| [ |
| { |
| "metadataOutputVersion" : "3.0", |
| "storagePrecision" : "Float16", |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 1 × 125 × 1024)", |
| "shortDescription" : "", |
| "shape" : "[1, 125, 1024]", |
| "name" : "conditioning", |
| "type" : "MultiArray" |
| } |
| ], |
| "modelParameters" : [ |
|
|
| ], |
| "specificationVersion" : 8, |
| "mlProgramOperationTypeHistogram" : { |
| "Ios17.elu" : 10, |
| "Ios17.reshape" : 12, |
| "Ios16.softmax" : 2, |
| "Ios17.matmul" : 4, |
| "Ios17.transpose" : 11, |
| "Split" : 2, |
| "Select" : 2, |
| "Ios17.add" : 11, |
| "Tile" : 1, |
| "Ios17.sliceByIndex" : 9, |
| "Ios17.squeeze" : 6, |
| "Ios17.layerNorm" : 4, |
| "Ios17.conv" : 12, |
| "Ios17.sub" : 4, |
| "Ios16.gelu" : 2, |
| "Ios17.cast" : 2, |
| "Ios17.linear" : 9, |
| "Stack" : 4, |
| "Ios17.concat" : 9, |
| "Ios17.mul" : 22 |
| }, |
| "computePrecision" : "Mixed (Float16, Float32, Int32)", |
| "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" : "2026-05-11", |
| "com.github.apple.coremltools.source" : "torch==2.11.0", |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" |
| }, |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float32", |
| "formattedType" : "MultiArray (Float32 1 × 1 × 240000)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 240000]", |
| "name" : "audio", |
| "type" : "MultiArray" |
| } |
| ], |
| "generatedClassName" : "mimi_encoderv2", |
| "method" : "predict" |
| } |
| ] |