[ { "metadataOutputVersion" : "3.0", "shortDescription" : "CLAP audio encoder (spectrogram-input): mel [1,1,1001,64] -> 512-d joint embedding, L2-norm applied by the caller", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512)", "shortDescription" : "", "shape" : "[1, 512]", "name" : "audio_embeds", "type" : "MultiArray" } ], "storagePrecision" : "Float16", "modelParameters" : [ ], "author" : "clapkit T1: laion\/clap-htsat-unfused audio tower (HTSAT + audio_projection), pre-norm", "specificationVersion" : 8, "mlProgramOperationTypeHistogram" : { "Ios17.mul" : 12, "Ios17.linear" : 77, "Ios17.transpose" : 79, "Ios17.matmul" : 25, "Ios17.conv" : 1, "Ios17.gather" : 20, "Ios17.add" : 41, "Ios17.sliceByIndex" : 18, "Ios17.batchNorm" : 1, "Ios17.concat" : 4, "Ios16.softmax" : 12, "Ios16.gelu" : 12, "Ios16.reduceMean" : 1, "Ios16.relu" : 1, "Ios17.reshape" : 130, "Ios17.layerNorm" : 29, "Ios17.cast" : 2 }, "computePrecision" : "Mixed (Float16, Float32, Int32, UInt16)", "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 × 1 × 1001 × 64)", "shortDescription" : "", "shape" : "[1, 1, 1001, 64]", "name" : "input_features", "type" : "MultiArray" } ], "userDefinedMetadata" : { "com.github.apple.coremltools.conversion_date" : "2026-07-18", "com.github.apple.coremltools.source" : "torch==2.5.1", "com.github.apple.coremltools.version" : "9.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "generatedClassName" : "clap_audio", "method" : "predict" } ]