| [ |
| { |
| "metadataOutputVersion" : "3.0", |
| "storagePrecision" : "Mixed (Float16, Palettized (8 bits))", |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16)", |
| "shortDescription" : "", |
| "shape" : "[]", |
| "name" : "audio_embeddings", |
| "type" : "MultiArray" |
| } |
| ], |
| "modelParameters" : [ |
|
|
| ], |
| "specificationVersion" : 8, |
| "mlProgramOperationTypeHistogram" : { |
| "Ios17.mul" : 18, |
| "Ios17.linear" : 111, |
| "Ios17.transpose" : 73, |
| "Ios16.constexprLutToDense" : 115, |
| "Ios17.conv" : 3, |
| "Ios17.matmul" : 36, |
| "Shape" : 1, |
| "Ios17.gather" : 1, |
| "Ios17.sliceByIndex" : 1, |
| "Ios17.concat" : 1, |
| "Ios17.add" : 37, |
| "Ios16.softmax" : 18, |
| "Ios16.gelu" : 22, |
| "Ios17.expandDims" : 1, |
| "Ios17.reshape" : 73, |
| "Ios17.cast" : 3, |
| "Ios17.layerNorm" : 37 |
| }, |
| "computePrecision" : "Mixed (Float16, Int32, UInt16)", |
| "isUpdatable" : "0", |
| "stateSchema" : [ |
|
|
| ], |
| "availability" : { |
| "macOS" : "14.0", |
| "tvOS" : "17.0", |
| "visionOS" : "1.0", |
| "watchOS" : "10.0", |
| "iOS" : "17.0", |
| "macCatalyst" : "17.0" |
| }, |
| "modelType" : { |
| "name" : "MLModelType_mlProgram" |
| }, |
| "userDefinedMetadata" : { |
| "com.github.apple.coremltools.conversion_date" : "2026-03-23", |
| "com.github.apple.coremltools.source" : "torch==2.11.0", |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" |
| }, |
| "inputSchema" : [ |
| { |
| "shortDescription" : "", |
| "dataType" : "Float32", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 128 × 100 | 1 × 128 × 200 | 1 × 128 × 400 | 1 × 128 × 600 | 1 × 128 × 800 | 1 × 128 × 1000 | 1 × 128 × 1500 | 1 × 128 × 2000 | 1 × 128 × 3000", |
| "formattedType" : "MultiArray (Float32 1 × 128 × 100)", |
| "type" : "MultiArray", |
| "shape" : "[1, 128, 100]", |
| "name" : "mel", |
| "enumeratedShapes" : "[[1, 128, 100], [1, 128, 200], [1, 128, 400], [1, 128, 600], [1, 128, 800], [1, 128, 1000], [1, 128, 1500], [1, 128, 2000], [1, 128, 3000]]" |
| } |
| ], |
| "generatedClassName" : "encoder", |
| "method" : "predict" |
| } |
| ] |
