Upload 1801 files

.gitattributes

@@ -288,3 +288,83 @@ sherpa_onnx_models/hSky-high/vits-piper-hSky_high-889/espeak-ng-data/ru_dict fil
 sherpa_onnx_models/hSky-high/vits-piper-hSky_high-889/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
 sherpa_onnx_models/hSky-high/vits-piper-hSky_high-889/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
 sherpa_onnx_models/hSky-high/vits-piper-hSky_high-889/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/samples/bVox0-244-rainbow.wav filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/samples/bVox1-409-rainbow.wav filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/samples/bVox1-839-rainbow.wav filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/samples/bVox2-289-rainbow.wav filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/samples/bVox2-349-rainbow.wav filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/af_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ar_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/cmn_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/da_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/en_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/fa_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/hu_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ia_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/it_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/lb_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/phondata filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ru_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/af_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/ar_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/cmn_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/da_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/en_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/fa_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/hu_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/ia_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/it_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/lb_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/phondata filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/ru_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-409/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/af_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/ar_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/cmn_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/da_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/en_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/fa_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/hu_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/ia_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/it_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/lb_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/phondata filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/ru_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox1-839/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/af_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/ar_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/cmn_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/da_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/en_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/fa_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/hu_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/ia_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/it_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/lb_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/phondata filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/ru_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-289/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/af_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/ar_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/cmn_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/da_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/en_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/fa_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/hu_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/ia_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/it_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/lb_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/phondata filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/ru_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/ta_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/ur_dict filter=lfs diff=lfs merge=lfs -text
+sherpa_onnx_models/bVox/vits-piper-bVox2-349/espeak-ng-data/yue_dict filter=lfs diff=lfs merge=lfs -text

sherpa_onnx_models/bVox/samples/bVox0-244-rainbow.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c972f236463eb4190f95d18b1f9cf34b420210e214ca22d2451ea00e844f2ee3
+size 2112226

sherpa_onnx_models/bVox/samples/bVox1-409-rainbow.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c274d95d36ac802912f66f52a170ad107a4c829247641564f723ddbdbf66a18
+size 1728810

sherpa_onnx_models/bVox/samples/bVox1-839-rainbow.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117d2a00ace9f59e773312ab43e80bde7f9f4f5da7a6ce98cfa287429e07cf8e
+size 1795602

sherpa_onnx_models/bVox/samples/bVox2-289-rainbow.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cadd311c8629f6db4539f9929f6aa54d1de0e0b14411d98a5d021b937b2f6dc
+size 2012418

sherpa_onnx_models/bVox/samples/bVox2-349-rainbow.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cc10c6e5b866ff5a1da0dcc17ec3c9b47540dc87ffb6ab67089158c6b66029
+size 2039834

sherpa_onnx_models/bVox/vits-piper-bVox0-244/bVox0-244.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd4bcec87e395475878bb8ee1f6cddbf09b8a2a2486e9647360982b3f20d70a
+size 63531605

sherpa_onnx_models/bVox/vits-piper-bVox0-244/bVox0-244.onnx.json

@@ -0,0 +1,504 @@
+{
+  "audio": {
+    "sample_rate": 22050
+  },
+  "espeak": {
+    "voice": "en-us"
+  },
+  "phoneme_type": "espeak",
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1.0,
+    "noise_w": 0.8
+  },
+  "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
+    ],
+    "g": [
+      154
+    ],
+    "ʦ": [
+      155
+    ],
+    "X": [
+      156
+    ],
+    "̝": [
+      157
+    ],
+    "̊": [
+      158
+    ],
+    "ɝ": [
+      159
+    ],
+    "ʷ": [
+      160
+    ]
+  },
+  "speaker_id_map": {},
+  "hop_length": 256,
+  "piper_version": "1.3.0"
+}

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/af_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25729d3bf4c4a0f08da60aea9eb5a0cf352630f83fab1ab0c3955b7740da1776
+size 121473

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/ar_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72316426e797777fe4df9420935a3b6a79b37d7e3f3948537ba71cd7b21b2541
+size 478165

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/cmn_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109aaa7708d3727382acb3ae41d8e2094a7e2bb9f651a81835be22a6f08071fe
+size 1566335

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/da_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0c21895b4844868612f9ea846bc6010e30b5dd1f4cb1567459d73d2792a8ac
+size 245287

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/en_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bd330ba8a2e3e8076e631508208ef49449d6147c17b7bd2b4b1e1468292e35
+size 166944

sherpa_onnx_models/bVox/vits-piper-bVox0-244/espeak-ng-data/fa_dict

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92f35ce7eb1d97360016617d97786412a94af55b776a18f1c280dab4f43befd
+size 292423