| [ |
| { |
| "metadataOutputVersion" : "3.0", |
| "storagePrecision" : "Mixed (Float16, Int32)", |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 2048 × 1 × 104)", |
| "shortDescription" : "", |
| "shape" : "[1, 2048, 1, 104]", |
| "name" : "audio_embeds", |
| "type" : "MultiArray" |
| } |
| ], |
| "modelParameters" : [ |
|
|
| ], |
| "specificationVersion" : 9, |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.batchNorm" : 49, |
| "Ios18.conv" : 150, |
| "Ios18.sub" : 49, |
| "Ios18.matmul" : 384, |
| "Ios18.concat" : 24, |
| "Ios18.rsqrt" : 49, |
| "Ios18.add" : 538, |
| "Ios16.einsum" : 384, |
| "Ios18.tanh" : 28, |
| "Ios16.reduceMean" : 98, |
| "Ios18.pow" : 49, |
| "Ios18.transpose" : 1155, |
| "Ios18.softmax" : 384, |
| "Ios18.reshape" : 1156, |
| "Split" : 72, |
| "Ios18.mul" : 217 |
| }, |
| "computePrecision" : "Mixed (Float16, Float32, Int32)", |
| "isUpdatable" : "0", |
| "stateSchema" : [ |
|
|
| ], |
| "availability" : { |
| "macOS" : "15.0", |
| "tvOS" : "18.0", |
| "visionOS" : "2.0", |
| "watchOS" : "11.0", |
| "iOS" : "18.0", |
| "macCatalyst" : "18.0" |
| }, |
| "modelType" : { |
| "name" : "MLModelType_mlProgram" |
| }, |
| "userDefinedMetadata" : { |
| "com.github.apple.coremltools.conversion_date" : "2026-09-20", |
| "com.github.apple.coremltools.source" : "torch==2.8.0", |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" |
| }, |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 128 × 800)", |
| "shortDescription" : "", |
| "shape" : "[1, 128, 800]", |
| "name" : "input_features", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 104)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1, 104]", |
| "name" : "key_bias", |
| "type" : "MultiArray" |
| } |
| ], |
| "generatedClassName" : "R2T2AudioEncoder", |
| "method" : "predict" |
| } |
| ] |
