Jarbas commited on
Commit
007a057
·
verified ·
1 Parent(s): 90bd1e7

Add vosk-tts Russian voices (tamara, irina, natasha)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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__irina/dictionary filter=lfs diff=lfs merge=lfs -text
37
+ vosk__natasha/dictionary filter=lfs diff=lfs merge=lfs -text
38
+ vosk__tamara/dictionary filter=lfs diff=lfs merge=lfs -text
vosk__irina/config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "ru"
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
+ "a0": [
58
+ 14
59
+ ],
60
+ "a1": [
61
+ 15
62
+ ],
63
+ "b": [
64
+ 16
65
+ ],
66
+ "bj": [
67
+ 17
68
+ ],
69
+ "c": [
70
+ 18
71
+ ],
72
+ "ch": [
73
+ 19
74
+ ],
75
+ "d": [
76
+ 20
77
+ ],
78
+ "dj": [
79
+ 21
80
+ ],
81
+ "e0": [
82
+ 22
83
+ ],
84
+ "e1": [
85
+ 23
86
+ ],
87
+ "f": [
88
+ 24
89
+ ],
90
+ "fj": [
91
+ 25
92
+ ],
93
+ "g": [
94
+ 26
95
+ ],
96
+ "gj": [
97
+ 27
98
+ ],
99
+ "h": [
100
+ 28
101
+ ],
102
+ "hj": [
103
+ 29
104
+ ],
105
+ "i0": [
106
+ 30
107
+ ],
108
+ "i1": [
109
+ 31
110
+ ],
111
+ "j": [
112
+ 32
113
+ ],
114
+ "k": [
115
+ 33
116
+ ],
117
+ "kj": [
118
+ 34
119
+ ],
120
+ "l": [
121
+ 35
122
+ ],
123
+ "lj": [
124
+ 36
125
+ ],
126
+ "m": [
127
+ 37
128
+ ],
129
+ "mj": [
130
+ 38
131
+ ],
132
+ "n": [
133
+ 39
134
+ ],
135
+ "nj": [
136
+ 40
137
+ ],
138
+ "o0": [
139
+ 41
140
+ ],
141
+ "o1": [
142
+ 42
143
+ ],
144
+ "p": [
145
+ 43
146
+ ],
147
+ "pj": [
148
+ 44
149
+ ],
150
+ "r": [
151
+ 45
152
+ ],
153
+ "rj": [
154
+ 46
155
+ ],
156
+ "s": [
157
+ 47
158
+ ],
159
+ "sch": [
160
+ 48
161
+ ],
162
+ "sh": [
163
+ 49
164
+ ],
165
+ "sj": [
166
+ 50
167
+ ],
168
+ "t": [
169
+ 51
170
+ ],
171
+ "tj": [
172
+ 52
173
+ ],
174
+ "u0": [
175
+ 53
176
+ ],
177
+ "u1": [
178
+ 54
179
+ ],
180
+ "v": [
181
+ 55
182
+ ],
183
+ "vj": [
184
+ 56
185
+ ],
186
+ "y0": [
187
+ 57
188
+ ],
189
+ "y1": [
190
+ 58
191
+ ],
192
+ "z": [
193
+ 59
194
+ ],
195
+ "zh": [
196
+ 60
197
+ ],
198
+ "zj": [
199
+ 61
200
+ ]
201
+ },
202
+ "num_symbols": 62,
203
+ "num_speakers": 1,
204
+ "speaker_id_map": {}
205
+ }
vosk__irina/dictionary ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1367962e3c627edbb05d70ee2c036ec6de1ad3287e07ac5173294b0f9cfcbd46
3
+ size 101426451
vosk__irina/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a67207b31536e3ddc11485abe6d4ba95084ae54751e4e5a768c5389a44a470f
3
+ size 121279404
vosk__natasha/config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "ru"
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
+ "a0": [
58
+ 14
59
+ ],
60
+ "a1": [
61
+ 15
62
+ ],
63
+ "b": [
64
+ 16
65
+ ],
66
+ "bj": [
67
+ 17
68
+ ],
69
+ "c": [
70
+ 18
71
+ ],
72
+ "ch": [
73
+ 19
74
+ ],
75
+ "d": [
76
+ 20
77
+ ],
78
+ "dj": [
79
+ 21
80
+ ],
81
+ "e0": [
82
+ 22
83
+ ],
84
+ "e1": [
85
+ 23
86
+ ],
87
+ "f": [
88
+ 24
89
+ ],
90
+ "fj": [
91
+ 25
92
+ ],
93
+ "g": [
94
+ 26
95
+ ],
96
+ "gj": [
97
+ 27
98
+ ],
99
+ "h": [
100
+ 28
101
+ ],
102
+ "hj": [
103
+ 29
104
+ ],
105
+ "i0": [
106
+ 30
107
+ ],
108
+ "i1": [
109
+ 31
110
+ ],
111
+ "j": [
112
+ 32
113
+ ],
114
+ "k": [
115
+ 33
116
+ ],
117
+ "kj": [
118
+ 34
119
+ ],
120
+ "l": [
121
+ 35
122
+ ],
123
+ "lj": [
124
+ 36
125
+ ],
126
+ "m": [
127
+ 37
128
+ ],
129
+ "mj": [
130
+ 38
131
+ ],
132
+ "n": [
133
+ 39
134
+ ],
135
+ "nj": [
136
+ 40
137
+ ],
138
+ "o0": [
139
+ 41
140
+ ],
141
+ "o1": [
142
+ 42
143
+ ],
144
+ "p": [
145
+ 43
146
+ ],
147
+ "pj": [
148
+ 44
149
+ ],
150
+ "r": [
151
+ 45
152
+ ],
153
+ "rj": [
154
+ 46
155
+ ],
156
+ "s": [
157
+ 47
158
+ ],
159
+ "sch": [
160
+ 48
161
+ ],
162
+ "sh": [
163
+ 49
164
+ ],
165
+ "sj": [
166
+ 50
167
+ ],
168
+ "t": [
169
+ 51
170
+ ],
171
+ "tj": [
172
+ 52
173
+ ],
174
+ "u0": [
175
+ 53
176
+ ],
177
+ "u1": [
178
+ 54
179
+ ],
180
+ "v": [
181
+ 55
182
+ ],
183
+ "vj": [
184
+ 56
185
+ ],
186
+ "y0": [
187
+ 57
188
+ ],
189
+ "y1": [
190
+ 58
191
+ ],
192
+ "z": [
193
+ 59
194
+ ],
195
+ "zh": [
196
+ 60
197
+ ],
198
+ "zj": [
199
+ 61
200
+ ]
201
+ },
202
+ "num_symbols": 62,
203
+ "num_speakers": 1,
204
+ "speaker_id_map": {}
205
+ }
vosk__natasha/dictionary ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1367962e3c627edbb05d70ee2c036ec6de1ad3287e07ac5173294b0f9cfcbd46
3
+ size 101426451
vosk__natasha/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355d023f99d1646724ce096cfe5c006daecc781e234c068efb13b6ecb2fd9069
3
+ size 121279404
vosk__tamara/config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "ru"
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
+ "a0": [
58
+ 14
59
+ ],
60
+ "a1": [
61
+ 15
62
+ ],
63
+ "b": [
64
+ 16
65
+ ],
66
+ "bj": [
67
+ 17
68
+ ],
69
+ "c": [
70
+ 18
71
+ ],
72
+ "ch": [
73
+ 19
74
+ ],
75
+ "d": [
76
+ 20
77
+ ],
78
+ "dj": [
79
+ 21
80
+ ],
81
+ "e0": [
82
+ 22
83
+ ],
84
+ "e1": [
85
+ 23
86
+ ],
87
+ "f": [
88
+ 24
89
+ ],
90
+ "fj": [
91
+ 25
92
+ ],
93
+ "g": [
94
+ 26
95
+ ],
96
+ "gj": [
97
+ 27
98
+ ],
99
+ "h": [
100
+ 28
101
+ ],
102
+ "hj": [
103
+ 29
104
+ ],
105
+ "i0": [
106
+ 30
107
+ ],
108
+ "i1": [
109
+ 31
110
+ ],
111
+ "j": [
112
+ 32
113
+ ],
114
+ "k": [
115
+ 33
116
+ ],
117
+ "kj": [
118
+ 34
119
+ ],
120
+ "l": [
121
+ 35
122
+ ],
123
+ "lj": [
124
+ 36
125
+ ],
126
+ "m": [
127
+ 37
128
+ ],
129
+ "mj": [
130
+ 38
131
+ ],
132
+ "n": [
133
+ 39
134
+ ],
135
+ "nj": [
136
+ 40
137
+ ],
138
+ "o0": [
139
+ 41
140
+ ],
141
+ "o1": [
142
+ 42
143
+ ],
144
+ "p": [
145
+ 43
146
+ ],
147
+ "pj": [
148
+ 44
149
+ ],
150
+ "r": [
151
+ 45
152
+ ],
153
+ "rj": [
154
+ 46
155
+ ],
156
+ "s": [
157
+ 47
158
+ ],
159
+ "sch": [
160
+ 48
161
+ ],
162
+ "sh": [
163
+ 49
164
+ ],
165
+ "sj": [
166
+ 50
167
+ ],
168
+ "t": [
169
+ 51
170
+ ],
171
+ "tj": [
172
+ 52
173
+ ],
174
+ "u0": [
175
+ 53
176
+ ],
177
+ "u1": [
178
+ 54
179
+ ],
180
+ "v": [
181
+ 55
182
+ ],
183
+ "vj": [
184
+ 56
185
+ ],
186
+ "y0": [
187
+ 57
188
+ ],
189
+ "y1": [
190
+ 58
191
+ ],
192
+ "z": [
193
+ 59
194
+ ],
195
+ "zh": [
196
+ 60
197
+ ],
198
+ "zj": [
199
+ 61
200
+ ]
201
+ },
202
+ "num_symbols": 62,
203
+ "num_speakers": 1,
204
+ "speaker_id_map": {}
205
+ }
vosk__tamara/dictionary ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b32ff8e4e4b47f4ca1ddc8ce06942dc45806d2d001391008f467c20e07cea2b1
3
+ size 95684077
vosk__tamara/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f6fc0fa7beb3c5c2cbc16b343490c98dfc87b7c4e0690fd42055d37ee0138c
3
+ size 75766780