Hugging Face's logo

danielferr85
/
piper-voices-rknn

ONNX
Model card Files
xet
 Community
danielferr85 commited on
Commit
3009faa
·
verified ·
1 Parent(s): afcd6af

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +89 -1
  2. README.md +9 -0
  3. download_models.py +14 -0
  4. en/en_GB/alan/medium/MODEL_CARD +15 -0
  5. en/en_GB/alan/medium/config.json +483 -0
  6. en/en_GB/alan/medium/dataset.jsonl.gz +3 -0
  7. en/en_GB/alan/medium/decoder.onnx +3 -0
  8. en/en_GB/alan/medium/decoder_rk3576.rknn +3 -0
  9. en/en_GB/alan/medium/decoder_rk3588.rknn +3 -0
  10. en/en_GB/alan/medium/encoder.onnx +3 -0
  11. en/en_GB/alan/medium/epoch=6339-step=1647790.ckpt +3 -0
  12. en/en_GB/alan/medium/train.sh +17 -0
  13. en/en_GB/alba/medium/MODEL_CARD +15 -0
  14. en/en_GB/alba/medium/config.json +483 -0
  15. en/en_GB/alba/medium/dataset.jsonl.gz +3 -0
  16. en/en_GB/alba/medium/decoder.onnx +3 -0
  17. en/en_GB/alba/medium/decoder_rk3576.rknn +3 -0
  18. en/en_GB/alba/medium/decoder_rk3588.rknn +3 -0
  19. en/en_GB/alba/medium/encoder.onnx +3 -0
  20. en/en_GB/alba/medium/epoch=4179-step=2101090.ckpt +3 -0
  21. en/en_GB/alba/medium/train.sh +17 -0
  22. en/en_GB/aru/medium/LICENSE +20 -0
  23. en/en_GB/aru/medium/MODEL_CARD +15 -0
  24. en/en_GB/aru/medium/config.json +496 -0
  25. en/en_GB/aru/medium/dataset.jsonl.gz +3 -0
  26. en/en_GB/aru/medium/decoder.onnx +3 -0
  27. en/en_GB/aru/medium/decoder_rk3576.rknn +3 -0
  28. en/en_GB/aru/medium/decoder_rk3588.rknn +3 -0
  29. en/en_GB/aru/medium/encoder.onnx +3 -0
  30. en/en_GB/aru/medium/epoch=3479-step=939600.ckpt +3 -0
  31. en/en_GB/aru/medium/train.sh +17 -0
  32. en/en_GB/cori/high/MODEL_CARD +17 -0
  33. en/en_GB/cori/high/config.json +497 -0
  34. en/en_GB/cori/high/cori-high-500.ckpt +3 -0
  35. en/en_GB/cori/high/decoder.onnx +3 -0
  36. en/en_GB/cori/high/decoder_rk3576.rknn +3 -0
  37. en/en_GB/cori/high/decoder_rk3588.rknn +3 -0
  38. en/en_GB/cori/high/encoder.onnx +3 -0
  39. en/en_GB/cori/medium/cori-med-640.ckpt +3 -0
  40. en/en_GB/cori/medium/decoder.onnx +3 -0
  41. en/en_GB/cori/medium/decoder_rk3576.rknn +3 -0
  42. en/en_GB/cori/medium/decoder_rk3588.rknn +3 -0
  43. en/en_GB/cori/medium/encoder.onnx +3 -0
  44. en/en_GB/jenny_dioco/medium/LICENSE +1 -0
  45. en/en_GB/jenny_dioco/medium/MODEL_CARD +15 -0
  46. en/en_GB/jenny_dioco/medium/config.json +483 -0
  47. en/en_GB/jenny_dioco/medium/dataset.jsonl.gz +3 -0
  48. en/en_GB/jenny_dioco/medium/decoder.onnx +3 -0
  49. en/en_GB/jenny_dioco/medium/decoder_rk3576.rknn +3 -0
  50. en/en_GB/jenny_dioco/medium/decoder_rk3588.rknn +3 -0
.gitattributes CHANGED
@@ -8,6 +8,7 @@
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
 
11
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
@@ -25,7 +26,6 @@
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
  *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +33,91 @@ 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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.lz4 filter=lfs diff=lfs merge=lfs -text
12
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
13
  *.model filter=lfs diff=lfs merge=lfs -text
14
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
26
  *.safetensors filter=lfs diff=lfs merge=lfs -text
27
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
28
  *.tar.* filter=lfs diff=lfs merge=lfs -text
 
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
  *.wasm 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
+ # Audio files - uncompressed
37
+ *.pcm filter=lfs diff=lfs merge=lfs -text
38
+ *.sam filter=lfs diff=lfs merge=lfs -text
39
+ *.raw filter=lfs diff=lfs merge=lfs -text
40
+ # Audio files - compressed
41
+ *.aac filter=lfs diff=lfs merge=lfs -text
42
+ *.flac filter=lfs diff=lfs merge=lfs -text
43
+ *.mp3 filter=lfs diff=lfs merge=lfs -text
44
+ *.ogg filter=lfs diff=lfs merge=lfs -text
45
+ *.wav filter=lfs diff=lfs merge=lfs -text
46
+ # Image files - uncompressed
47
+ *.bmp filter=lfs diff=lfs merge=lfs -text
48
+ *.gif filter=lfs diff=lfs merge=lfs -text
49
+ *.png filter=lfs diff=lfs merge=lfs -text
50
+ *.tiff filter=lfs diff=lfs merge=lfs -text
51
+ # Image files - compressed
52
+ *.jpg filter=lfs diff=lfs merge=lfs -text
53
+ *.jpeg filter=lfs diff=lfs merge=lfs -text
54
+ *.webp filter=lfs diff=lfs merge=lfs -text
55
+ *.jsonl.gz filter=lfs diff=lfs merge=lfs -text
56
+ en/en_GB/alan/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
57
+ en/en_GB/alan/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
58
+ en/en_GB/alba/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
59
+ en/en_GB/alba/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
60
+ en/en_GB/aru/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
61
+ en/en_GB/aru/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
62
+ en/en_GB/cori/high/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
63
+ en/en_GB/cori/high/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
64
+ en/en_GB/cori/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
65
+ en/en_GB/cori/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
66
+ en/en_GB/jenny_dioco/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
67
+ en/en_GB/jenny_dioco/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
68
+ en/en_GB/northern_english_male/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
69
+ en/en_GB/northern_english_male/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
70
+ en/en_GB/semaine/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
71
+ en/en_GB/semaine/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
72
+ en/en_GB/vctk/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
73
+ en/en_GB/vctk/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
74
+ en/en_US/amy/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
75
+ en/en_US/amy/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
76
+ en/en_US/arctic/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
77
+ en/en_US/arctic/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
78
+ en/en_US/bryce/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
79
+ en/en_US/bryce/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
80
+ en/en_US/hfc_female/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
81
+ en/en_US/hfc_female/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
82
+ en/en_US/hfc_male/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
83
+ en/en_US/hfc_male/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
84
+ en/en_US/joe/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
85
+ en/en_US/joe/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
86
+ en/en_US/john/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
87
+ en/en_US/john/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
88
+ en/en_US/kristin/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
89
+ en/en_US/kristin/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
90
+ en/en_US/kusal/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
91
+ en/en_US/kusal/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
92
+ en/en_US/l2arctic/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
93
+ en/en_US/l2arctic/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
94
+ en/en_US/lessac/high/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
95
+ en/en_US/lessac/high/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
96
+ en/en_US/lessac/low/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
97
+ en/en_US/lessac/low/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
98
+ en/en_US/lessac/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
99
+ en/en_US/lessac/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
100
+ en/en_US/libritts_r/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
101
+ en/en_US/libritts_r/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
102
+ en/en_US/ljspeech/high/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
103
+ en/en_US/ljspeech/high/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
104
+ en/en_US/ljspeech/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
105
+ en/en_US/ljspeech/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
106
+ en/en_US/ryan/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
107
+ en/en_US/ryan/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
108
+ en/en_US/sam/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
109
+ en/en_US/sam/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
110
+ es/es_ES/davefx/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
111
+ es/es_ES/davefx/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
112
+ es/es_ES/sharvard/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
113
+ es/es_ES/sharvard/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
114
+ es/es_MX/ald/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
115
+ es/es_MX/ald/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
116
+ fr/fr_FR/mls/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
117
+ fr/fr_FR/mls/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
118
+ fr/fr_FR/siwis/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
119
+ fr/fr_FR/siwis/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
120
+ fr/fr_FR/upmc/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
121
+ fr/fr_FR/upmc/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
122
+ zh/zh_CN/huayan/medium/decoder_rk3576.rknn filter=lfs diff=lfs merge=lfs -text
123
+ zh/zh_CN/huayan/medium/decoder_rk3588.rknn filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+ Encoder (ONNX) and Decoder (RKNN) models for project RKLLAMA: https://github.com/NotPunchnox
6
+
7
+ RKNN Toolkit version: 2.3.2
8
+
9
+ Checkpoints for [Piper](https://github.com/rhasspy/piper) text to speech system.
download_models.py ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from huggingface_hub import snapshot_download
2
+
3
+ #models = ["es","en","zh","fr"]
4
+ models = ["en"]
5
+
6
+ for model in models:
7
+ snapshot_download(
8
+ repo_id="rhasspy/piper-checkpoints",
9
+ repo_type="dataset",
10
+ allow_patterns=f"{model}/**",
11
+ local_dir=".",
12
+ local_dir_use_symlinks=False
13
+ )
14
+
en/en_GB/alan/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for alan (medium)
2
+
3
+ * Language: en_GB (English, Great Britain)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://github.com/MycroftAI/mimic3-voices/blob/master/voices/en_UK/apope_low
11
+ * License: See URL
12
+
13
+ ## Training
14
+
15
+ Finetuned from U.S. English lessac voice (medium quality).
en/en_GB/alan/medium/config.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "en-gb-x-rp"
7
+ },
8
+ "inference": {
9
+ "noise_scale": 0.667,
10
+ "length_scale": 1,
11
+ "noise_w": 0.8
12
+ },
13
+ "phoneme_type": "espeak",
14
+ "phoneme_map": {},
15
+ "phoneme_id_map": {
16
+ "_": [
17
+ 0
18
+ ],
19
+ "^": [
20
+ 1
21
+ ],
22
+ "$": [
23
+ 2
24
+ ],
25
+ " ": [
26
+ 3
27
+ ],
28
+ "!": [
29
+ 4
30
+ ],
31
+ "'": [
32
+ 5
33
+ ],
34
+ "(": [
35
+ 6
36
+ ],
37
+ ")": [
38
+ 7
39
+ ],
40
+ ",": [
41
+ 8
42
+ ],
43
+ "-": [
44
+ 9
45
+ ],
46
+ ".": [
47
+ 10
48
+ ],
49
+ ":": [
50
+ 11
51
+ ],
52
+ ";": [
53
+ 12
54
+ ],
55
+ "?": [
56
+ 13
57
+ ],
58
+ "a": [
59
+ 14
60
+ ],
61
+ "b": [
62
+ 15
63
+ ],
64
+ "c": [
65
+ 16
66
+ ],
67
+ "d": [
68
+ 17
69
+ ],
70
+ "e": [
71
+ 18
72
+ ],
73
+ "f": [
74
+ 19
75
+ ],
76
+ "h": [
77
+ 20
78
+ ],
79
+ "i": [
80
+ 21
81
+ ],
82
+ "j": [
83
+ 22
84
+ ],
85
+ "k": [
86
+ 23
87
+ ],
88
+ "l": [
89
+ 24
90
+ ],
91
+ "m": [
92
+ 25
93
+ ],
94
+ "n": [
95
+ 26
96
+ ],
97
+ "o": [
98
+ 27
99
+ ],
100
+ "p": [
101
+ 28
102
+ ],
103
+ "q": [
104
+ 29
105
+ ],
106
+ "r": [
107
+ 30
108
+ ],
109
+ "s": [
110
+ 31
111
+ ],
112
+ "t": [
113
+ 32
114
+ ],
115
+ "u": [
116
+ 33
117
+ ],
118
+ "v": [
119
+ 34
120
+ ],
121
+ "w": [
122
+ 35
123
+ ],
124
+ "x": [
125
+ 36
126
+ ],
127
+ "y": [
128
+ 37
129
+ ],
130
+ "z": [
131
+ 38
132
+ ],
133
+ "æ": [
134
+ 39
135
+ ],
136
+ "ç": [
137
+ 40
138
+ ],
139
+ "ð": [
140
+ 41
141
+ ],
142
+ "ø": [
143
+ 42
144
+ ],
145
+ "ħ": [
146
+ 43
147
+ ],
148
+ "ŋ": [
149
+ 44
150
+ ],
151
+ "œ": [
152
+ 45
153
+ ],
154
+ "ǀ": [
155
+ 46
156
+ ],
157
+ "ǁ": [
158
+ 47
159
+ ],
160
+ "ǂ": [
161
+ 48
162
+ ],
163
+ "ǃ": [
164
+ 49
165
+ ],
166
+ "ɐ": [
167
+ 50
168
+ ],
169
+ "ɑ": [
170
+ 51
171
+ ],
172
+ "ɒ": [
173
+ 52
174
+ ],
175
+ "ɓ": [
176
+ 53
177
+ ],
178
+ "ɔ": [
179
+ 54
180
+ ],
181
+ "ɕ": [
182
+ 55
183
+ ],
184
+ "ɖ": [
185
+ 56
186
+ ],
187
+ "ɗ": [
188
+ 57
189
+ ],
190
+ "ɘ": [
191
+ 58
192
+ ],
193
+ "ə": [
194
+ 59
195
+ ],
196
+ "ɚ": [
197
+ 60
198
+ ],
199
+ "ɛ": [
200
+ 61
201
+ ],
202
+ "ɜ": [
203
+ 62
204
+ ],
205
+ "ɞ": [
206
+ 63
207
+ ],
208
+ "ɟ": [
209
+ 64
210
+ ],
211
+ "ɠ": [
212
+ 65
213
+ ],
214
+ "ɡ": [
215
+ 66
216
+ ],
217
+ "ɢ": [
218
+ 67
219
+ ],
220
+ "ɣ": [
221
+ 68
222
+ ],
223
+ "ɤ": [
224
+ 69
225
+ ],
226
+ "ɥ": [
227
+ 70
228
+ ],
229
+ "ɦ": [
230
+ 71
231
+ ],
232
+ "ɧ": [
233
+ 72
234
+ ],
235
+ "ɨ": [
236
+ 73
237
+ ],
238
+ "ɪ": [
239
+ 74
240
+ ],
241
+ "ɫ": [
242
+ 75
243
+ ],
244
+ "ɬ": [
245
+ 76
246
+ ],
247
+ "ɭ": [
248
+ 77
249
+ ],
250
+ "ɮ": [
251
+ 78
252
+ ],
253
+ "ɯ": [
254
+ 79
255
+ ],
256
+ "ɰ": [
257
+ 80
258
+ ],
259
+ "ɱ": [
260
+ 81
261
+ ],
262
+ "ɲ": [
263
+ 82
264
+ ],
265
+ "ɳ": [
266
+ 83
267
+ ],
268
+ "ɴ": [
269
+ 84
270
+ ],
271
+ "ɵ": [
272
+ 85
273
+ ],
274
+ "ɶ": [
275
+ 86
276
+ ],
277
+ "ɸ": [
278
+ 87
279
+ ],
280
+ "ɹ": [
281
+ 88
282
+ ],
283
+ "ɺ": [
284
+ 89
285
+ ],
286
+ "ɻ": [
287
+ 90
288
+ ],
289
+ "ɽ": [
290
+ 91
291
+ ],
292
+ "ɾ": [
293
+ 92
294
+ ],
295
+ "ʀ": [
296
+ 93
297
+ ],
298
+ "ʁ": [
299
+ 94
300
+ ],
301
+ "ʂ": [
302
+ 95
303
+ ],
304
+ "ʃ": [
305
+ 96
306
+ ],
307
+ "ʄ": [
308
+ 97
309
+ ],
310
+ "ʈ": [
311
+ 98
312
+ ],
313
+ "ʉ": [
314
+ 99
315
+ ],
316
+ "ʊ": [
317
+ 100
318
+ ],
319
+ "ʋ": [
320
+ 101
321
+ ],
322
+ "ʌ": [
323
+ 102
324
+ ],
325
+ "ʍ": [
326
+ 103
327
+ ],
328
+ "ʎ": [
329
+ 104
330
+ ],
331
+ "ʏ": [
332
+ 105
333
+ ],
334
+ "ʐ": [
335
+ 106
336
+ ],
337
+ "ʑ": [
338
+ 107
339
+ ],
340
+ "ʒ": [
341
+ 108
342
+ ],
343
+ "ʔ": [
344
+ 109
345
+ ],
346
+ "ʕ": [
347
+ 110
348
+ ],
349
+ "ʘ": [
350
+ 111
351
+ ],
352
+ "ʙ": [
353
+ 112
354
+ ],
355
+ "ʛ": [
356
+ 113
357
+ ],
358
+ "ʜ": [
359
+ 114
360
+ ],
361
+ "ʝ": [
362
+ 115
363
+ ],
364
+ "ʟ": [
365
+ 116
366
+ ],
367
+ "ʡ": [
368
+ 117
369
+ ],
370
+ "ʢ": [
371
+ 118
372
+ ],
373
+ "ʲ": [
374
+ 119
375
+ ],
376
+ "ˈ": [
377
+ 120
378
+ ],
379
+ "ˌ": [
380
+ 121
381
+ ],
382
+ "ː": [
383
+ 122
384
+ ],
385
+ "ˑ": [
386
+ 123
387
+ ],
388
+ "˞": [
389
+ 124
390
+ ],
391
+ "β": [
392
+ 125
393
+ ],
394
+ "θ": [
395
+ 126
396
+ ],
397
+ "χ": [
398
+ 127
399
+ ],
400
+ "ᵻ": [
401
+ 128
402
+ ],
403
+ "ⱱ": [
404
+ 129
405
+ ],
406
+ "0": [
407
+ 130
408
+ ],
409
+ "1": [
410
+ 131
411
+ ],
412
+ "2": [
413
+ 132
414
+ ],
415
+ "3": [
416
+ 133
417
+ ],
418
+ "4": [
419
+ 134
420
+ ],
421
+ "5": [
422
+ 135
423
+ ],
424
+ "6": [
425
+ 136
426
+ ],
427
+ "7": [
428
+ 137
429
+ ],
430
+ "8": [
431
+ 138
432
+ ],
433
+ "9": [
434
+ 139
435
+ ],
436
+ "̧": [
437
+ 140
438
+ ],
439
+ "̃": [
440
+ 141
441
+ ],
442
+ "̪": [
443
+ 142
444
+ ],
445
+ "̯": [
446
+ 143
447
+ ],
448
+ "̩": [
449
+ 144
450
+ ],
451
+ "ʰ": [
452
+ 145
453
+ ],
454
+ "ˤ": [
455
+ 146
456
+ ],
457
+ "ε": [
458
+ 147
459
+ ],
460
+ "↓": [
461
+ 148
462
+ ],
463
+ "#": [
464
+ 149
465
+ ],
466
+ "\"": [
467
+ 150
468
+ ],
469
+ "↑": [
470
+ 151
471
+ ],
472
+ "̺": [
473
+ 152
474
+ ],
475
+ "̻": [
476
+ 153
477
+ ]
478
+ },
479
+ "num_symbols": 256,
480
+ "num_speakers": 1,
481
+ "speaker_id_map": {},
482
+ "piper_version": "1.0.0"
483
+ }
en/en_GB/alan/medium/dataset.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65d7038e32bb936fc790a754caf46f35f6f1b6bfe9e896418aebae947033dfb
3
+ size 289013
en/en_GB/alan/medium/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270a7854dad3ee2f2fc24f3d8d12554c10c2d93b8207f1b5ac48d634cedb5532
3
+ size 35094574
en/en_GB/alan/medium/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8618d590d453df8a30edaef9b40c62d6db56820ee720784b23f31d62f96d0ea
3
+ size 19481425
en/en_GB/alan/medium/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7dcd8ec0c0085e7101e11a6073222a6f2309b9e3f66daf2a456d6c8244ea3a5
3
+ size 20061137
en/en_GB/alan/medium/encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9f7c6187b71154087580a891ea67e79e55b0964a5be2a8aaaff8c64843ac23
3
+ size 28418242
en/en_GB/alan/medium/epoch=6339-step=1647790.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b80d6d668b2c6ec359606e30b4d079c6423dde9cddd7165febf94e83414a37
3
+ size 845898392
en/en_GB/alan/medium/train.sh ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ set -eo pipefail
3
+
4
+ this_dir="$( cd "$( dirname "$0" )" && pwd )"
5
+ repo_dir="$(realpath "${this_dir}/../../../../")"
6
+
7
+ export PYTHONPATH="${repo_dir}/src/python:${PYTHONPATH}"
8
+ python3 -m piper_train \
9
+ --dataset-dir "${this_dir}" \
10
+ --accelerator 'gpu' \
11
+ --devices 1 \
12
+ --batch-size 64 \
13
+ --validation-split 0 \
14
+ --num-test-examples 0 \
15
+ --max_epochs 10000 \
16
+ --checkpoint-epochs 10 \
17
+ --precision 32 "$@"
en/en_GB/alba/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for alba (medium)
2
+
3
+ * Language: en_GB (English, Great Britain)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://datashare.ed.ac.uk/handle/10283/3270
11
+ * License: https://creativecommons.org/licenses/by/4.0/
12
+
13
+ ## Training
14
+
15
+ Finetuned from U.S. English lessac voice (medium quality).
en/en_GB/alba/medium/config.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "en-gb-x-rp"
7
+ },
8
+ "inference": {
9
+ "noise_scale": 0.667,
10
+ "length_scale": 1,
11
+ "noise_w": 0.8
12
+ },
13
+ "phoneme_type": "espeak",
14
+ "phoneme_map": {},
15
+ "phoneme_id_map": {
16
+ "_": [
17
+ 0
18
+ ],
19
+ "^": [
20
+ 1
21
+ ],
22
+ "$": [
23
+ 2
24
+ ],
25
+ " ": [
26
+ 3
27
+ ],
28
+ "!": [
29
+ 4
30
+ ],
31
+ "'": [
32
+ 5
33
+ ],
34
+ "(": [
35
+ 6
36
+ ],
37
+ ")": [
38
+ 7
39
+ ],
40
+ ",": [
41
+ 8
42
+ ],
43
+ "-": [
44
+ 9
45
+ ],
46
+ ".": [
47
+ 10
48
+ ],
49
+ ":": [
50
+ 11
51
+ ],
52
+ ";": [
53
+ 12
54
+ ],
55
+ "?": [
56
+ 13
57
+ ],
58
+ "a": [
59
+ 14
60
+ ],
61
+ "b": [
62
+ 15
63
+ ],
64
+ "c": [
65
+ 16
66
+ ],
67
+ "d": [
68
+ 17
69
+ ],
70
+ "e": [
71
+ 18
72
+ ],
73
+ "f": [
74
+ 19
75
+ ],
76
+ "h": [
77
+ 20
78
+ ],
79
+ "i": [
80
+ 21
81
+ ],
82
+ "j": [
83
+ 22
84
+ ],
85
+ "k": [
86
+ 23
87
+ ],
88
+ "l": [
89
+ 24
90
+ ],
91
+ "m": [
92
+ 25
93
+ ],
94
+ "n": [
95
+ 26
96
+ ],
97
+ "o": [
98
+ 27
99
+ ],
100
+ "p": [
101
+ 28
102
+ ],
103
+ "q": [
104
+ 29
105
+ ],
106
+ "r": [
107
+ 30
108
+ ],
109
+ "s": [
110
+ 31
111
+ ],
112
+ "t": [
113
+ 32
114
+ ],
115
+ "u": [
116
+ 33
117
+ ],
118
+ "v": [
119
+ 34
120
+ ],
121
+ "w": [
122
+ 35
123
+ ],
124
+ "x": [
125
+ 36
126
+ ],
127
+ "y": [
128
+ 37
129
+ ],
130
+ "z": [
131
+ 38
132
+ ],
133
+ "æ": [
134
+ 39
135
+ ],
136
+ "ç": [
137
+ 40
138
+ ],
139
+ "ð": [
140
+ 41
141
+ ],
142
+ "ø": [
143
+ 42
144
+ ],
145
+ "ħ": [
146
+ 43
147
+ ],
148
+ "ŋ": [
149
+ 44
150
+ ],
151
+ "œ": [
152
+ 45
153
+ ],
154
+ "ǀ": [
155
+ 46
156
+ ],
157
+ "ǁ": [
158
+ 47
159
+ ],
160
+ "ǂ": [
161
+ 48
162
+ ],
163
+ "ǃ": [
164
+ 49
165
+ ],
166
+ "ɐ": [
167
+ 50
168
+ ],
169
+ "ɑ": [
170
+ 51
171
+ ],
172
+ "ɒ": [
173
+ 52
174
+ ],
175
+ "ɓ": [
176
+ 53
177
+ ],
178
+ "ɔ": [
179
+ 54
180
+ ],
181
+ "ɕ": [
182
+ 55
183
+ ],
184
+ "ɖ": [
185
+ 56
186
+ ],
187
+ "ɗ": [
188
+ 57
189
+ ],
190
+ "ɘ": [
191
+ 58
192
+ ],
193
+ "ə": [
194
+ 59
195
+ ],
196
+ "ɚ": [
197
+ 60
198
+ ],
199
+ "ɛ": [
200
+ 61
201
+ ],
202
+ "ɜ": [
203
+ 62
204
+ ],
205
+ "ɞ": [
206
+ 63
207
+ ],
208
+ "ɟ": [
209
+ 64
210
+ ],
211
+ "ɠ": [
212
+ 65
213
+ ],
214
+ "ɡ": [
215
+ 66
216
+ ],
217
+ "ɢ": [
218
+ 67
219
+ ],
220
+ "ɣ": [
221
+ 68
222
+ ],
223
+ "ɤ": [
224
+ 69
225
+ ],
226
+ "ɥ": [
227
+ 70
228
+ ],
229
+ "ɦ": [
230
+ 71
231
+ ],
232
+ "ɧ": [
233
+ 72
234
+ ],
235
+ "ɨ": [
236
+ 73
237
+ ],
238
+ "ɪ": [
239
+ 74
240
+ ],
241
+ "ɫ": [
242
+ 75
243
+ ],
244
+ "ɬ": [
245
+ 76
246
+ ],
247
+ "ɭ": [
248
+ 77
249
+ ],
250
+ "ɮ": [
251
+ 78
252
+ ],
253
+ "ɯ": [
254
+ 79
255
+ ],
256
+ "ɰ": [
257
+ 80
258
+ ],
259
+ "ɱ": [
260
+ 81
261
+ ],
262
+ "ɲ": [
263
+ 82
264
+ ],
265
+ "ɳ": [
266
+ 83
267
+ ],
268
+ "ɴ": [
269
+ 84
270
+ ],
271
+ "ɵ": [
272
+ 85
273
+ ],
274
+ "ɶ": [
275
+ 86
276
+ ],
277
+ "ɸ": [
278
+ 87
279
+ ],
280
+ "ɹ": [
281
+ 88
282
+ ],
283
+ "ɺ": [
284
+ 89
285
+ ],
286
+ "ɻ": [
287
+ 90
288
+ ],
289
+ "ɽ": [
290
+ 91
291
+ ],
292
+ "ɾ": [
293
+ 92
294
+ ],
295
+ "ʀ": [
296
+ 93
297
+ ],
298
+ "ʁ": [
299
+ 94
300
+ ],
301
+ "ʂ": [
302
+ 95
303
+ ],
304
+ "ʃ": [
305
+ 96
306
+ ],
307
+ "ʄ": [
308
+ 97
309
+ ],
310
+ "ʈ": [
311
+ 98
312
+ ],
313
+ "ʉ": [
314
+ 99
315
+ ],
316
+ "ʊ": [
317
+ 100
318
+ ],
319
+ "ʋ": [
320
+ 101
321
+ ],
322
+ "ʌ": [
323
+ 102
324
+ ],
325
+ "ʍ": [
326
+ 103
327
+ ],
328
+ "ʎ": [
329
+ 104
330
+ ],
331
+ "ʏ": [
332
+ 105
333
+ ],
334
+ "ʐ": [
335
+ 106
336
+ ],
337
+ "ʑ": [
338
+ 107
339
+ ],
340
+ "ʒ": [
341
+ 108
342
+ ],
343
+ "ʔ": [
344
+ 109
345
+ ],
346
+ "ʕ": [
347
+ 110
348
+ ],
349
+ "ʘ": [
350
+ 111
351
+ ],
352
+ "ʙ": [
353
+ 112
354
+ ],
355
+ "ʛ": [
356
+ 113
357
+ ],
358
+ "ʜ": [
359
+ 114
360
+ ],
361
+ "ʝ": [
362
+ 115
363
+ ],
364
+ "ʟ": [
365
+ 116
366
+ ],
367
+ "ʡ": [
368
+ 117
369
+ ],
370
+ "ʢ": [
371
+ 118
372
+ ],
373
+ "ʲ": [
374
+ 119
375
+ ],
376
+ "ˈ": [
377
+ 120
378
+ ],
379
+ "ˌ": [
380
+ 121
381
+ ],
382
+ "ː": [
383
+ 122
384
+ ],
385
+ "ˑ": [
386
+ 123
387
+ ],
388
+ "˞": [
389
+ 124
390
+ ],
391
+ "β": [
392
+ 125
393
+ ],
394
+ "θ": [
395
+ 126
396
+ ],
397
+ "χ": [
398
+ 127
399
+ ],
400
+ "ᵻ": [
401
+ 128
402
+ ],
403
+ "ⱱ": [
404
+ 129
405
+ ],
406
+ "0": [
407
+ 130
408
+ ],
409
+ "1": [
410
+ 131
411
+ ],
412
+ "2": [
413
+ 132
414
+ ],
415
+ "3": [
416
+ 133
417
+ ],
418
+ "4": [
419
+ 134
420
+ ],
421
+ "5": [
422
+ 135
423
+ ],
424
+ "6": [
425
+ 136
426
+ ],
427
+ "7": [
428
+ 137
429
+ ],
430
+ "8": [
431
+ 138
432
+ ],
433
+ "9": [
434
+ 139
435
+ ],
436
+ "̧": [
437
+ 140
438
+ ],
439
+ "̃": [
440
+ 141
441
+ ],
442
+ "̪": [
443
+ 142
444
+ ],
445
+ "̯": [
446
+ 143
447
+ ],
448
+ "̩": [
449
+ 144
450
+ ],
451
+ "ʰ": [
452
+ 145
453
+ ],
454
+ "ˤ": [
455
+ 146
456
+ ],
457
+ "ε": [
458
+ 147
459
+ ],
460
+ "↓": [
461
+ 148
462
+ ],
463
+ "#": [
464
+ 149
465
+ ],
466
+ "\"": [
467
+ 150
468
+ ],
469
+ "↑": [
470
+ 151
471
+ ],
472
+ "̺": [
473
+ 152
474
+ ],
475
+ "̻": [
476
+ 153
477
+ ]
478
+ },
479
+ "num_symbols": 256,
480
+ "num_speakers": 1,
481
+ "speaker_id_map": {},
482
+ "piper_version": "1.0.0"
483
+ }
en/en_GB/alba/medium/dataset.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335113e2a147b79dda353a74ea91132417a7ff9bf206fc12f0296735708597f6
3
+ size 747160
en/en_GB/alba/medium/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccd699b7a10bfe8281fc6c19bb39a9ebe973846557da19554535fef97d0a0f2
3
+ size 35094574
en/en_GB/alba/medium/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a6655f3047e0100399fe1578824de0007771969480a955d94fde373ed348dc
3
+ size 19481425
en/en_GB/alba/medium/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc3027f2d5c501747c87398ec838c3072fa7cba1ecfbd92894d192829c0ef52
3
+ size 20061137
en/en_GB/alba/medium/encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46972f2a8c0cc301b7c2b1008b9934baf115d4e216593239814960927cea3b6d
3
+ size 28418242
en/en_GB/alba/medium/epoch=4179-step=2101090.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1ed5167e20860ab465447825522df20edfda6e8c73494db8fc87db6f79fe53
3
+ size 845898392
en/en_GB/alba/medium/train.sh ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ set -eo pipefail
3
+
4
+ this_dir="$( cd "$( dirname "$0" )" && pwd )"
5
+ repo_dir="$(realpath "${this_dir}/../../../../")"
6
+
7
+ export PYTHONPATH="${repo_dir}/src/python:${PYTHONPATH}"
8
+ python3 -m piper_train \
9
+ --dataset-dir "${this_dir}" \
10
+ --accelerator 'gpu' \
11
+ --devices 1 \
12
+ --batch-size 25 \
13
+ --validation-split 0 \
14
+ --num-test-examples 0 \
15
+ --max_epochs 10000 \
16
+ --checkpoint-epochs 10 \
17
+ --precision 32 "$@"
en/en_GB/aru/medium/LICENSE ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Carnegie Mellon University
2
+ Copyright (c) 2003
3
+ All Rights Reserved.
4
+
5
+ Permission to use, copy, modify, and license this software and its
6
+ documentation for any purpose, is hereby granted without fee,
7
+ subject to the following conditions:
8
+ 1. The code must retain the above copyright notice, this list of
9
+ conditions and the following disclaimer.
10
+ 2. Any modifications must be clearly marked as such.
11
+ 3. Original authors' names are not deleted.
12
+
13
+ THE AUTHORS OF THIS WORK DISCLAIM ALL WARRANTIES WITH REGARD TO
14
+ THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
15
+ AND FITNESS, IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY
16
+ SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
17
+ WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
18
+ AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
19
+ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
20
+ THIS SOFTWARE.
en/en_GB/aru/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for aru (medium)
2
+
3
+ * Language: en_GB (English, Great Britain)
4
+ * Speakers: 12
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://www.liverpool.ac.uk/architecture/research/acoustics-research-unit/speech-corpus/
11
+ * License: https://creativecommons.org/licenses/by/4.0/
12
+
13
+ ## Training
14
+
15
+ Finetuned from U.S. English lessac voice (medium quality).
en/en_GB/aru/medium/config.json ADDED
@@ -0,0 +1,496 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "en-gb-x-rp"
7
+ },
8
+ "inference": {
9
+ "noise_scale": 0.667,
10
+ "length_scale": 1,
11
+ "noise_w": 0.8
12
+ },
13
+ "phoneme_type": "espeak",
14
+ "phoneme_map": {},
15
+ "phoneme_id_map": {
16
+ "_": [
17
+ 0
18
+ ],
19
+ "^": [
20
+ 1
21
+ ],
22
+ "$": [
23
+ 2
24
+ ],
25
+ " ": [
26
+ 3
27
+ ],
28
+ "!": [
29
+ 4
30
+ ],
31
+ "'": [
32
+ 5
33
+ ],
34
+ "(": [
35
+ 6
36
+ ],
37
+ ")": [
38
+ 7
39
+ ],
40
+ ",": [
41
+ 8
42
+ ],
43
+ "-": [
44
+ 9
45
+ ],
46
+ ".": [
47
+ 10
48
+ ],
49
+ ":": [
50
+ 11
51
+ ],
52
+ ";": [
53
+ 12
54
+ ],
55
+ "?": [
56
+ 13
57
+ ],
58
+ "a": [
59
+ 14
60
+ ],
61
+ "b": [
62
+ 15
63
+ ],
64
+ "c": [
65
+ 16
66
+ ],
67
+ "d": [
68
+ 17
69
+ ],
70
+ "e": [
71
+ 18
72
+ ],
73
+ "f": [
74
+ 19
75
+ ],
76
+ "h": [
77
+ 20
78
+ ],
79
+ "i": [
80
+ 21
81
+ ],
82
+ "j": [
83
+ 22
84
+ ],
85
+ "k": [
86
+ 23
87
+ ],
88
+ "l": [
89
+ 24
90
+ ],
91
+ "m": [
92
+ 25
93
+ ],
94
+ "n": [
95
+ 26
96
+ ],
97
+ "o": [
98
+ 27
99
+ ],
100
+ "p": [
101
+ 28
102
+ ],
103
+ "q": [
104
+ 29
105
+ ],
106
+ "r": [
107
+ 30
108
+ ],
109
+ "s": [
110
+ 31
111
+ ],
112
+ "t": [
113
+ 32
114
+ ],
115
+ "u": [
116
+ 33
117
+ ],
118
+ "v": [
119
+ 34
120
+ ],
121
+ "w": [
122
+ 35
123
+ ],
124
+ "x": [
125
+ 36
126
+ ],
127
+ "y": [
128
+ 37
129
+ ],
130
+ "z": [
131
+ 38
132
+ ],
133
+ "æ": [
134
+ 39
135
+ ],
136
+ "ç": [
137
+ 40
138
+ ],
139
+ "ð": [
140
+ 41
141
+ ],
142
+ "ø": [
143
+ 42
144
+ ],
145
+ "ħ": [
146
+ 43
147
+ ],
148
+ "ŋ": [
149
+ 44
150
+ ],
151
+ "œ": [
152
+ 45
153
+ ],
154
+ "ǀ": [
155
+ 46
156
+ ],
157
+ "ǁ": [
158
+ 47
159
+ ],
160
+ "ǂ": [
161
+ 48
162
+ ],
163
+ "ǃ": [
164
+ 49
165
+ ],
166
+ "ɐ": [
167
+ 50
168
+ ],
169
+ "ɑ": [
170
+ 51
171
+ ],
172
+ "ɒ": [
173
+ 52
174
+ ],
175
+ "ɓ": [
176
+ 53
177
+ ],
178
+ "ɔ": [
179
+ 54
180
+ ],
181
+ "ɕ": [
182
+ 55
183
+ ],
184
+ "ɖ": [
185
+ 56
186
+ ],
187
+ "ɗ": [
188
+ 57
189
+ ],
190
+ "ɘ": [
191
+ 58
192
+ ],
193
+ "ə": [
194
+ 59
195
+ ],
196
+ "ɚ": [
197
+ 60
198
+ ],
199
+ "ɛ": [
200
+ 61
201
+ ],
202
+ "ɜ": [
203
+ 62
204
+ ],
205
+ "ɞ": [
206
+ 63
207
+ ],
208
+ "ɟ": [
209
+ 64
210
+ ],
211
+ "ɠ": [
212
+ 65
213
+ ],
214
+ "ɡ": [
215
+ 66
216
+ ],
217
+ "ɢ": [
218
+ 67
219
+ ],
220
+ "ɣ": [
221
+ 68
222
+ ],
223
+ "ɤ": [
224
+ 69
225
+ ],
226
+ "ɥ": [
227
+ 70
228
+ ],
229
+ "ɦ": [
230
+ 71
231
+ ],
232
+ "ɧ": [
233
+ 72
234
+ ],
235
+ "ɨ": [
236
+ 73
237
+ ],
238
+ "ɪ": [
239
+ 74
240
+ ],
241
+ "ɫ": [
242
+ 75
243
+ ],
244
+ "ɬ": [
245
+ 76
246
+ ],
247
+ "ɭ": [
248
+ 77
249
+ ],
250
+ "ɮ": [
251
+ 78
252
+ ],
253
+ "ɯ": [
254
+ 79
255
+ ],
256
+ "ɰ": [
257
+ 80
258
+ ],
259
+ "ɱ": [
260
+ 81
261
+ ],
262
+ "ɲ": [
263
+ 82
264
+ ],
265
+ "ɳ": [
266
+ 83
267
+ ],
268
+ "ɴ": [
269
+ 84
270
+ ],
271
+ "ɵ": [
272
+ 85
273
+ ],
274
+ "ɶ": [
275
+ 86
276
+ ],
277
+ "ɸ": [
278
+ 87
279
+ ],
280
+ "ɹ": [
281
+ 88
282
+ ],
283
+ "ɺ": [
284
+ 89
285
+ ],
286
+ "ɻ": [
287
+ 90
288
+ ],
289
+ "ɽ": [
290
+ 91
291
+ ],
292
+ "ɾ": [
293
+ 92
294
+ ],
295
+ "ʀ": [
296
+ 93
297
+ ],
298
+ "ʁ": [
299
+ 94
300
+ ],
301
+ "ʂ": [
302
+ 95
303
+ ],
304
+ "ʃ": [
305
+ 96
306
+ ],
307
+ "ʄ": [
308
+ 97
309
+ ],
310
+ "ʈ": [
311
+ 98
312
+ ],
313
+ "ʉ": [
314
+ 99
315
+ ],
316
+ "ʊ": [
317
+ 100
318
+ ],
319
+ "ʋ": [
320
+ 101
321
+ ],
322
+ "ʌ": [
323
+ 102
324
+ ],
325
+ "ʍ": [
326
+ 103
327
+ ],
328
+ "ʎ": [
329
+ 104
330
+ ],
331
+ "ʏ": [
332
+ 105
333
+ ],
334
+ "ʐ": [
335
+ 106
336
+ ],
337
+ "ʑ": [
338
+ 107
339
+ ],
340
+ "ʒ": [
341
+ 108
342
+ ],
343
+ "ʔ": [
344
+ 109
345
+ ],
346
+ "ʕ": [
347
+ 110
348
+ ],
349
+ "ʘ": [
350
+ 111
351
+ ],
352
+ "ʙ": [
353
+ 112
354
+ ],
355
+ "ʛ": [
356
+ 113
357
+ ],
358
+ "ʜ": [
359
+ 114
360
+ ],
361
+ "ʝ": [
362
+ 115
363
+ ],
364
+ "ʟ": [
365
+ 116
366
+ ],
367
+ "ʡ": [
368
+ 117
369
+ ],
370
+ "ʢ": [
371
+ 118
372
+ ],
373
+ "ʲ": [
374
+ 119
375
+ ],
376
+ "ˈ": [
377
+ 120
378
+ ],
379
+ "ˌ": [
380
+ 121
381
+ ],
382
+ "ː": [
383
+ 122
384
+ ],
385
+ "ˑ": [
386
+ 123
387
+ ],
388
+ "˞": [
389
+ 124
390
+ ],
391
+ "β": [
392
+ 125
393
+ ],
394
+ "θ": [
395
+ 126
396
+ ],
397
+ "χ": [
398
+ 127
399
+ ],
400
+ "ᵻ": [
401
+ 128
402
+ ],
403
+ "ⱱ": [
404
+ 129
405
+ ],
406
+ "0": [
407
+ 130
408
+ ],
409
+ "1": [
410
+ 131
411
+ ],
412
+ "2": [
413
+ 132
414
+ ],
415
+ "3": [
416
+ 133
417
+ ],
418
+ "4": [
419
+ 134
420
+ ],
421
+ "5": [
422
+ 135
423
+ ],
424
+ "6": [
425
+ 136
426
+ ],
427
+ "7": [
428
+ 137
429
+ ],
430
+ "8": [
431
+ 138
432
+ ],
433
+ "9": [
434
+ 139
435
+ ],
436
+ "̧": [
437
+ 140
438
+ ],
439
+ "̃": [
440
+ 141
441
+ ],
442
+ "̪": [
443
+ 142
444
+ ],
445
+ "̯": [
446
+ 143
447
+ ],
448
+ "̩": [
449
+ 144
450
+ ],
451
+ "ʰ": [
452
+ 145
453
+ ],
454
+ "ˤ": [
455
+ 146
456
+ ],
457
+ "ε": [
458
+ 147
459
+ ],
460
+ "↓": [
461
+ 148
462
+ ],
463
+ "#": [
464
+ 149
465
+ ],
466
+ "\"": [
467
+ 150
468
+ ],
469
+ "↑": [
470
+ 151
471
+ ],
472
+ "̺": [
473
+ 152
474
+ ],
475
+ "̻": [
476
+ 153
477
+ ]
478
+ },
479
+ "num_symbols": 256,
480
+ "num_speakers": 12,
481
+ "speaker_id_map": {
482
+ "03": 0,
483
+ "06": 1,
484
+ "10": 2,
485
+ "01": 3,
486
+ "09": 4,
487
+ "08": 5,
488
+ "11": 6,
489
+ "05": 7,
490
+ "12": 8,
491
+ "02": 9,
492
+ "07": 10,
493
+ "04": 11
494
+ },
495
+ "piper_version": "1.0.0"
496
+ }
en/en_GB/aru/medium/dataset.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b189398a59fa935f374a3a822fc0d4f525a6e5b10cbc192865b1bdecc471a4
3
+ size 1252160
en/en_GB/aru/medium/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780dd02cf1b8227d13e3b77aaaecdca7017a068dd0312690e6ab38116f1e3485
3
+ size 48235922
en/en_GB/aru/medium/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d85ab5b24f7ef2f5371b1976991f6a64166983a4d50eb1edb0ced401a1348c3
3
+ size 26162159
en/en_GB/aru/medium/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcc8333b8836b5cd636f22667f52428d3594ab8f90fa62aa1be81709ed73f6e
3
+ size 26837231
en/en_GB/aru/medium/encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72b29eec81172cc606dde26c4d13f61e375061f205d0a705e7789e290bb4a9d
3
+ size 28837460
en/en_GB/aru/medium/epoch=3479-step=939600.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3186419f2312e3d761d3c0f4e805208e221cf2887765b7fdd8e75789fb21555
3
+ size 924537864
en/en_GB/aru/medium/train.sh ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ set -eo pipefail
3
+
4
+ this_dir="$( cd "$( dirname "$0" )" && pwd )"
5
+ repo_dir="$(realpath "${this_dir}/../../../../")"
6
+
7
+ export PYTHONPATH="${repo_dir}/src/python:${PYTHONPATH}"
8
+ python3 -m piper_train \
9
+ --dataset-dir "${this_dir}" \
10
+ --accelerator 'gpu' \
11
+ --devices 1 \
12
+ --batch-size 64 \
13
+ --validation-split 0 \
14
+ --num-test-examples 0 \
15
+ --max_epochs 10000 \
16
+ --checkpoint-epochs 10 \
17
+ --precision 32 "$@"
en/en_GB/cori/high/MODEL_CARD ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for cori (high)
2
+
3
+ * Language: en_GB (English, Great Britain)
4
+ * Speakers: 1
5
+ * Quality: high
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://librivox.org
11
+ * License: public domain
12
+
13
+ ## Training
14
+
15
+ See: https://brycebeattie.com/files/tts/
16
+
17
+ UK English female voice. Single Speaker. Trained from scratch on high quality settings for 500 epochs. I put together the dataset, which ended up with about 24 hours of recordings. All recordings came from LibriVox.org.
en/en_GB/cori/high/config.json ADDED
@@ -0,0 +1,497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "cori",
3
+ "audio": {
4
+ "sample_rate": 22050,
5
+ "quality": "high"
6
+ },
7
+ "espeak": {
8
+ "voice": "en"
9
+ },
10
+ "language": {
11
+ "code": "en_GB"
12
+ },
13
+ "inference": {
14
+ "noise_scale": 0.667,
15
+ "length_scale": 1,
16
+ "noise_w": 0.8
17
+ },
18
+ "phoneme_type": "espeak",
19
+ "phoneme_map": {},
20
+ "phoneme_id_map": {
21
+ " ": [
22
+ 3
23
+ ],
24
+ "!": [
25
+ 4
26
+ ],
27
+ "\"": [
28
+ 150
29
+ ],
30
+ "#": [
31
+ 149
32
+ ],
33
+ "$": [
34
+ 2
35
+ ],
36
+ "'": [
37
+ 5
38
+ ],
39
+ "(": [
40
+ 6
41
+ ],
42
+ ")": [
43
+ 7
44
+ ],
45
+ ",": [
46
+ 8
47
+ ],
48
+ "-": [
49
+ 9
50
+ ],
51
+ ".": [
52
+ 10
53
+ ],
54
+ "0": [
55
+ 130
56
+ ],
57
+ "1": [
58
+ 131
59
+ ],
60
+ "2": [
61
+ 132
62
+ ],
63
+ "3": [
64
+ 133
65
+ ],
66
+ "4": [
67
+ 134
68
+ ],
69
+ "5": [
70
+ 135
71
+ ],
72
+ "6": [
73
+ 136
74
+ ],
75
+ "7": [
76
+ 137
77
+ ],
78
+ "8": [
79
+ 138
80
+ ],
81
+ "9": [
82
+ 139
83
+ ],
84
+ ":": [
85
+ 11
86
+ ],
87
+ ";": [
88
+ 12
89
+ ],
90
+ "?": [
91
+ 13
92
+ ],
93
+ "X": [
94
+ 156
95
+ ],
96
+ "^": [
97
+ 1
98
+ ],
99
+ "_": [
100
+ 0
101
+ ],
102
+ "a": [
103
+ 14
104
+ ],
105
+ "b": [
106
+ 15
107
+ ],
108
+ "c": [
109
+ 16
110
+ ],
111
+ "d": [
112
+ 17
113
+ ],
114
+ "e": [
115
+ 18
116
+ ],
117
+ "f": [
118
+ 19
119
+ ],
120
+ "g": [
121
+ 154
122
+ ],
123
+ "h": [
124
+ 20
125
+ ],
126
+ "i": [
127
+ 21
128
+ ],
129
+ "j": [
130
+ 22
131
+ ],
132
+ "k": [
133
+ 23
134
+ ],
135
+ "l": [
136
+ 24
137
+ ],
138
+ "m": [
139
+ 25
140
+ ],
141
+ "n": [
142
+ 26
143
+ ],
144
+ "o": [
145
+ 27
146
+ ],
147
+ "p": [
148
+ 28
149
+ ],
150
+ "q": [
151
+ 29
152
+ ],
153
+ "r": [
154
+ 30
155
+ ],
156
+ "s": [
157
+ 31
158
+ ],
159
+ "t": [
160
+ 32
161
+ ],
162
+ "u": [
163
+ 33
164
+ ],
165
+ "v": [
166
+ 34
167
+ ],
168
+ "w": [
169
+ 35
170
+ ],
171
+ "x": [
172
+ 36
173
+ ],
174
+ "y": [
175
+ 37
176
+ ],
177
+ "z": [
178
+ 38
179
+ ],
180
+ "æ": [
181
+ 39
182
+ ],
183
+ "ç": [
184
+ 40
185
+ ],
186
+ "ð": [
187
+ 41
188
+ ],
189
+ "ø": [
190
+ 42
191
+ ],
192
+ "ħ": [
193
+ 43
194
+ ],
195
+ "ŋ": [
196
+ 44
197
+ ],
198
+ "œ": [
199
+ 45
200
+ ],
201
+ "ǀ": [
202
+ 46
203
+ ],
204
+ "ǁ": [
205
+ 47
206
+ ],
207
+ "ǂ": [
208
+ 48
209
+ ],
210
+ "ǃ": [
211
+ 49
212
+ ],
213
+ "ɐ": [
214
+ 50
215
+ ],
216
+ "ɑ": [
217
+ 51
218
+ ],
219
+ "ɒ": [
220
+ 52
221
+ ],
222
+ "ɓ": [
223
+ 53
224
+ ],
225
+ "ɔ": [
226
+ 54
227
+ ],
228
+ "ɕ": [
229
+ 55
230
+ ],
231
+ "ɖ": [
232
+ 56
233
+ ],
234
+ "ɗ": [
235
+ 57
236
+ ],
237
+ "ɘ": [
238
+ 58
239
+ ],
240
+ "ə": [
241
+ 59
242
+ ],
243
+ "ɚ": [
244
+ 60
245
+ ],
246
+ "ɛ": [
247
+ 61
248
+ ],
249
+ "ɜ": [
250
+ 62
251
+ ],
252
+ "ɞ": [
253
+ 63
254
+ ],
255
+ "ɟ": [
256
+ 64
257
+ ],
258
+ "ɠ": [
259
+ 65
260
+ ],
261
+ "ɡ": [
262
+ 66
263
+ ],
264
+ "ɢ": [
265
+ 67
266
+ ],
267
+ "ɣ": [
268
+ 68
269
+ ],
270
+ "ɤ": [
271
+ 69
272
+ ],
273
+ "ɥ": [
274
+ 70
275
+ ],
276
+ "ɦ": [
277
+ 71
278
+ ],
279
+ "ɧ": [
280
+ 72
281
+ ],
282
+ "ɨ": [
283
+ 73
284
+ ],
285
+ "ɪ": [
286
+ 74
287
+ ],
288
+ "ɫ": [
289
+ 75
290
+ ],
291
+ "ɬ": [
292
+ 76
293
+ ],
294
+ "ɭ": [
295
+ 77
296
+ ],
297
+ "ɮ": [
298
+ 78
299
+ ],
300
+ "ɯ": [
301
+ 79
302
+ ],
303
+ "ɰ": [
304
+ 80
305
+ ],
306
+ "ɱ": [
307
+ 81
308
+ ],
309
+ "ɲ": [
310
+ 82
311
+ ],
312
+ "ɳ": [
313
+ 83
314
+ ],
315
+ "ɴ": [
316
+ 84
317
+ ],
318
+ "ɵ": [
319
+ 85
320
+ ],
321
+ "ɶ": [
322
+ 86
323
+ ],
324
+ "ɸ": [
325
+ 87
326
+ ],
327
+ "ɹ": [
328
+ 88
329
+ ],
330
+ "ɺ": [
331
+ 89
332
+ ],
333
+ "ɻ": [
334
+ 90
335
+ ],
336
+ "ɽ": [
337
+ 91
338
+ ],
339
+ "ɾ": [
340
+ 92
341
+ ],
342
+ "ʀ": [
343
+ 93
344
+ ],
345
+ "ʁ": [
346
+ 94
347
+ ],
348
+ "ʂ": [
349
+ 95
350
+ ],
351
+ "ʃ": [
352
+ 96
353
+ ],
354
+ "ʄ": [
355
+ 97
356
+ ],
357
+ "ʈ": [
358
+ 98
359
+ ],
360
+ "ʉ": [
361
+ 99
362
+ ],
363
+ "ʊ": [
364
+ 100
365
+ ],
366
+ "ʋ": [
367
+ 101
368
+ ],
369
+ "ʌ": [
370
+ 102
371
+ ],
372
+ "ʍ": [
373
+ 103
374
+ ],
375
+ "ʎ": [
376
+ 104
377
+ ],
378
+ "ʏ": [
379
+ 105
380
+ ],
381
+ "ʐ": [
382
+ 106
383
+ ],
384
+ "ʑ": [
385
+ 107
386
+ ],
387
+ "ʒ": [
388
+ 108
389
+ ],
390
+ "ʔ": [
391
+ 109
392
+ ],
393
+ "ʕ": [
394
+ 110
395
+ ],
396
+ "ʘ": [
397
+ 111
398
+ ],
399
+ "ʙ": [
400
+ 112
401
+ ],
402
+ "ʛ": [
403
+ 113
404
+ ],
405
+ "ʜ": [
406
+ 114
407
+ ],
408
+ "ʝ": [
409
+ 115
410
+ ],
411
+ "ʟ": [
412
+ 116
413
+ ],
414
+ "ʡ": [
415
+ 117
416
+ ],
417
+ "ʢ": [
418
+ 118
419
+ ],
420
+ "ʦ": [
421
+ 155
422
+ ],
423
+ "ʰ": [
424
+ 145
425
+ ],
426
+ "ʲ": [
427
+ 119
428
+ ],
429
+ "ˈ": [
430
+ 120
431
+ ],
432
+ "ˌ": [
433
+ 121
434
+ ],
435
+ "ː": [
436
+ 122
437
+ ],
438
+ "ˑ": [
439
+ 123
440
+ ],
441
+ "˞": [
442
+ 124
443
+ ],
444
+ "ˤ": [
445
+ 146
446
+ ],
447
+ "̃": [
448
+ 141
449
+ ],
450
+ "̧": [
451
+ 140
452
+ ],
453
+ "̩": [
454
+ 144
455
+ ],
456
+ "̪": [
457
+ 142
458
+ ],
459
+ "̯": [
460
+ 143
461
+ ],
462
+ "̺": [
463
+ 152
464
+ ],
465
+ "̻": [
466
+ 153
467
+ ],
468
+ "β": [
469
+ 125
470
+ ],
471
+ "ε": [
472
+ 147
473
+ ],
474
+ "θ": [
475
+ 126
476
+ ],
477
+ "χ": [
478
+ 127
479
+ ],
480
+ "ᵻ": [
481
+ 128
482
+ ],
483
+ "↑": [
484
+ 151
485
+ ],
486
+ "↓": [
487
+ 148
488
+ ],
489
+ "ⱱ": [
490
+ 129
491
+ ]
492
+ },
493
+ "num_symbols": 256,
494
+ "num_speakers": 1,
495
+ "speaker_id_map": {},
496
+ "piper_version": "1.0.0"
497
+ }
en/en_GB/cori/high/cori-high-500.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a700fbe4e5ec7e937226a02f1a761c3a8ad16074f138f920d2be4582565fb2
3
+ size 998156853
en/en_GB/cori/high/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71094c5498e4c21498d1184d12a25d42029fc7bac3fafb6c4a341a55ba9c922
3
+ size 85783473
en/en_GB/cori/high/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a28d4c0ea047d4f4285def69f51b4bf2b3665243ed7325b1b9040ea39baa55c2
3
+ size 46299025
en/en_GB/cori/high/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1a9287c6dcf189fee22ef7f2882f47246c4cdb889751318ad40e756a92c01a
3
+ size 50837457
en/en_GB/cori/high/encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e96a2e52d5fa84fb0004e762e31b03dd270e9ae5673bd202eae39745d8cd0fb0
3
+ size 28418256
en/en_GB/cori/medium/cori-med-640.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19af142f51b16ecd5953f21662f063a2401a41b19e6ae11f06909ad64517b1d
3
+ size 845889993
en/en_GB/cori/medium/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1fc55c54c3cd3a62ca999311c86b5cee80d00ef1626d0221628bd0176f4f67
3
+ size 35094574
en/en_GB/cori/medium/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e84fb9cfe1c50c739261b5df88c740392274c83189cb8365c3e9bb73deb40a
3
+ size 19481425
en/en_GB/cori/medium/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627fca864ea42bc735038b81b70ea01bf8f4f9aee7112a0d355c86aae567301f
3
+ size 20061137
en/en_GB/cori/medium/encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e48f526c05bccb71c0b036b3e51ed458bfb0524b0e0583c23be79f39b7fd736
3
+ size 28418242
en/en_GB/jenny_dioco/medium/LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ Attribution is required in software/websites/projects/interfaces (including voice interfaces) that generate audio in response to user action using this dataset. Atribution means: the voice must be referred to as "Jenny", and where at all practical, "Jenny (Dioco)". Attribution is not required when distributing the generated clips (although welcome). Commercial use is permitted. Don't do unfair things like claim the dataset is your own. No further restrictions apply.
en/en_GB/jenny_dioco/medium/MODEL_CARD ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model card for jenny_dioco (medium)
2
+
3
+ * Language: en_GB (English, Great Britain)
4
+ * Speakers: 1
5
+ * Quality: medium
6
+ * Samplerate: 22,050Hz
7
+
8
+ ## Dataset
9
+
10
+ * URL: https://github.com/dioco-group/jenny-tts-dataset
11
+ * License: See URL
12
+
13
+ ## Training
14
+
15
+ Finetuned from U.S. English lessac voice (medium quality).
en/en_GB/jenny_dioco/medium/config.json ADDED
@@ -0,0 +1,483 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio": {
3
+ "sample_rate": 22050
4
+ },
5
+ "espeak": {
6
+ "voice": "en-gb-x-rp"
7
+ },
8
+ "inference": {
9
+ "noise_scale": 0.667,
10
+ "length_scale": 1,
11
+ "noise_w": 0.8
12
+ },
13
+ "phoneme_type": "espeak",
14
+ "phoneme_map": {},
15
+ "phoneme_id_map": {
16
+ "_": [
17
+ 0
18
+ ],
19
+ "^": [
20
+ 1
21
+ ],
22
+ "$": [
23
+ 2
24
+ ],
25
+ " ": [
26
+ 3
27
+ ],
28
+ "!": [
29
+ 4
30
+ ],
31
+ "'": [
32
+ 5
33
+ ],
34
+ "(": [
35
+ 6
36
+ ],
37
+ ")": [
38
+ 7
39
+ ],
40
+ ",": [
41
+ 8
42
+ ],
43
+ "-": [
44
+ 9
45
+ ],
46
+ ".": [
47
+ 10
48
+ ],
49
+ ":": [
50
+ 11
51
+ ],
52
+ ";": [
53
+ 12
54
+ ],
55
+ "?": [
56
+ 13
57
+ ],
58
+ "a": [
59
+ 14
60
+ ],
61
+ "b": [
62
+ 15
63
+ ],
64
+ "c": [
65
+ 16
66
+ ],
67
+ "d": [
68
+ 17
69
+ ],
70
+ "e": [
71
+ 18
72
+ ],
73
+ "f": [
74
+ 19
75
+ ],
76
+ "h": [
77
+ 20
78
+ ],
79
+ "i": [
80
+ 21
81
+ ],
82
+ "j": [
83
+ 22
84
+ ],
85
+ "k": [
86
+ 23
87
+ ],
88
+ "l": [
89
+ 24
90
+ ],
91
+ "m": [
92
+ 25
93
+ ],
94
+ "n": [
95
+ 26
96
+ ],
97
+ "o": [
98
+ 27
99
+ ],
100
+ "p": [
101
+ 28
102
+ ],
103
+ "q": [
104
+ 29
105
+ ],
106
+ "r": [
107
+ 30
108
+ ],
109
+ "s": [
110
+ 31
111
+ ],
112
+ "t": [
113
+ 32
114
+ ],
115
+ "u": [
116
+ 33
117
+ ],
118
+ "v": [
119
+ 34
120
+ ],
121
+ "w": [
122
+ 35
123
+ ],
124
+ "x": [
125
+ 36
126
+ ],
127
+ "y": [
128
+ 37
129
+ ],
130
+ "z": [
131
+ 38
132
+ ],
133
+ "æ": [
134
+ 39
135
+ ],
136
+ "ç": [
137
+ 40
138
+ ],
139
+ "ð": [
140
+ 41
141
+ ],
142
+ "ø": [
143
+ 42
144
+ ],
145
+ "ħ": [
146
+ 43
147
+ ],
148
+ "ŋ": [
149
+ 44
150
+ ],
151
+ "œ": [
152
+ 45
153
+ ],
154
+ "ǀ": [
155
+ 46
156
+ ],
157
+ "ǁ": [
158
+ 47
159
+ ],
160
+ "ǂ": [
161
+ 48
162
+ ],
163
+ "ǃ": [
164
+ 49
165
+ ],
166
+ "ɐ": [
167
+ 50
168
+ ],
169
+ "ɑ": [
170
+ 51
171
+ ],
172
+ "ɒ": [
173
+ 52
174
+ ],
175
+ "ɓ": [
176
+ 53
177
+ ],
178
+ "ɔ": [
179
+ 54
180
+ ],
181
+ "ɕ": [
182
+ 55
183
+ ],
184
+ "ɖ": [
185
+ 56
186
+ ],
187
+ "ɗ": [
188
+ 57
189
+ ],
190
+ "ɘ": [
191
+ 58
192
+ ],
193
+ "ə": [
194
+ 59
195
+ ],
196
+ "ɚ": [
197
+ 60
198
+ ],
199
+ "ɛ": [
200
+ 61
201
+ ],
202
+ "ɜ": [
203
+ 62
204
+ ],
205
+ "ɞ": [
206
+ 63
207
+ ],
208
+ "ɟ": [
209
+ 64
210
+ ],
211
+ "ɠ": [
212
+ 65
213
+ ],
214
+ "ɡ": [
215
+ 66
216
+ ],
217
+ "ɢ": [
218
+ 67
219
+ ],
220
+ "ɣ": [
221
+ 68
222
+ ],
223
+ "ɤ": [
224
+ 69
225
+ ],
226
+ "ɥ": [
227
+ 70
228
+ ],
229
+ "ɦ": [
230
+ 71
231
+ ],
232
+ "ɧ": [
233
+ 72
234
+ ],
235
+ "ɨ": [
236
+ 73
237
+ ],
238
+ "ɪ": [
239
+ 74
240
+ ],
241
+ "ɫ": [
242
+ 75
243
+ ],
244
+ "ɬ": [
245
+ 76
246
+ ],
247
+ "ɭ": [
248
+ 77
249
+ ],
250
+ "ɮ": [
251
+ 78
252
+ ],
253
+ "ɯ": [
254
+ 79
255
+ ],
256
+ "ɰ": [
257
+ 80
258
+ ],
259
+ "ɱ": [
260
+ 81
261
+ ],
262
+ "ɲ": [
263
+ 82
264
+ ],
265
+ "ɳ": [
266
+ 83
267
+ ],
268
+ "ɴ": [
269
+ 84
270
+ ],
271
+ "ɵ": [
272
+ 85
273
+ ],
274
+ "ɶ": [
275
+ 86
276
+ ],
277
+ "ɸ": [
278
+ 87
279
+ ],
280
+ "ɹ": [
281
+ 88
282
+ ],
283
+ "ɺ": [
284
+ 89
285
+ ],
286
+ "ɻ": [
287
+ 90
288
+ ],
289
+ "ɽ": [
290
+ 91
291
+ ],
292
+ "ɾ": [
293
+ 92
294
+ ],
295
+ "ʀ": [
296
+ 93
297
+ ],
298
+ "ʁ": [
299
+ 94
300
+ ],
301
+ "ʂ": [
302
+ 95
303
+ ],
304
+ "ʃ": [
305
+ 96
306
+ ],
307
+ "ʄ": [
308
+ 97
309
+ ],
310
+ "ʈ": [
311
+ 98
312
+ ],
313
+ "ʉ": [
314
+ 99
315
+ ],
316
+ "ʊ": [
317
+ 100
318
+ ],
319
+ "ʋ": [
320
+ 101
321
+ ],
322
+ "ʌ": [
323
+ 102
324
+ ],
325
+ "ʍ": [
326
+ 103
327
+ ],
328
+ "ʎ": [
329
+ 104
330
+ ],
331
+ "ʏ": [
332
+ 105
333
+ ],
334
+ "ʐ": [
335
+ 106
336
+ ],
337
+ "ʑ": [
338
+ 107
339
+ ],
340
+ "ʒ": [
341
+ 108
342
+ ],
343
+ "ʔ": [
344
+ 109
345
+ ],
346
+ "ʕ": [
347
+ 110
348
+ ],
349
+ "ʘ": [
350
+ 111
351
+ ],
352
+ "ʙ": [
353
+ 112
354
+ ],
355
+ "ʛ": [
356
+ 113
357
+ ],
358
+ "ʜ": [
359
+ 114
360
+ ],
361
+ "ʝ": [
362
+ 115
363
+ ],
364
+ "ʟ": [
365
+ 116
366
+ ],
367
+ "ʡ": [
368
+ 117
369
+ ],
370
+ "ʢ": [
371
+ 118
372
+ ],
373
+ "ʲ": [
374
+ 119
375
+ ],
376
+ "ˈ": [
377
+ 120
378
+ ],
379
+ "ˌ": [
380
+ 121
381
+ ],
382
+ "ː": [
383
+ 122
384
+ ],
385
+ "ˑ": [
386
+ 123
387
+ ],
388
+ "˞": [
389
+ 124
390
+ ],
391
+ "β": [
392
+ 125
393
+ ],
394
+ "θ": [
395
+ 126
396
+ ],
397
+ "χ": [
398
+ 127
399
+ ],
400
+ "ᵻ": [
401
+ 128
402
+ ],
403
+ "ⱱ": [
404
+ 129
405
+ ],
406
+ "0": [
407
+ 130
408
+ ],
409
+ "1": [
410
+ 131
411
+ ],
412
+ "2": [
413
+ 132
414
+ ],
415
+ "3": [
416
+ 133
417
+ ],
418
+ "4": [
419
+ 134
420
+ ],
421
+ "5": [
422
+ 135
423
+ ],
424
+ "6": [
425
+ 136
426
+ ],
427
+ "7": [
428
+ 137
429
+ ],
430
+ "8": [
431
+ 138
432
+ ],
433
+ "9": [
434
+ 139
435
+ ],
436
+ "̧": [
437
+ 140
438
+ ],
439
+ "̃": [
440
+ 141
441
+ ],
442
+ "̪": [
443
+ 142
444
+ ],
445
+ "̯": [
446
+ 143
447
+ ],
448
+ "̩": [
449
+ 144
450
+ ],
451
+ "ʰ": [
452
+ 145
453
+ ],
454
+ "ˤ": [
455
+ 146
456
+ ],
457
+ "ε": [
458
+ 147
459
+ ],
460
+ "↓": [
461
+ 148
462
+ ],
463
+ "#": [
464
+ 149
465
+ ],
466
+ "\"": [
467
+ 150
468
+ ],
469
+ "↑": [
470
+ 151
471
+ ],
472
+ "̺": [
473
+ 152
474
+ ],
475
+ "̻": [
476
+ 153
477
+ ]
478
+ },
479
+ "num_symbols": 256,
480
+ "num_speakers": 1,
481
+ "speaker_id_map": {},
482
+ "piper_version": "1.0.0"
483
+ }
en/en_GB/jenny_dioco/medium/dataset.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc04bb3fcb7b9f9dbfecabd5bb4e3fc2b777c3499f27b424e6058e2ecd426b5e
3
+ size 4875404
en/en_GB/jenny_dioco/medium/decoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69d277a5866f648aac24f8a31c988b8379c250a8faba980e047c70703a0623b
3
+ size 35094574
en/en_GB/jenny_dioco/medium/decoder_rk3576.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7659378550d299de4c580f0a35ff53f92dcb4de6ef6d196fa86dab8918f50502
3
+ size 19481425
en/en_GB/jenny_dioco/medium/decoder_rk3588.rknn ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc60dfabfb897cfbf8ac8b4a832828396ded3fae0245ea8d5bd176e8835743d
3
+ size 20061137