Upload config.json with huggingface_hub
Browse files- config.json +82 -0
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "SenseVoiceSmall-coreml",
|
| 3 |
+
"upstream": {
|
| 4 |
+
"model": "FunAudioLLM/SenseVoiceSmall",
|
| 5 |
+
"code": "https://github.com/FunAudioLLM/SenseVoice",
|
| 6 |
+
"model_revision": "3eb3b4eeffc2f2dde6051b853983753db33e35c3",
|
| 7 |
+
"code_commit": "b97857e5c807a466d0a062cf84dba9fe38a1d66a",
|
| 8 |
+
"assets": [
|
| 9 |
+
{
|
| 10 |
+
"name": "cmvn_am.mvn",
|
| 11 |
+
"url": "https://modelscope.cn/api/v1/models/iic/SenseVoiceSmall/repo?Revision=master&FilePath=am.mvn",
|
| 12 |
+
"sha256": "29b3c740a2c0cfc6b308126d31d7f265fa2be74f3bb095cd2f143ea970896ae5",
|
| 13 |
+
"bytes": 11203
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"name": "spm",
|
| 17 |
+
"url": "https://modelscope.cn/api/v1/models/iic/SenseVoiceSmall/repo?Revision=master&FilePath=chn_jpn_yue_eng_ko_spectok.bpe.model",
|
| 18 |
+
"sha256": "aa87f86064c3730d799ddf7af3c04659151102cba548bce325cf06ba4da4e6a8",
|
| 19 |
+
"bytes": 377341
|
| 20 |
+
}
|
| 21 |
+
]
|
| 22 |
+
},
|
| 23 |
+
"artifacts": {
|
| 24 |
+
"coreml_zip": "coreml/SenseVoiceSmall.mlmodelc.zip"
|
| 25 |
+
},
|
| 26 |
+
"coreml": {
|
| 27 |
+
"format": "mlmodelc",
|
| 28 |
+
"inputs": [
|
| 29 |
+
{
|
| 30 |
+
"name": "speech",
|
| 31 |
+
"dtype": "float32",
|
| 32 |
+
"shape": [
|
| 33 |
+
1,
|
| 34 |
+
"T",
|
| 35 |
+
560
|
| 36 |
+
]
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"name": "speech_lengths",
|
| 40 |
+
"dtype": "int32",
|
| 41 |
+
"shape": [
|
| 42 |
+
1
|
| 43 |
+
]
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"name": "language",
|
| 47 |
+
"dtype": "int32",
|
| 48 |
+
"shape": [
|
| 49 |
+
1
|
| 50 |
+
]
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"name": "textnorm",
|
| 54 |
+
"dtype": "int32",
|
| 55 |
+
"shape": [
|
| 56 |
+
1
|
| 57 |
+
]
|
| 58 |
+
}
|
| 59 |
+
],
|
| 60 |
+
"outputs": [
|
| 61 |
+
{
|
| 62 |
+
"name": "ctc_logits"
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"name": "encoder_out_lens"
|
| 66 |
+
}
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"decoding": {
|
| 70 |
+
"ctc_blank_id": 0,
|
| 71 |
+
"token_offset": 0
|
| 72 |
+
},
|
| 73 |
+
"notes": [
|
| 74 |
+
"Do not run a single forward pass on extremely long audio; use VAD/chunking."
|
| 75 |
+
],
|
| 76 |
+
"build": {
|
| 77 |
+
"artifact": "coreml/SenseVoiceSmall.mlmodelc.zip",
|
| 78 |
+
"sha256": "880711fa03577363e6c1b1b6e9321f130ea1a53d5c065d92e1abd8a431bad6be",
|
| 79 |
+
"bytes": 432164139,
|
| 80 |
+
"xcodebuild_version": "Xcode 26.0\nBuild version 17A324"
|
| 81 |
+
}
|
| 82 |
+
}
|