[ { "metadataOutputVersion" : "3.0", "shortDescription" : "StyleTTS2 HiFi-GAN decoder (LibriTTS) @ T_mel=2048. 24 kHz, hop=300.", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1 × 1228800)", "shortDescription" : "", "shape" : "[1, 1, 1228800]", "name" : "waveform", "type" : "MultiArray" } ], "storagePrecision" : "Float32", "modelParameters" : [ ], "specificationVersion" : 8, "mlProgramOperationTypeHistogram" : { "Ios17.greater" : 1, "UpsampleNearestNeighbor" : 2, "Ios17.floor" : 1, "Ios17.instanceNorm" : 98, "Ios17.reshape" : 110, "Ios17.transpose" : 8, "Ios17.sin" : 103, "Split" : 106, "Ios17.convTranspose" : 5, "Ios17.expandDims" : 4, "Ios17.add" : 381, "Tile" : 2, "Ios17.sliceByIndex" : 6, "Ios17.squeeze" : 2, "Ios17.conv" : 119, "Ios17.sub" : 2, "Ios17.cast" : 1, "Ios17.tanh" : 2, "Ios17.pow" : 101, "Ios17.linear" : 107, "Ios17.leakyRelu" : 10, "Ios17.concat" : 6, "Ios16.cumsum" : 1, "Ios17.mul" : 331 }, "computePrecision" : "Mixed (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" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512 × 2048)", "shortDescription" : "", "shape" : "[1, 512, 2048]", "name" : "asr", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 4096)", "shortDescription" : "", "shape" : "[1, 4096]", "name" : "F0_curve", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 4096)", "shortDescription" : "", "shape" : "[1, 4096]", "name" : "N", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128)", "shortDescription" : "", "shape" : "[1, 128]", "name" : "s", "type" : "MultiArray" } ], "userDefinedMetadata" : { "com.github.apple.coremltools.version" : "8.3.0", "com.github.apple.coremltools.source" : "torch==2.11.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "generatedClassName" : "styletts2_decoder_2048", "method" : "predict" } ]