[ { "metadataOutputVersion" : "3.0", "storagePrecision" : "Float16", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 49152)", "shortDescription" : "", "shape" : "[1, 49152]", "name" : "wav_tts", "type" : "MultiArray" } ], "modelParameters" : [ ], "specificationVersion" : 9, "functions" : [ { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 16)", "shortDescription" : "", "shape" : "[1, 144, 16]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 49152)", "shortDescription" : "", "shape" : "[1, 49152]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l16", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 32)", "shortDescription" : "", "shape" : "[1, 144, 32]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 98304)", "shortDescription" : "", "shape" : "[1, 98304]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l32", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 64)", "shortDescription" : "", "shape" : "[1, 144, 64]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 196608)", "shortDescription" : "", "shape" : "[1, 196608]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l64", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 128)", "shortDescription" : "", "shape" : "[1, 144, 128]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 393216)", "shortDescription" : "", "shape" : "[1, 393216]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l128", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 256)", "shortDescription" : "", "shape" : "[1, 144, 256]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 786432)", "shortDescription" : "", "shape" : "[1, 786432]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l256", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 384)", "shortDescription" : "", "shape" : "[1, 144, 384]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 1179648)", "shortDescription" : "", "shape" : "[1, 1179648]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l384", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } }, { "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 512)", "shortDescription" : "", "shape" : "[1, 144, 512]", "name" : "latent", "type" : "MultiArray" } ], "computePrecision" : "Mixed (Float16, Float32, Int32)", "storagePrecision" : "Float16", "stateSchema" : [ ], "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 1572864)", "shortDescription" : "", "shape" : "[1, 1572864]", "name" : "wav_tts", "type" : "MultiArray" } ], "name" : "vocoder_l512", "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 } } ], "mlProgramOperationTypeHistogram" : { "Ios18.mul" : 2, "Ios18.batchNorm" : 1, "Pad" : 12, "Ios18.gelu" : 10, "Ios18.layerNorm" : 10, "Ios18.transpose" : 22, "Ios18.leakyRelu" : 1, "Ios18.conv" : 33, "Ios18.add" : 11, "Ios18.reshape" : 3 }, "isUpdatable" : "0", "stateSchema" : [ ], "availability" : { "macOS" : "15.0", "tvOS" : "18.0", "visionOS" : "2.0", "watchOS" : "11.0", "iOS" : "18.0", "macCatalyst" : "18.0" }, "computePrecision" : "Mixed (Float16, Float32, Int32)", "modelType" : { "name" : "MLModelType_mlProgram" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 144 × 16)", "shortDescription" : "", "shape" : "[1, 144, 16]", "name" : "latent", "type" : "MultiArray" } ], "defaultFunctionName" : "vocoder_l16", "generatedClassName" : "Vocoder", "userDefinedMetadata" : { }, "method" : "predict" } ]