csukuangfj commited on
Commit
0c31dc5
1 Parent(s): d556fd2
CMU-in-IPA.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8235d0aef35db62bdcf6a701fb91ec17b02ab72223b27aaea53476488cdae7fe
3
- size 879147
 
 
 
 
en_US-libritts-high.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:861bd29768dd7ff804add4e21dea7e570378bf29443873bb3f4826b5720eb82a
3
- size 136673987
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c0eeb0bf6aa67875dd1d2b37d014357dee2aba96f5481686da522dc6b0b93a
3
+ size 136673944
lexicon.txt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d66e0ac92e0003805047814a220ef9592b527b99806e5e1a3745dc436d70c6
3
- size 36727361
 
 
 
 
tokens.txt DELETED
@@ -1,130 +0,0 @@
1
- _ 0
2
- ^ 1
3
- $ 2
4
- 3
5
- ! 4
6
- ' 5
7
- ( 6
8
- ) 7
9
- , 8
10
- - 9
11
- . 10
12
- : 11
13
- ; 12
14
- ? 13
15
- a 14
16
- b 15
17
- c 16
18
- d 17
19
- e 18
20
- f 19
21
- h 20
22
- i 21
23
- j 22
24
- k 23
25
- l 24
26
- m 25
27
- n 26
28
- o 27
29
- p 28
30
- q 29
31
- r 30
32
- s 31
33
- t 32
34
- u 33
35
- v 34
36
- w 35
37
- x 36
38
- y 37
39
- z 38
40
- æ 39
41
- ç 40
42
- ð 41
43
- ø 42
44
- ħ 43
45
- ŋ 44
46
- œ 45
47
- ǀ 46
48
- ǁ 47
49
- ǂ 48
50
- ǃ 49
51
- ɐ 50
52
- ɑ 51
53
- ɒ 52
54
- ɓ 53
55
- ɔ 54
56
- ɕ 55
57
- ɖ 56
58
- ɗ 57
59
- ɘ 58
60
- ə 59
61
- ɚ 60
62
- ɛ 61
63
- ɜ 62
64
- ɞ 63
65
- ɟ 64
66
- ɠ 65
67
- ɡ 66
68
- ɢ 67
69
- ɣ 68
70
- ɤ 69
71
- ɥ 70
72
- ɦ 71
73
- ɧ 72
74
- ɨ 73
75
- ɪ 74
76
- ɫ 75
77
- ɬ 76
78
- ɭ 77
79
- ɮ 78
80
- ɯ 79
81
- ɰ 80
82
- ɱ 81
83
- ɲ 82
84
- ɳ 83
85
- ɴ 84
86
- ɵ 85
87
- ɶ 86
88
- ɸ 87
89
- ɹ 88
90
- ɺ 89
91
- ɻ 90
92
- ɽ 91
93
- ɾ 92
94
- ʀ 93
95
- ʁ 94
96
- ʂ 95
97
- ʃ 96
98
- ʄ 97
99
- ʈ 98
100
- ʉ 99
101
- ʊ 100
102
- ʋ 101
103
- ʌ 102
104
- ʍ 103
105
- ʎ 104
106
- ʏ 105
107
- ʐ 106
108
- ʑ 107
109
- ʒ 108
110
- ʔ 109
111
- ʕ 110
112
- ʘ 111
113
- ʙ 112
114
- ʛ 113
115
- ʜ 114
116
- ʝ 115
117
- ʟ 116
118
- ʡ 117
119
- ʢ 118
120
- ʲ 119
121
- ˈ 120
122
- ˌ 121
123
- ː 122
124
- ˑ 123
125
- ˞ 124
126
- β 125
127
- θ 126
128
- χ 127
129
- ᵻ 128
130
- ⱱ 129
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vits-piper-en_US.py ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+
3
+ import json
4
+ import os
5
+ import re
6
+ from typing import Any, Dict
7
+
8
+ import onnx
9
+
10
+
11
+ def add_meta_data(filename: str, meta_data: Dict[str, Any]):
12
+ """Add meta data to an ONNX model. It is changed in-place.
13
+
14
+ Args:
15
+ filename:
16
+ Filename of the ONNX model to be changed.
17
+ meta_data:
18
+ Key-value pairs.
19
+ """
20
+ model = onnx.load(filename)
21
+ for key, value in meta_data.items():
22
+ meta = model.metadata_props.add()
23
+ meta.key = key
24
+ meta.value = str(value)
25
+
26
+ onnx.save(model, filename)
27
+
28
+
29
+ def load_config(model):
30
+ with open(f"{model}.json", "r") as file:
31
+ config = json.load(file)
32
+ return config
33
+
34
+
35
+ # for en_US-lessac-medium.onnx
36
+ # export TYPE=lessac
37
+ # export NAME=medium
38
+ def main():
39
+ t = os.environ.get("TYPE", None)
40
+ if not t:
41
+ print("Please provide the environment variable TYPE")
42
+ return
43
+
44
+ # thorsten or thorsten_emotional
45
+ name = os.environ.get("NAME", None)
46
+ if not t:
47
+ print("Please provide the environment variable NAME")
48
+ return
49
+ print("type", t)
50
+
51
+ config = load_config(f"en_US-{name}-{t}.onnx")
52
+
53
+ print("add model metadata")
54
+ meta_data = {
55
+ "model_type": "vits",
56
+ "comment": "piper", # must be piper for models from piper
57
+ "language": "English",
58
+ "voice": config["espeak"]["voice"], # e.g., en-us
59
+ "has_espeak": int("espeak" in config),
60
+ "n_speakers": config["num_speakers"],
61
+ "sample_rate": config["audio"]["sample_rate"],
62
+ }
63
+ print(meta_data)
64
+ add_meta_data(f"en_US-{name}-{t}.onnx", meta_data)
65
+
66
+
67
+ main()
vits-piper-en_US.sh ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+
3
+ name=$NAME
4
+ echo "name: $name"
5
+
6
+ type=$TYPE
7
+ echo "type: $type"
8
+
9
+ set -ex
10
+
11
+ # for en_US-lessac-medium.onnx
12
+ # export TYPE=lessac
13
+ # export NAME=medium
14
+
15
+ wget -qq https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/$name/$type/en_US-$name-$type.onnx
16
+ wget -qq https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/$name/$type/en_US-$name-$type.onnx.json
17
+ wget -qq https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/$name/$type/MODEL_CARD
18
+
19
+ pip install piper-phonemize onnx onnxruntime==1.16.0
20
+
21
+ python3 ./vits-piper-en_US.py