Hugging Face's logo

FluidInference
/
silero-vad-coreml

Voice Activity Detection
Core ML
English
audio
silero
speech
ios
macos
swift
Model card Files
xet
 Community
2

Add Silero VAD CoreML v6.2.1 256ms artifact

#2
by lwrf42 - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+1131
-0
Files changed (5) hide show
  1. silero-vad-unified-256ms-v6.2.1.mlmodelc/analytics/coremldata.bin +3 -0
  2. silero-vad-unified-256ms-v6.2.1.mlmodelc/coremldata.bin +3 -0
  3. silero-vad-unified-256ms-v6.2.1.mlmodelc/metadata.json +120 -0
  4. silero-vad-unified-256ms-v6.2.1.mlmodelc/model.mil +0 -0
  5. silero-vad-unified-256ms-v6.2.1.mlmodelc/weights/weight.bin +3 -0
silero-vad-unified-256ms-v6.2.1.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8067594eb3126ab8318af507f0c00cabfed40d5fedb8a0ee5075dd02e903d909
3
+ size 243
silero-vad-unified-256ms-v6.2.1.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db35a4fd995222a7fb0129713473b15d1462572ab4a2e5e4d56bcaad9e40f41
3
+ size 625
silero-vad-unified-256ms-v6.2.1.mlmodelc/metadata.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "shortDescription" : "Silero VAD Unified Model 256ms (STFT + Encoder + Decoder) with noisy-OR aggregation",
4
+ "metadataOutputVersion" : "3.0",
5
+ "outputSchema" : [
6
+ {
7
+ "hasShapeFlexibility" : "0",
8
+ "isOptional" : "0",
9
+ "dataType" : "Float32",
10
+ "formattedType" : "MultiArray (Float32 1 × 1 × 1)",
11
+ "shortDescription" : "",
12
+ "shape" : "[1, 1, 1]",
13
+ "name" : "vad_output",
14
+ "type" : "MultiArray"
15
+ },
16
+ {
17
+ "hasShapeFlexibility" : "0",
18
+ "isOptional" : "0",
19
+ "dataType" : "Float32",
20
+ "formattedType" : "MultiArray (Float32 1 × 128)",
21
+ "shortDescription" : "",
22
+ "shape" : "[1, 128]",
23
+ "name" : "new_hidden_state",
24
+ "type" : "MultiArray"
25
+ },
26
+ {
27
+ "hasShapeFlexibility" : "0",
28
+ "isOptional" : "0",
29
+ "dataType" : "Float32",
30
+ "formattedType" : "MultiArray (Float32 1 × 128)",
31
+ "shortDescription" : "",
32
+ "shape" : "[1, 128]",
33
+ "name" : "new_cell_state",
34
+ "type" : "MultiArray"
35
+ }
36
+ ],
37
+ "version" : "6.2.1",
38
+ "modelParameters" : [
39
+
40
+ ],
41
+ "author" : "Fluid Infernece + Silero Team",
42
+ "specificationVersion" : 6,
43
+ "storagePrecision" : "Mixed (Float16, Float32)",
44
+ "mlProgramOperationTypeHistogram" : {
45
+ "Concat" : 9,
46
+ "Lstm" : 8,
47
+ "SliceByIndex" : 41,
48
+ "Clip" : 32,
49
+ "Pow" : 16,
50
+ "Transpose" : 16,
51
+ "Sub" : 2,
52
+ "Relu" : 40,
53
+ "Squeeze" : 18,
54
+ "Cast" : 54,
55
+ "Sigmoid" : 8,
56
+ "Add" : 16,
57
+ "ExpandDims" : 26,
58
+ "Sqrt" : 8,
59
+ "Mul" : 7,
60
+ "Conv" : 48,
61
+ "Pad" : 8
62
+ },
63
+ "computePrecision" : "Mixed (Float16, Float32, Int32)",
64
+ "stateSchema" : [
65
+
66
+ ],
67
+ "isUpdatable" : "0",
68
+ "availability" : {
69
+ "macOS" : "12.0",
70
+ "tvOS" : "15.0",
71
+ "visionOS" : "1.0",
72
+ "watchOS" : "8.0",
73
+ "iOS" : "15.0",
74
+ "macCatalyst" : "15.0"
75
+ },
76
+ "modelType" : {
77
+ "name" : "MLModelType_mlProgram"
78
+ },
79
+ "inputSchema" : [
80
+ {
81
+ "hasShapeFlexibility" : "0",
82
+ "isOptional" : "0",
83
+ "dataType" : "Float32",
84
+ "formattedType" : "MultiArray (Float32 1 × 4160)",
85
+ "shortDescription" : "",
86
+ "shape" : "[1, 4160]",
87
+ "name" : "audio_input",
88
+ "type" : "MultiArray"
89
+ },
90
+ {
91
+ "hasShapeFlexibility" : "0",
92
+ "isOptional" : "0",
93
+ "dataType" : "Float32",
94
+ "formattedType" : "MultiArray (Float32 1 × 128)",
95
+ "shortDescription" : "",
96
+ "shape" : "[1, 128]",
97
+ "name" : "hidden_state",
98
+ "type" : "MultiArray"
99
+ },
100
+ {
101
+ "hasShapeFlexibility" : "0",
102
+ "isOptional" : "0",
103
+ "dataType" : "Float32",
104
+ "formattedType" : "MultiArray (Float32 1 × 128)",
105
+ "shortDescription" : "",
106
+ "shape" : "[1, 128]",
107
+ "name" : "cell_state",
108
+ "type" : "MultiArray"
109
+ }
110
+ ],
111
+ "userDefinedMetadata" : {
112
+ "com.github.apple.coremltools.conversion_date" : "2026-06-23",
113
+ "com.github.apple.coremltools.source" : "torch==2.7.0",
114
+ "com.github.apple.coremltools.version" : "9.0b1",
115
+ "com.github.apple.coremltools.source_dialect" : "TorchScript"
116
+ },
117
+ "generatedClassName" : "silero_vad_unified_256ms_v6_2_1",
118
+ "method" : "predict"
119
+ }
120
+ ]
silero-vad-unified-256ms-v6.2.1.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
silero-vad-unified-256ms-v6.2.1.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ecc8b5081146140ab654c89109cf001f2183abddd7a2411c5081feeffff063
3
+ size 882304