[ { "shortDescription" : "Token and duration prediction for TDT decoder", "metadataOutputVersion" : "3.0", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_17", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "reduce_max_0", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_24", "type" : "MultiArray" } ], "version" : "1.0", "modelParameters" : [ ], "author" : "FluidAudio", "specificationVersion" : 7, "mlProgramOperationTypeHistogram" : { "SliceByIndex" : 2, "Ios16.reduceArgmax" : 2, "Ios16.reshape" : 1, "Ios16.reduceMax" : 1 }, "computePrecision" : "Mixed (Float16, Int32)", "stateSchema" : [ ], "isUpdatable" : "0", "availability" : { "macOS" : "13.0", "tvOS" : "16.0", "visionOS" : "1.0", "watchOS" : "9.0", "iOS" : "16.0", "macCatalyst" : "16.0" }, "modelType" : { "name" : "MLModelType_mlProgram" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1030)", "shortDescription" : "", "shape" : "[1, 1, 1, 1030]", "name" : "logits", "type" : "MultiArray" } ], "userDefinedMetadata" : { "com.github.apple.coremltools.source_dialect" : "TorchScript", "com.github.apple.coremltools.source" : "torch==2.5.0", "com.github.apple.coremltools.version" : "8.3.0" }, "generatedClassName" : "TokenDurationPrediction", "method" : "predict" } ]