chickenflyshigh/voice-assistant-chatbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
chickenflyshigh
2024-10-29 22:05:42 +11:00
commit 51efcd9c0f
25 changed files with 4973 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
piper-tts/en_GB-jenny_dioco-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/en_GB-semaine-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/en_US-ryan-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/en_en_GB_jenny_dioco_medium_en_GB-jenny_dioco-medium.onnx.json
+493
View File
@@ -0,0 +1,493 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-gb-x-rp"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"dataset": "jenny_dioco"
}
piper-tts/en_en_GB_semaine_medium_en_GB-semaine-medium.onnx.json
+508
View File
@@ -0,0 +1,508 @@
{
"piper_version": "1.2.0",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-gb-x-rp"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 4,
"speaker_id_map": {
"prudence": 0,
"spike": 1,
"obadiah": 2,
"poppy": 3
},
"piper_version": "1.0.0",
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"dataset": "semaine"
}
piper-tts/en_en_US_ryan_medium_en_US-ryan-medium.onnx.json
+493
View File
@@ -0,0 +1,493 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "en-us"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"dataset": "ryan"
}
piper-tts/fr_FR-mls-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/fr_fr_FR_mls_medium_fr_FR-mls-medium.onnx.json
+634
View File
@@ -0,0 +1,634 @@
{
"dataset": "mls",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "fr"
},
"language": {
"code": "fr_FR",
"family": "fr",
"region": "FR",
"name_native": "Français",
"name_english": "French",
"country_english": "France"
},
"inference": {
"noise_scale": 0.333,
"length_scale": 1,
"noise_w": 0.333
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̊": [
158
],
"̝": [
157
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 125,
"speaker_id_map": {
"1840": 0,
"3698": 1,
"123": 2,
"1474": 3,
"12709": 4,
"7423": 5,
"9242": 6,
"8778": 7,
"3060": 8,
"4512": 9,
"6249": 10,
"12541": 11,
"13634": 12,
"10065": 13,
"6128": 14,
"5232": 15,
"5764": 16,
"12713": 17,
"12823": 18,
"6070": 19,
"12501": 20,
"9121": 21,
"1649": 22,
"2776": 23,
"11772": 24,
"5612": 25,
"11822": 26,
"1590": 27,
"5525": 28,
"10827": 29,
"1243": 30,
"13142": 31,
"62": 32,
"13177": 33,
"10620": 34,
"8102": 35,
"8582": 36,
"11875": 37,
"7239": 38,
"9854": 39,
"7377": 40,
"10082": 41,
"12512": 42,
"1329": 43,
"2506": 44,
"6856": 45,
"10058": 46,
"103": 47,
"14": 48,
"6381": 49,
"1664": 50,
"11954": 51,
"66": 52,
"1127": 53,
"3270": 54,
"13611": 55,
"13658": 56,
"12968": 57,
"1989": 58,
"12981": 59,
"7193": 60,
"6348": 61,
"7679": 62,
"2284": 63,
"3182": 64,
"3503": 65,
"2033": 66,
"2771": 67,
"7614": 68,
"125": 69,
"3204": 70,
"5595": 71,
"5553": 72,
"694": 73,
"1624": 74,
"1887": 75,
"2926": 76,
"7150": 77,
"3190": 78,
"3344": 79,
"4699": 80,
"1798": 81,
"1745": 82,
"5077": 83,
"753": 84,
"52": 85,
"4174": 86,
"4018": 87,
"12899": 88,
"1844": 89,
"4396": 90,
"1817": 91,
"2155": 92,
"2946": 93,
"4336": 94,
"4609": 95,
"1977": 96,
"10957": 97,
"204": 98,
"4650": 99,
"5295": 100,
"5968": 101,
"4744": 102,
"2825": 103,
"9804": 104,
"707": 105,
"30": 106,
"115": 107,
"5840": 108,
"2587": 109,
"2607": 110,
"2544": 111,
"28": 112,
"27": 113,
"177": 114,
"112": 115,
"94": 116,
"2596": 117,
"3595": 118,
"7032": 119,
"7848": 120,
"11247": 121,
"7439": 122,
"2904": 123,
"6362": 124
},
"piper_version": "1.0.0"
}
piper-tts/glados.onnx
BIN
View File
Binary file not shown.
piper-tts/glados.onnx.json
+497
View File
@@ -0,0 +1,497 @@
{
"dataset": "glados",
"audio": {
"sample_rate": 22050,
"quality": "stacked_llama"
},
"espeak": {
"voice": "en-us"
},
"language": {
"code": "en-us"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
" ": [
3
],
"!": [
4
],
"\"": [
150
],
"#": [
149
],
"$": [
2
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
":": [
11
],
";": [
12
],
"?": [
13
],
"X": [
156
],
"^": [
1
],
"_": [
0
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"g": [
154
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʦ": [
155
],
"ʰ": [
145
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"ˤ": [
146
],
"̃": [
141
],
"̧": [
140
],
"̩": [
144
],
"̪": [
142
],
"̯": [
143
],
"̺": [
152
],
"̻": [
153
],
"β": [
125
],
"ε": [
147
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"↑": [
151
],
"↓": [
148
],
"ⱱ": [
129
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0"
}
piper-tts/ru_RU-dmitri-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/ru_ru_RU_dmitri_medium_ru_RU-dmitri-medium.onnx.json
+487
View File
@@ -0,0 +1,487 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "ru"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "ru_RU",
"family": "ru",
"region": "RU",
"name_native": "Русский",
"name_english": "Russian",
"country_english": "Russia"
},
"dataset": "dmitri"
}
piper-tts/silero_vad.onnx
BIN
View File
Binary file not shown.
piper-tts/vi_VN-vais1000-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/vi_vi_VN_vais1000_medium_vi_VN-vais1000-medium.onnx.json
+492
View File
@@ -0,0 +1,492 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "vi"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
],
"̺": [
152
],
"̻": [
153
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "vi_VN",
"family": "vi",
"region": "VN",
"name_native": "Tiếng Việt",
"name_english": "Vietnamese",
"country_english": "Vietnam"
},
"dataset": "vais1000"
}
piper-tts/zh_CN-huayan-medium.onnx
BIN
View File
Binary file not shown.
piper-tts/zh_zh_CN_huayan_medium_zh_CN-huayan-medium.onnx.json
+487
View File
@@ -0,0 +1,487 @@
{
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"espeak": {
"voice": "cmn"
},
"inference": {
"noise_scale": 0.667,
"length_scale": 1,
"noise_w": 0.8
},
"phoneme_type": "espeak",
"phoneme_map": {},
"phoneme_id_map": {
"_": [
0
],
"^": [
1
],
"$": [
2
],
" ": [
3
],
"!": [
4
],
"'": [
5
],
"(": [
6
],
")": [
7
],
",": [
8
],
"-": [
9
],
".": [
10
],
":": [
11
],
";": [
12
],
"?": [
13
],
"a": [
14
],
"b": [
15
],
"c": [
16
],
"d": [
17
],
"e": [
18
],
"f": [
19
],
"h": [
20
],
"i": [
21
],
"j": [
22
],
"k": [
23
],
"l": [
24
],
"m": [
25
],
"n": [
26
],
"o": [
27
],
"p": [
28
],
"q": [
29
],
"r": [
30
],
"s": [
31
],
"t": [
32
],
"u": [
33
],
"v": [
34
],
"w": [
35
],
"x": [
36
],
"y": [
37
],
"z": [
38
],
"æ": [
39
],
"ç": [
40
],
"ð": [
41
],
"ø": [
42
],
"ħ": [
43
],
"ŋ": [
44
],
"œ": [
45
],
"ǀ": [
46
],
"ǁ": [
47
],
"ǂ": [
48
],
"ǃ": [
49
],
"ɐ": [
50
],
"ɑ": [
51
],
"ɒ": [
52
],
"ɓ": [
53
],
"ɔ": [
54
],
"ɕ": [
55
],
"ɖ": [
56
],
"ɗ": [
57
],
"ɘ": [
58
],
"ə": [
59
],
"ɚ": [
60
],
"ɛ": [
61
],
"ɜ": [
62
],
"ɞ": [
63
],
"ɟ": [
64
],
"ɠ": [
65
],
"ɡ": [
66
],
"ɢ": [
67
],
"ɣ": [
68
],
"ɤ": [
69
],
"ɥ": [
70
],
"ɦ": [
71
],
"ɧ": [
72
],
"ɨ": [
73
],
"ɪ": [
74
],
"ɫ": [
75
],
"ɬ": [
76
],
"ɭ": [
77
],
"ɮ": [
78
],
"ɯ": [
79
],
"ɰ": [
80
],
"ɱ": [
81
],
"ɲ": [
82
],
"ɳ": [
83
],
"ɴ": [
84
],
"ɵ": [
85
],
"ɶ": [
86
],
"ɸ": [
87
],
"ɹ": [
88
],
"ɺ": [
89
],
"ɻ": [
90
],
"ɽ": [
91
],
"ɾ": [
92
],
"ʀ": [
93
],
"ʁ": [
94
],
"ʂ": [
95
],
"ʃ": [
96
],
"ʄ": [
97
],
"ʈ": [
98
],
"ʉ": [
99
],
"ʊ": [
100
],
"ʋ": [
101
],
"ʌ": [
102
],
"ʍ": [
103
],
"ʎ": [
104
],
"ʏ": [
105
],
"ʐ": [
106
],
"ʑ": [
107
],
"ʒ": [
108
],
"ʔ": [
109
],
"ʕ": [
110
],
"ʘ": [
111
],
"ʙ": [
112
],
"ʛ": [
113
],
"ʜ": [
114
],
"ʝ": [
115
],
"ʟ": [
116
],
"ʡ": [
117
],
"ʢ": [
118
],
"ʲ": [
119
],
"ˈ": [
120
],
"ˌ": [
121
],
"ː": [
122
],
"ˑ": [
123
],
"˞": [
124
],
"β": [
125
],
"θ": [
126
],
"χ": [
127
],
"ᵻ": [
128
],
"ⱱ": [
129
],
"0": [
130
],
"1": [
131
],
"2": [
132
],
"3": [
133
],
"4": [
134
],
"5": [
135
],
"6": [
136
],
"7": [
137
],
"8": [
138
],
"9": [
139
],
"̧": [
140
],
"̃": [
141
],
"̪": [
142
],
"̯": [
143
],
"̩": [
144
],
"ʰ": [
145
],
"ˤ": [
146
],
"ε": [
147
],
"↓": [
148
],
"#": [
149
],
"\"": [
150
],
"↑": [
151
]
},
"num_symbols": 256,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "1.0.0",
"language": {
"code": "zh_CN",
"family": "zh",
"region": "CN",
"name_native": "简体中文",
"name_english": "Chinese",
"country_english": "China"
},
"dataset": "huayan"
}