65
|
67 |
+
н_S 66
|
68 |
+
о_B 67
|
69 |
+
о_E 68
|
70 |
+
о_I 69
|
71 |
+
о_S 70
|
72 |
+
п_B 71
|
73 |
+
п_E 72
|
74 |
+
п_I 73
|
75 |
+
п_S 74
|
76 |
+
р_B 75
|
77 |
+
р_E 76
|
78 |
+
р_I 77
|
79 |
+
р_S 78
|
80 |
+
с_B 79
|
81 |
+
с_E 80
|
82 |
+
с_I 81
|
83 |
+
с_S 82
|
84 |
+
т_B 83
|
85 |
+
т_E 84
|
86 |
+
т_I 85
|
87 |
+
т_S 86
|
88 |
+
у_B 87
|
89 |
+
у_E 88
|
90 |
+
у_I 89
|
91 |
+
у_S 90
|
92 |
+
ф_B 91
|
93 |
+
ф_E 92
|
94 |
+
ф_I 93
|
95 |
+
ф_S 94
|
96 |
+
х_B 95
|
97 |
+
х_E 96
|
98 |
+
х_I 97
|
99 |
+
х_S 98
|
100 |
+
ц_B 99
|
101 |
+
ц_E 100
|
102 |
+
ц_I 101
|
103 |
+
ц_S 102
|
104 |
+
ч_B 103
|
105 |
+
ч_E 104
|
106 |
+
ч_I 105
|
107 |
+
ч_S 106
|
108 |
+
ш_B 107
|
109 |
+
ш_E 108
|
110 |
+
ш_I 109
|
111 |
+
ш_S 110
|
112 |
+
щ_B 111
|
113 |
+
щ_E 112
|
114 |
+
щ_I 113
|
115 |
+
щ_S 114
|
116 |
+
ы_B 115
|
117 |
+
ы_E 116
|
118 |
+
ы_I 117
|
119 |
+
ы_S 118
|
120 |
+
ь_B 119
|
121 |
+
ь_E 120
|
122 |
+
ь_I 121
|
123 |
+
ь_S 122
|
124 |
+
э_B 123
|
125 |
+
э_E 124
|
126 |
+
э_I 125
|
127 |
+
э_S 126
|
128 |
+
ю_B 127
|
129 |
+
ю_E 128
|
130 |
+
ю_I 129
|
131 |
+
ю_S 130
|
132 |
+
я_B 131
|
133 |
+
я_E 132
|
134 |
+
я_I 133
|
135 |
+
я_S 134
|
136 |
+
і_B 135
|
137 |
+
і_E 136
|
138 |
+
і_I 137
|
139 |
+
і_S 138
|
140 |
+
ғ_B 139
|
141 |
+
ғ_E 140
|
142 |
+
ғ_I 141
|
143 |
+
ғ_S 142
|
144 |
+
қ_B 143
|
145 |
+
қ_E 144
|
146 |
+
қ_I 145
|
147 |
+
қ_S 146
|
148 |
+
ң_B 147
|
149 |
+
ң_E 148
|
150 |
+
ң_I 149
|
151 |
+
ң_S 150
|
152 |
+
ү_B 151
|
153 |
+
ү_E 152
|
154 |
+
ү_I 153
|
155 |
+
ү_S 154
|
156 |
+
ұ_B 155
|
157 |
+
ұ_E 156
|
158 |
+
ұ_I 157
|
159 |
+
ұ_S 158
|
160 |
+
һ_B 159
|
161 |
+
һ_E 160
|
162 |
+
һ_I 161
|
163 |
+
һ_S 162
|
164 |
+
ә_B 163
|
165 |
+
ә_E 164
|
166 |
+
ә_I 165
|
167 |
+
ә_S 166
|
168 |
+
ө_B 167
|
169 |
+
ө_E 168
|
170 |
+
ө_I 169
|
171 |
+
ө_S 170
|
172 |
+
#0 171
|
173 |
+
#1 172
|
174 |
+
#2 173
|
175 |
+
#3 174
|
vosk_models/vosk-model-kz-0.15/graph/phones/align_lexicon.int
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vosk_models/vosk-model-kz-0.15/graph/phones/align_lexicon.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a76d493077610286950eef7c06a68c9f251c94383da3ef1651331c7dc29710f
|
3 |
+
size 19139024
|
vosk_models/vosk-model-kz-0.15/graph/phones/disambig.int
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
171
|
2 |
+
172
|
3 |
+
173
|
4 |
+
174
|
vosk_models/vosk-model-kz-0.15/graph/phones/disambig.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#0
|
2 |
+
#1
|
3 |
+
#2
|
4 |
+
#3
|
vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.csl
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1
|
vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.int
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1
|
vosk_models/vosk-model-kz-0.15/graph/phones/optional_silence.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
SIL
|
vosk_models/vosk-model-kz-0.15/graph/phones/silence.csl
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1:2:3:4:5:6:7:8:9:10
|
vosk_models/vosk-model-kz-0.15/graph/phones/word_boundary.int
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
1 nonword
|
2 |
+
2 begin
|
3 |
+
3 end
|
4 |
+
4 internal
|
5 |
+
5 singleton
|
6 |
+
6 nonword
|
7 |
+
7 begin
|
8 |
+
8 end
|
9 |
+
9 internal
|
10 |
+
10 singleton
|
11 |
+
11 begin
|
12 |
+
12 end
|
13 |
+
13 internal
|
14 |
+
14 singleton
|
15 |
+
15 begin
|
16 |
+
16 end
|
17 |
+
17 internal
|
18 |
+
18 singleton
|
19 |
+
19 begin
|
20 |
+
20 end
|
21 |
+
21 internal
|
22 |
+
22 singleton
|
23 |
+
23 begin
|
24 |
+
24 end
|
25 |
+
25 internal
|
26 |
+
26 singleton
|
27 |
+
27 begin
|
28 |
+
28 end
|
29 |
+
29 internal
|
30 |
+
30 singleton
|
31 |
+
31 begin
|
32 |
+
32 end
|
33 |
+
33 internal
|
34 |
+
34 singleton
|
35 |
+
35 begin
|
36 |
+
36 end
|
37 |
+
37 internal
|
38 |
+
38 singleton
|
39 |
+
39 begin
|
40 |
+
40 end
|
41 |
+
41 internal
|
42 |
+
42 singleton
|
43 |
+
43 begin
|
44 |
+
44 end
|
45 |
+
45 internal
|
46 |
+
46 singleton
|
47 |
+
47 begin
|
48 |
+
48 end
|
49 |
+
49 internal
|
50 |
+
50 singleton
|
51 |
+
51 begin
|
52 |
+
52 end
|
53 |
+
53 internal
|
54 |
+
54 singleton
|
55 |
+
55 begin
|
56 |
+
56 end
|
57 |
+
57 internal
|
58 |
+
58 singleton
|
59 |
+
59 begin
|
60 |
+
60 end
|
61 |
+
61 internal
|
62 |
+
62 singleton
|
63 |
+
63 begin
|
64 |
+
64 end
|
65 |
+
65 internal
|
66 |
+
66 singleton
|
67 |
+
67 begin
|
68 |
+
68 end
|
69 |
+
69 internal
|
70 |
+
70 singleton
|
71 |
+
71 begin
|
72 |
+
72 end
|
73 |
+
73 internal
|
74 |
+
74 singleton
|
75 |
+
75 begin
|
76 |
+
76 end
|
77 |
+
77 internal
|
78 |
+
78 singleton
|
79 |
+
79 begin
|
80 |
+
80 end
|
81 |
+
81 internal
|
82 |
+
82 singleton
|
83 |
+
83 begin
|
84 |
+
84 end
|
85 |
+
85 internal
|
86 |
+
86 singleton
|
87 |
+
87 begin
|
88 |
+
88 end
|
89 |
+
89 internal
|
90 |
+
90 singleton
|
91 |
+
91 begin
|
92 |
+
92 end
|
93 |
+
93 internal
|
94 |
+
94 singleton
|
95 |
+
95 begin
|
96 |
+
96 end
|
97 |
+
97 internal
|
98 |
+
98 singleton
|
99 |
+
99 begin
|
100 |
+
100 end
|
101 |
+
101 internal
|
102 |
+
102 singleton
|
103 |
+
103 begin
|
104 |
+
104 end
|
105 |
+
105 internal
|
106 |
+
106 singleton
|
107 |
+
107 begin
|
108 |
+
108 end
|
109 |
+
109 internal
|
110 |
+
110 singleton
|
111 |
+
111 begin
|
112 |
+
112 end
|
113 |
+
113 internal
|
114 |
+
114 singleton
|
115 |
+
115 begin
|
116 |
+
116 end
|
117 |
+
117 internal
|
118 |
+
118 singleton
|
119 |
+
119 begin
|
120 |
+
120 end
|
121 |
+
121 internal
|
122 |
+
122 singleton
|
123 |
+
123 begin
|
124 |
+
124 end
|
125 |
+
125 internal
|
126 |
+
126 singleton
|
127 |
+
127 begin
|
128 |
+
128 end
|
129 |
+
129 internal
|
130 |
+
130 singleton
|
131 |
+
131 begin
|
132 |
+
132 end
|
133 |
+
133 internal
|
134 |
+
134 singleton
|
135 |
+
135 begin
|
136 |
+
136 end
|
137 |
+
137 internal
|
138 |
+
138 singleton
|
139 |
+
139 begin
|
140 |
+
140 end
|
141 |
+
141 internal
|
142 |
+
142 singleton
|
143 |
+
143 begin
|
144 |
+
144 end
|
145 |
+
145 internal
|
146 |
+
146 singleton
|
147 |
+
147 begin
|
148 |
+
148 end
|
149 |
+
149 internal
|
150 |
+
150 singleton
|
151 |
+
151 begin
|
152 |
+
152 end
|
153 |
+
153 internal
|
154 |
+
154 singleton
|
155 |
+
155 begin
|
156 |
+
156 end
|
157 |
+
157 internal
|
158 |
+
158 singleton
|
159 |
+
159 begin
|
160 |
+
160 end
|
161 |
+
161 internal
|
162 |
+
162 singleton
|
163 |
+
163 begin
|
164 |
+
164 end
|
165 |
+
165 internal
|
166 |
+
166 singleton
|
167 |
+
167 begin
|
168 |
+
168 end
|
169 |
+
169 internal
|
170 |
+
170 singleton
|
vosk_models/vosk-model-kz-0.15/graph/phones/word_boundary.txt
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
SIL nonword
|
2 |
+
SIL_B begin
|
3 |
+
SIL_E end
|
4 |
+
SIL_I internal
|
5 |
+
SIL_S singleton
|
6 |
+
GBG nonword
|
7 |
+
GBG_B begin
|
8 |
+
GBG_E end
|
9 |
+
GBG_I internal
|
10 |
+
GBG_S singleton
|
11 |
+
а_B begin
|
12 |
+
а_E end
|
13 |
+
а_I internal
|
14 |
+
а_S singleton
|
15 |
+
б_B begin
|
16 |
+
б_E end
|
17 |
+
б_I internal
|
18 |
+
б_S singleton
|
19 |
+
в_B begin
|
20 |
+
в_E end
|
21 |
+
в_I internal
|
22 |
+
в_S singleton
|
23 |
+
г_B begin
|
24 |
+
г_E end
|
25 |
+
г_I internal
|
26 |
+
г_S singleton
|
27 |
+
д_B begin
|
28 |
+
д_E end
|
29 |
+
д_I internal
|
30 |
+
д_S singleton
|
31 |
+
е_B begin
|
32 |
+
е_E end
|
33 |
+
е_I internal
|
34 |
+
е_S singleton
|
35 |
+
ж_B begin
|
36 |
+
ж_E end
|
37 |
+
ж_I internal
|
38 |
+
ж_S singleton
|
39 |
+
з_B begin
|
40 |
+
з_E end
|
41 |
+
з_I internal
|
42 |
+
з_S singleton
|
43 |
+
и_B begin
|
44 |
+
и_E end
|
45 |
+
и_I internal
|
46 |
+
и_S singleton
|
47 |
+
й_B begin
|
48 |
+
й_E end
|
49 |
+
й_I internal
|
50 |
+
й_S singleton
|
51 |
+
к_B begin
|
52 |
+
к_E end
|
53 |
+
к_I internal
|
54 |
+
к_S singleton
|
55 |
+
л_B begin
|
56 |
+
л_E end
|
57 |
+
л_I internal
|
58 |
+
л_S singleton
|
59 |
+
м_B begin
|
60 |
+
м_E end
|
61 |
+
м_I internal
|
62 |
+
м_S singleton
|
63 |
+
н_B begin
|
64 |
+
н_E end
|
65 |
+
н_I internal
|
66 |
+
н_S singleton
|
67 |
+
о_B begin
|
68 |
+
о_E end
|
69 |
+
о_I internal
|
70 |
+
о_S singleton
|
71 |
+
п_B begin
|
72 |
+
п_E end
|
73 |
+
п_I internal
|
74 |
+
п_S singleton
|
75 |
+
р_B begin
|
76 |
+
р_E end
|
77 |
+
р_I internal
|
78 |
+
р_S singleton
|
79 |
+
с_B begin
|
80 |
+
с_E end
|
81 |
+
с_I internal
|
82 |
+
с_S singleton
|
83 |
+
т_B begin
|
84 |
+
т_E end
|
85 |
+
т_I internal
|
86 |
+
т_S singleton
|
87 |
+
у_B begin
|
88 |
+
у_E end
|
89 |
+
у_I internal
|
90 |
+
у_S singleton
|
91 |
+
ф_B begin
|
92 |
+
ф_E end
|
93 |
+
ф_I internal
|
94 |
+
ф_S singleton
|
95 |
+
х_B begin
|
96 |
+
х_E end
|
97 |
+
х_I internal
|
98 |
+
х_S singleton
|
99 |
+
ц_B begin
|
100 |
+
ц_E end
|
101 |
+
ц_I internal
|
102 |
+
ц_S singleton
|
103 |
+
ч_B begin
|
104 |
+
ч_E end
|
105 |
+
ч_I internal
|
106 |
+
ч_S singleton
|
107 |
+
ш_B begin
|
108 |
+
ш_E end
|
109 |
+
ш_I internal
|
110 |
+
ш_S singleton
|
111 |
+
щ_B begin
|
112 |
+
щ_E end
|
113 |
+
щ_I internal
|
114 |
+
щ_S singleton
|
115 |
+
ы_B begin
|
116 |
+
ы_E end
|
117 |
+
ы_I internal
|
118 |
+
ы_S singleton
|
119 |
+
ь_B begin
|
120 |
+
ь_E end
|
121 |
+
ь_I internal
|
122 |
+
ь_S singleton
|
123 |
+
э_B begin
|
124 |
+
э_E end
|
125 |
+
э_I internal
|
126 |
+
э_S singleton
|
127 |
+
ю_B begin
|
128 |
+
ю_E end
|
129 |
+
ю_I internal
|
130 |
+
ю_S singleton
|
131 |
+
я_B begin
|
132 |
+
я_E end
|
133 |
+
я_I internal
|
134 |
+
я_S singleton
|
135 |
+
і_B begin
|
136 |
+
і_E end
|
137 |
+
і_I internal
|
138 |
+
і_S singleton
|
139 |
+
ғ_B begin
|
140 |
+
ғ_E end
|
141 |
+
ғ_I internal
|
142 |
+
ғ_S singleton
|
143 |
+
қ_B begin
|
144 |
+
қ_E end
|
145 |
+
қ_I internal
|
146 |
+
қ_S singleton
|
147 |
+
ң_B begin
|
148 |
+
ң_E end
|
149 |
+
ң_I internal
|
150 |
+
ң_S singleton
|
151 |
+
ү_B begin
|
152 |
+
ү_E end
|
153 |
+
ү_I internal
|
154 |
+
ү_S singleton
|
155 |
+
ұ_B begin
|
156 |
+
ұ_E end
|
157 |
+
ұ_I internal
|
158 |
+
ұ_S singleton
|
159 |
+
һ_B begin
|
160 |
+
һ_E end
|
161 |
+
һ_I internal
|
162 |
+
һ_S singleton
|
163 |
+
ә_B begin
|
164 |
+
ә_E end
|
165 |
+
ә_I internal
|
166 |
+
ә_S singleton
|
167 |
+
ө_B begin
|
168 |
+
ө_E end
|
169 |
+
ө_I internal
|
170 |
+
ө_S singleton
|
vosk_models/vosk-model-kz-0.15/graph/words.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vosk_models/vosk-model-kz-0.15/ivector/final.dubm
ADDED
Binary file (168 kB). View file
|
|
vosk_models/vosk-model-kz-0.15/ivector/final.ie
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7903fb879d26a7ea72c51aadfefb10f856e09f1663794c54c32c0c44c1703ac
|
3 |
+
size 9927287
|