| [ |
| { |
| "metadataOutputVersion" : "3.0", |
| "storagePrecision" : "Mixed (Float16, Palettized (8 bits))", |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "anchor", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16)", |
| "shortDescription" : "", |
| "shape" : "[]", |
| "name" : "x_pre", |
| "type" : "MultiArray" |
| } |
| ], |
| "modelParameters" : [ |
|
|
| ], |
| "specificationVersion" : 8, |
| "mlProgramOperationTypeHistogram" : { |
| "Ios17.mul" : 161, |
| "Ios17.linear" : 46, |
| "Ios17.cos" : 36, |
| "Ios16.constexprLutToDense" : 101, |
| "Ios17.conv" : 54, |
| "Ios17.leakyRelu" : 13, |
| "Ios17.concat" : 6, |
| "Ios17.add" : 193, |
| "Ios17.convTranspose" : 3, |
| "Ios17.sliceByIndex" : 2, |
| "UpsampleNearestNeighbor" : 1, |
| "Ios16.reduceMean" : 1, |
| "Ios17.expandDims" : 4, |
| "Ios17.instanceNorm" : 42, |
| "Ios17.reshape" : 46, |
| "Split" : 46, |
| "Ios17.squeeze" : 1 |
| }, |
| "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" : "2026-04-27", |
| "com.github.apple.coremltools.source" : "torch==2.11.0", |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" |
| }, |
| "inputSchema" : [ |
| { |
| "dataType" : "Float16", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 512 × 1...2000", |
| "shapeRange" : "[[1, 1], [512, 512], [1, 2000]]", |
| "formattedType" : "MultiArray (Float16 1 × 512 × 120)", |
| "type" : "MultiArray", |
| "shape" : "[1, 512, 120]", |
| "name" : "asr", |
| "shortDescription" : "" |
| }, |
| { |
| "dataType" : "Float16", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 2...4000", |
| "shapeRange" : "[[1, 1], [2, 4000]]", |
| "formattedType" : "MultiArray (Float16 1 × 240)", |
| "type" : "MultiArray", |
| "shape" : "[1, 240]", |
| "name" : "F0_curve", |
| "shortDescription" : "" |
| }, |
| { |
| "dataType" : "Float16", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 2...4000", |
| "shapeRange" : "[[1, 1], [2, 4000]]", |
| "formattedType" : "MultiArray (Float16 1 × 240)", |
| "type" : "MultiArray", |
| "shape" : "[1, 240]", |
| "name" : "N_pred", |
| "shortDescription" : "" |
| }, |
| { |
| "dataType" : "Float16", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 256 × 1...40000", |
| "shapeRange" : "[[1, 1], [256, 256], [1, 40000]]", |
| "formattedType" : "MultiArray (Float16 1 × 256 × 2400)", |
| "type" : "MultiArray", |
| "shape" : "[1, 256, 2400]", |
| "name" : "x_source_0", |
| "shortDescription" : "" |
| }, |
| { |
| "dataType" : "Float16", |
| "hasShapeFlexibility" : "1", |
| "isOptional" : "0", |
| "shapeFlexibility" : "1 × 128 × 1...240001", |
| "shapeRange" : "[[1, 1], [128, 128], [1, 240001]]", |
| "formattedType" : "MultiArray (Float16 1 × 128 × 14401)", |
| "type" : "MultiArray", |
| "shape" : "[1, 128, 14401]", |
| "name" : "x_source_1", |
| "shortDescription" : "" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 128)", |
| "shortDescription" : "", |
| "shape" : "[1, 128]", |
| "name" : "style_timbre", |
| "type" : "MultiArray" |
| } |
| ], |
| "generatedClassName" : "KokoroVocoder", |
| "method" : "predict" |
| } |
| ] |
