add read me

This commit is contained in:
2026-01-09 10:33:49 +11:00
parent c9e7e898d1
commit dd05e6d1fd
480 changed files with 9030 additions and 0 deletions

BIN
data/BT7274.onnx Normal file

Binary file not shown.

497
data/BT7274.onnx.json Normal file
View File

@@ -0,0 +1,497 @@
{
"dataset": "piper",
"audio": {
"sample_rate": 22050,
"quality": "dataset_L3-training"
},
"espeak": {
"voice": "en"
},
"language": {
"code": "en"
},
"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"
}

BIN
data/Donald Trump.tar.gz Normal file

Binary file not shown.

BIN
data/en_GB-alan-low.onnx Normal file

Binary file not shown.

View File

@@ -0,0 +1,420 @@
{
"audio": {
"sample_rate": 16000,
"quality": "low"
},
"espeak": {
"voice": "en-gb-x-rp"
},
"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
]
},
"num_symbols": 130,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "0.2.0",
"language": {
"code": "en_GB",
"family": "en",
"region": "GB",
"name_native": "English",
"name_english": "English",
"country_english": "Great Britain"
},
"dataset": "alan"
}

Binary file not shown.

View File

@@ -0,0 +1,497 @@
{
"dataset": "eminem_dojo",
"audio": {
"sample_rate": 22050,
"quality": "training_folder"
},
"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"
}

Binary file not shown.

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"
}

Binary file not shown.

View File

@@ -0,0 +1,497 @@
{
"dataset": "en_US-hal_6409-medium",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"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"
}

Binary file not shown.

View File

@@ -0,0 +1,497 @@
{
"dataset": "en_US-picard_7399-medium",
"audio": {
"sample_rate": 22050,
"quality": "medium"
},
"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"
}

BIN
data/en_US-ryan-medium.onnx Normal file

Binary file not shown.

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"
}

BIN
data/en_US-trump-high.onnx Normal file

Binary file not shown.

View File

@@ -0,0 +1,497 @@
{
"dataset": "Trump-V2",
"audio": {
"sample_rate": 22050,
"quality": "Trump-V2"
},
"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"
}

Binary file not shown.

View File

@@ -0,0 +1,420 @@
{
"audio": {
"sample_rate": 16000,
"quality": "low"
},
"espeak": {
"voice": "en-us"
},
"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
]
},
"num_symbols": 130,
"num_speakers": 1,
"speaker_id_map": {},
"piper_version": "0.2.0",
"language": {
"code": "en_US",
"family": "en",
"region": "US",
"name_native": "English",
"name_english": "English",
"country_english": "United States"
},
"dataset": "danny"
}

10
docker-compose.yml Normal file
View File

@@ -0,0 +1,10 @@
services:
piper:
image: rhasspy/wyoming-piper
container_name: piper_tts
restart: unless-stopped
ports:
- "10200:10200"
volumes:
- ./data:/data
command: --voice en_US-hal_6409-medium --data-dir /data --length-scale 1.22 --noise-scale 0.667 --noise-w 0.8

29
doorbell_tts_to_wav.sh Executable file
View File

@@ -0,0 +1,29 @@
#!/usr/bin/env bash
set -euo pipefail
TEXT="${1:-}"
OUT_WAV="${2:-}"
DEFAULT_VOICE="en_US-hal_6409-medium.onnx"
VOICE="${3:-$DEFAULT_VOICE}"
SPEED="${4:-1.0}"
PIPER_BIN="/home/sam/speech_piper/piper/piper"
MODEL_DIR="/home/sam/speech_piper/data"
if [[ -z "$TEXT" || -z "$OUT_WAV" ]]; then
echo "Usage: $0 \"text\" /path/to/out.wav [voice.onnx] [speed]"
exit 1
fi
TMP_WAV="/tmp/piper_doorbell_$$.wav"
echo "$TEXT" | \
"$PIPER_BIN" --model "$MODEL_DIR/$VOICE" --output_file "$TMP_WAV" \
--length-scale "$SPEED"
# Convert to ESP-friendly WAV: 16kHz mono 16-bit
sox "$TMP_WAV" -r 16000 -c 1 -b 16 -e signed-integer "$OUT_WAV"
rm -f "$TMP_WAV"
echo "Wrote: $OUT_WAV"

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -0,0 +1,8 @@
name Vietnamese (Northern)
language vi
words 1 2
pitch 95 175
tone 100 225 800 100 2000 50 5400 75 8000 200

View File

@@ -0,0 +1,9 @@
name Vietnamese (Central)
language vi-vn-x-central
phonemes vi-hue
dictrules 1
words 1
pitch 82 118 //80 118
voicing 90 //18
flutter 20

View File

@@ -0,0 +1,9 @@
name Vietnamese (Southern)
language vi-vn-x-south
phonemes vi-sgn
dictrules 2
words 1
pitch 82 118 //80 118
voicing 90 //18
flutter 20

View File

@@ -0,0 +1,4 @@
name Esperanto
language eo
apostrophe 2

View File

@@ -0,0 +1,2 @@
name Interlingua
language ia

View File

@@ -0,0 +1,5 @@
name Ido
language io
phonemes eo
status testing

View File

@@ -0,0 +1,4 @@
name Lojban
language jbo
speed 80 // speed adjustment, percentage

View File

@@ -0,0 +1,8 @@
name Lingua Franca Nova
language lfn
phonemes base2
l_unpronouncable 0
numbers 2 3
stressLength 150 140 180 180 0 0 200 200

View File

@@ -0,0 +1,5 @@
name Klingon
language piqd
status testing
stressRule 3

View File

@@ -0,0 +1,7 @@
name Pyash
language py
maintainer Logan Streondj <logan@liberit.ca>
status testing
speed 80 // speed adjustment, percentage
stressRule 0

View File

@@ -0,0 +1,6 @@
name Lang Belta
language qdb
numbers 4 3
replace 1 t ?

View File

@@ -0,0 +1,4 @@
name Quenya
language qya
stressRule 2
// rule=penultimate, with qya_rules for light penultimate syllables to move primary stress to the preceding (antepenultimate) syllable

View File

@@ -0,0 +1,4 @@
name Sindarin
language sjn
stressRule 2
// rule=penultimate, with sjn_rules for light penultimate syllables to move primary stress to the preceding (antepenultimate) syllable

View File

@@ -0,0 +1,6 @@
name Nahuatl (Classical)
language nci
intonation 3
stressRule 2
stressLength 190 190 200 200 0 0 220 240

View File

@@ -0,0 +1,2 @@
name Lithuanian
language lt

View File

@@ -0,0 +1,12 @@
name Latgalian
language ltg
maintainer Valdis Vitolins <valdis.vitolins@odo.lv>
status testing
phonemes lv
dictionary lv
dictrules 2 // Setting for Latgalian pronunciation
words 0 2
pitch 64 118
tone 60 150 204 100 400 255 700 10 3000 255
stressAmp 12 10 8 8 0 0 15 16
stressLength 160 140 200 140 0 0 240 160

View File

@@ -0,0 +1,9 @@
name Latvian
language lv
maintainer Valdis Vitolins <valdis.vitolins@odo.lv>
status mature
words 0 2
pitch 67 123
tone 60 150 204 100 400 255 700 10 3000 255
stressAmp 11 8 11 9 0 0 14 12
stressLength 160 120 200 130 0 0 230 180

View File

@@ -0,0 +1,4 @@
name Swahili
language sw
status testing

View File

@@ -0,0 +1,4 @@
name Setswana
language tn
status testing

View File

@@ -0,0 +1,3 @@
name Georgian
language ka
lowercaseSentence // A period followed by a lowercase letter is considered a sentence (mkhedruli)

Some files were not shown because too many files have changed in this diff Show More