[ { "metadataOutputVersion" : "3.0", "shortDescription" : "Fluid Speech Pro by FluidVoice (fp16): decoder (RNNT prediction network)", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 640 × 1)", "shortDescription" : "", "shape" : "[1, 640, 1]", "name" : "decoder", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 640)", "shortDescription" : "", "shape" : "[2, 1, 640]", "name" : "h_out", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 640)", "shortDescription" : "", "shape" : "[2, 1, 640]", "name" : "c_out", "type" : "MultiArray" } ], "storagePrecision" : "Float16", "modelParameters" : [ ], "author" : "FluidVoice", "specificationVersion" : 9, "license" : "CC-BY-4.0", "mlProgramOperationTypeHistogram" : { "Select" : 1, "Ios18.lstm" : 2, "Ios18.gather" : 1, "Stack" : 2, "Identity" : 1, "Split" : 2, "Ios18.transpose" : 2, "Ios18.squeeze" : 4, "Ios18.cast" : 8, "Ios18.greaterEqual" : 1, "Ios18.add" : 1 }, "computePrecision" : "Mixed (Float16, Float32, Int16, Int32)", "stateSchema" : [ ], "isUpdatable" : "0", "availability" : { "macOS" : "15.0", "tvOS" : "18.0", "visionOS" : "2.0", "watchOS" : "11.0", "iOS" : "18.0", "macCatalyst" : "18.0" }, "modelType" : { "name" : "MLModelType_mlProgram" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1 × 1)", "shortDescription" : "", "shape" : "[1, 1]", "name" : "targets", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Int32", "formattedType" : "MultiArray (Int32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "target_length", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 640)", "shortDescription" : "", "shape" : "[2, 1, 640]", "name" : "h_in", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 640)", "shortDescription" : "", "shape" : "[2, 1, 640]", "name" : "c_in", "type" : "MultiArray" } ], "userDefinedMetadata" : { "com.github.apple.coremltools.conversion_date" : "2026-11-02", "fluidspeech.source" : "FluidVoice-Labs\/fluid-speech-pro@53f490b9292c5943847f635b7abfc3f123018964", "com.github.apple.coremltools.source" : "torch==2.7.0", "com.github.apple.coremltools.version" : "9.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "generatedClassName" : "Decoder", "method" : "predict" } ]