[
  {
    "metadataOutputVersion" : "3.0",
    "storagePrecision" : "Float16",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32 1 × 390 × 1024)",
        "shortDescription" : "",
        "shape" : "[1, 390, 1024]",
        "name" : "audio_embeddings",
        "type" : "MultiArray"
      }
    ],
    "modelParameters" : [

    ],
    "specificationVersion" : 9,
    "mlProgramOperationTypeHistogram" : {
      "Ios18.mul" : 18,
      "Ios18.softmax" : 18,
      "Ios18.linear" : 111,
      "Ios18.gelu" : 22,
      "Ios18.layerNorm" : 37,
      "Ios18.transpose" : 74,
      "Ios18.matmul" : 36,
      "Ios18.cast" : 3,
      "Ios18.conv" : 3,
      "Ios18.reshape" : 76,
      "Ios18.add" : 55
    },
    "computePrecision" : "Mixed (Float16, Float32, Int32)",
    "isUpdatable" : "0",
    "stateSchema" : [

    ],
    "availability" : {
      "macOS" : "15.0",
      "tvOS" : "18.0",
      "visionOS" : "2.0",
      "watchOS" : "11.0",
      "iOS" : "18.0",
      "macCatalyst" : "18.0"
    },
    "modelType" : {
      "name" : "MLModelType_mlProgram"
    },
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.conversion_date" : "2026-07-15",
      "com.github.apple.coremltools.source" : "torch==2.7.0",
      "com.github.apple.coremltools.version" : "9.0",
      "com.github.apple.coremltools.source_dialect" : "TorchScript"
    },
    "inputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32 1 × 128 × 3000)",
        "shortDescription" : "",
        "shape" : "[1, 128, 3000]",
        "name" : "mel_features",
        "type" : "MultiArray"
      },
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32 1 × 1 × 390 × 390)",
        "shortDescription" : "",
        "shape" : "[1, 1, 390, 390]",
        "name" : "attention_mask",
        "type" : "MultiArray"
      }
    ],
    "generatedClassName" : "audio_3000",
    "method" : "predict"
  }
]