Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- pretrained_models/demos/lemas_edit_test/align/en_AUD0000000214_S0001522.json +98 -0
- pretrained_models/demos/lemas_edit_test/align/zh_emilia_zh_0008385782.json +182 -0
- pretrained_models/demos/lemas_edit_test/vocals/en_AUD0000000214_S0001522.mp3 +0 -0
- pretrained_models/demos/lemas_edit_test/vocals/zh_emilia_zh_0008385782.mp3 +0 -0
- pretrained_models/demos/test.wav +3 -0
.gitattributes
CHANGED
|
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
pretrained_models/ckpts/autoregressive/encodec_4cb2048_giga.th filter=lfs diff=lfs merge=lfs -text
|
| 37 |
pretrained_models/demo/test.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
pretrained_models/whisperx/whisperx-vad-segmentation.bak filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 36 |
pretrained_models/ckpts/autoregressive/encodec_4cb2048_giga.th filter=lfs diff=lfs merge=lfs -text
|
| 37 |
pretrained_models/demo/test.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
pretrained_models/whisperx/whisperx-vad-segmentation.bak filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
pretrained_models/demos/test.wav filter=lfs diff=lfs merge=lfs -text
|
pretrained_models/demos/lemas_edit_test/align/en_AUD0000000214_S0001522.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"id": "en_AUD0000000214_S0001522",
|
| 3 |
+
"file_name": "en_AUD0000000214_S0001522.mp3",
|
| 4 |
+
"display_text": "THAT I WAS IN FACT UNABLE TO DO ANY LITERARY WORK",
|
| 5 |
+
"modified_index": [
|
| 6 |
+
5,
|
| 7 |
+
6
|
| 8 |
+
],
|
| 9 |
+
"modified_text": [
|
| 10 |
+
"UNABLE",
|
| 11 |
+
"POWERLESS"
|
| 12 |
+
],
|
| 13 |
+
"interval": [
|
| 14 |
+
0.14,
|
| 15 |
+
3.029
|
| 16 |
+
],
|
| 17 |
+
"words": [
|
| 18 |
+
{
|
| 19 |
+
"text": "THAT",
|
| 20 |
+
"interval": [
|
| 21 |
+
0.14,
|
| 22 |
+
0.261
|
| 23 |
+
]
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"text": "I",
|
| 27 |
+
"interval": [
|
| 28 |
+
0.341,
|
| 29 |
+
0.361
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"text": "WAS",
|
| 34 |
+
"interval": [
|
| 35 |
+
0.401,
|
| 36 |
+
0.562
|
| 37 |
+
]
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"text": "IN",
|
| 41 |
+
"interval": [
|
| 42 |
+
0.602,
|
| 43 |
+
0.702
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"text": "FACT",
|
| 48 |
+
"interval": [
|
| 49 |
+
0.762,
|
| 50 |
+
1.063
|
| 51 |
+
]
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"text": "UNABLE",
|
| 55 |
+
"interval": [
|
| 56 |
+
1.183,
|
| 57 |
+
1.545
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"text": "TO",
|
| 62 |
+
"interval": [
|
| 63 |
+
1.605,
|
| 64 |
+
1.685
|
| 65 |
+
]
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"text": "DO",
|
| 69 |
+
"interval": [
|
| 70 |
+
1.745,
|
| 71 |
+
1.825
|
| 72 |
+
]
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"text": "ANY",
|
| 76 |
+
"interval": [
|
| 77 |
+
2.006,
|
| 78 |
+
2.146
|
| 79 |
+
]
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"text": "LITERARY",
|
| 83 |
+
"interval": [
|
| 84 |
+
2.267,
|
| 85 |
+
2.708
|
| 86 |
+
]
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"text": "WORK",
|
| 90 |
+
"interval": [
|
| 91 |
+
2.788,
|
| 92 |
+
3.029
|
| 93 |
+
]
|
| 94 |
+
}
|
| 95 |
+
],
|
| 96 |
+
"speaker": "Guest-1",
|
| 97 |
+
"original_language": "en-US"
|
| 98 |
+
}
|
pretrained_models/demos/lemas_edit_test/align/zh_emilia_zh_0008385782.json
ADDED
|
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"id": "zh_emilia_zh_0008385782",
|
| 3 |
+
"file_name": "zh_emilia_zh_0008385782.mp3",
|
| 4 |
+
"display_text": "又出使南方的闽东岳等族,希望他们紧随其后,作为支援。",
|
| 5 |
+
"modified_index": [
|
| 6 |
+
3,
|
| 7 |
+
5
|
| 8 |
+
],
|
| 9 |
+
"modified_text": [
|
| 10 |
+
"南方",
|
| 11 |
+
"北方"
|
| 12 |
+
],
|
| 13 |
+
"interval": [
|
| 14 |
+
0.12,
|
| 15 |
+
5.335
|
| 16 |
+
],
|
| 17 |
+
"words": [
|
| 18 |
+
{
|
| 19 |
+
"text": "you4",
|
| 20 |
+
"interval": [
|
| 21 |
+
0.12,
|
| 22 |
+
0.281
|
| 23 |
+
]
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"text": "chu1",
|
| 27 |
+
"interval": [
|
| 28 |
+
0.361,
|
| 29 |
+
0.481
|
| 30 |
+
]
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"text": "shi3",
|
| 34 |
+
"interval": [
|
| 35 |
+
0.582,
|
| 36 |
+
0.662
|
| 37 |
+
]
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"text": "nan2",
|
| 41 |
+
"interval": [
|
| 42 |
+
0.742,
|
| 43 |
+
0.903
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"text": "fang1",
|
| 48 |
+
"interval": [
|
| 49 |
+
0.963,
|
| 50 |
+
1.163
|
| 51 |
+
]
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"text": "de5",
|
| 55 |
+
"interval": [
|
| 56 |
+
1.203,
|
| 57 |
+
1.284
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"text": "min3",
|
| 62 |
+
"interval": [
|
| 63 |
+
1.464,
|
| 64 |
+
1.685
|
| 65 |
+
]
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"text": "dong1",
|
| 69 |
+
"interval": [
|
| 70 |
+
1.825,
|
| 71 |
+
2.006
|
| 72 |
+
]
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"text": "yue4",
|
| 76 |
+
"interval": [
|
| 77 |
+
2.066,
|
| 78 |
+
2.166
|
| 79 |
+
]
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"text": "deng3",
|
| 83 |
+
"interval": [
|
| 84 |
+
2.266,
|
| 85 |
+
2.427
|
| 86 |
+
]
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"text": "zu2,",
|
| 90 |
+
"interval": [
|
| 91 |
+
2.467,
|
| 92 |
+
2.567
|
| 93 |
+
]
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"text": "xi1",
|
| 97 |
+
"interval": [
|
| 98 |
+
3.189,
|
| 99 |
+
3.269
|
| 100 |
+
]
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"text": "wang4",
|
| 104 |
+
"interval": [
|
| 105 |
+
3.329,
|
| 106 |
+
3.47
|
| 107 |
+
]
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"text": "ta1",
|
| 111 |
+
"interval": [
|
| 112 |
+
3.49,
|
| 113 |
+
3.57
|
| 114 |
+
]
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"text": "men5",
|
| 118 |
+
"interval": [
|
| 119 |
+
3.65,
|
| 120 |
+
3.771
|
| 121 |
+
]
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"text": "jin3",
|
| 125 |
+
"interval": [
|
| 126 |
+
3.831,
|
| 127 |
+
3.991
|
| 128 |
+
]
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"text": "sui2",
|
| 132 |
+
"interval": [
|
| 133 |
+
4.051,
|
| 134 |
+
4.172
|
| 135 |
+
]
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"text": "qi2",
|
| 139 |
+
"interval": [
|
| 140 |
+
4.232,
|
| 141 |
+
4.312
|
| 142 |
+
]
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"text": "hou4,",
|
| 146 |
+
"interval": [
|
| 147 |
+
4.392,
|
| 148 |
+
4.533
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"text": "zuo4",
|
| 153 |
+
"interval": [
|
| 154 |
+
4.733,
|
| 155 |
+
4.834
|
| 156 |
+
]
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"text": "wei2",
|
| 160 |
+
"interval": [
|
| 161 |
+
4.894,
|
| 162 |
+
4.994
|
| 163 |
+
]
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"text": "zhi1",
|
| 167 |
+
"interval": [
|
| 168 |
+
5.034,
|
| 169 |
+
5.155
|
| 170 |
+
]
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"text": "yuan2.",
|
| 174 |
+
"interval": [
|
| 175 |
+
5.215,
|
| 176 |
+
5.335
|
| 177 |
+
]
|
| 178 |
+
}
|
| 179 |
+
],
|
| 180 |
+
"speaker": "Guest-1",
|
| 181 |
+
"original_language": "zh-CN"
|
| 182 |
+
}
|
pretrained_models/demos/lemas_edit_test/vocals/en_AUD0000000214_S0001522.mp3
ADDED
|
Binary file (21.4 kB). View file
|
|
|
pretrained_models/demos/lemas_edit_test/vocals/zh_emilia_zh_0008385782.mp3
ADDED
|
Binary file (58.8 kB). View file
|
|
|
pretrained_models/demos/test.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6913e2ff86f5d12b70ed46e78363dd7b33ce4642dd32e0641a614dfc0c81a92
|
| 3 |
+
size 464084
|