[ { "metadataOutputVersion" : "3.0", "storagePrecision" : "Float32", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1 × 120000)", "shortDescription" : "", "shape" : "[1, 1, 120000]", "name" : "audio", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "audio_length_samples", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128)", "shortDescription" : "", "shape" : "[1, 128]", "name" : "pred_dur", "type" : "MultiArray" } ], "modelParameters" : [ ], "specificationVersion" : 8, "mlProgramOperationTypeHistogram" : { "Ios17.greater" : 4, "Ios17.greaterEqual" : 3, "Ios17.gather" : 2, "Ios17.logicalAnd" : 6, "Ios17.atan" : 1, "Ios17.gatherAlongAxis" : 2, "Ios17.cos" : 1, "Ios17.exp" : 1, "UpsampleNearestNeighbor" : 4, "Ios17.sub" : 5, "Identity" : 1, "Ios17.instanceNorm" : 65, "Ios17.clip" : 1, "Ios16.reduceSum" : 3, "Ios17.leakyRelu" : 28, "Ios16.cumsum" : 121, "Ios17.equal" : 2, "Pad" : 2, "Shape" : 1, "Ios17.round" : 1, "Ios17.sliceByIndex" : 249, "Ios17.lstm" : 6, "Ios17.concat" : 12, "Ios17.pow" : 50, "NonZero" : 1, "Ios17.sqrt" : 1, "Ios17.convTranspose" : 7, "Ios17.minimum" : 1, "Ios17.expandDims" : 16, "Ios17.less" : 5, "Ios17.mul" : 216, "Ios17.transpose" : 82, "Ios17.matmul" : 24, "Ios16.sigmoid" : 1, "Ios17.maximum" : 1, "Ios16.gelu" : 12, "Ios17.reshape" : 121, "Split" : 73, "Ios17.cast" : 13, "Ios17.conv" : 90, "Ios17.squeeze" : 8, "Ios17.linear" : 149, "Ios17.sin" : 51, "Ios17.tanh" : 1, "Ios17.realDiv" : 2, "Select" : 11, "Ios17.scatterNd" : 1, "Ios16.softmax" : 12, "Ios17.add" : 399, "Ios17.layerNorm" : 31, "Tile" : 4 }, "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" }, "userDefinedMetadata" : { "com.github.apple.coremltools.source_dialect" : "TorchScript", "com.github.apple.coremltools.source" : "torch==2.3.1", "com.github.apple.coremltools.version" : "8.3.0" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1 × 128)", "shortDescription" : "", "shape" : "[1, 128]", "name" : "input_ids", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1 × 128)", "shortDescription" : "", "shape" : "[1, 128]", "name" : "attention_mask", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 256)", "shortDescription" : "", "shape" : "[1, 256]", "name" : "ref_s", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "speed", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 9)", "shortDescription" : "", "shape" : "[1, 9]", "name" : "random_phases", "type" : "MultiArray" } ], "generatedClassName" : "kokoro_5s", "method" : "predict" } ]