[ { "metadataOutputVersion" : "3.0", "storagePrecision" : "Mixed (Float16, Float32)", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 21 × 589 × 3)", "shortDescription" : "", "shape" : "[21, 589, 3]", "name" : "speaker_probs", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 21 × 589 × 3)", "shortDescription" : "", "shape" : "[21, 589, 3]", "name" : "speaker_ids", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 21 × 3)", "shortDescription" : "", "shape" : "[21, 3]", "name" : "speaker_activity", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 21 × 589)", "shortDescription" : "", "shape" : "[21, 589]", "name" : "overlapped_speaker_activity", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1767)", "shortDescription" : "", "shape" : "[1767]", "name" : "voice_activity", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 21 × 1 × 160000)", "shortDescription" : "", "shape" : "[21, 1, 160000]", "name" : "sliding_window_waveform", "type" : "MultiArray" } ], "modelParameters" : [ ], "specificationVersion" : 7, "mlProgramOperationTypeHistogram" : { "Transpose" : 2, "Ios16.maxPool" : 3, "Ios16.exp" : 1, "Ios16.softmax" : 1, "SlidingWindows" : 1, "Ios16.linear" : 5, "Ios16.add" : 40, "Ios16.realDiv" : 1, "Ios16.reduceMax" : 1, "Ios16.reduceSum" : 2, "Ios16.reduceArgmax" : 1, "Ios16.greater" : 1, "Ios16.log" : 1, "ExpandDims" : 1, "Ios16.instanceNorm" : 4, "Ios16.cast" : 4, "Ios16.conv" : 3, "Ios16.lstm" : 4, "OneHot" : 1, "Ios16.scatter" : 42, "SliceByIndex" : 61, "Ios16.abs" : 1, "Ios16.leakyRelu" : 5 }, "computePrecision" : "Mixed (Float16, Float32, Int32)", "isUpdatable" : "0", "stateSchema" : [ ], "availability" : { "macOS" : "13.0", "tvOS" : "16.0", "visionOS" : "1.0", "watchOS" : "9.0", "iOS" : "16.0", "macCatalyst" : "16.0" }, "modelType" : { "name" : "MLModelType_mlProgram" }, "userDefinedMetadata" : { "com.github.apple.coremltools.source_dialect" : "TorchScript", "com.github.apple.coremltools.source" : "torch==2.5.1", "com.github.apple.coremltools.version" : "8.0" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 480000)", "shortDescription" : "", "shape" : "[480000]", "name" : "waveform", "type" : "MultiArray" } ], "generatedClassName" : "SpeakerSegmenter", "method" : "predict" } ]