[
  {
    "metadataOutputVersion" : "3.0",
    "storagePrecision" : "Float16",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 1500)",
        "shortDescription" : "",
        "shape" : "[1, 1024, 1, 1500]",
        "name" : "encoder_output_embeds",
        "type" : "MultiArray"
      }
    ],
    "modelParameters" : [

    ],
    "specificationVersion" : 7,
    "mlProgramOperationTypeHistogram" : {
      "Ios16.softmax" : 24,
      "Ios16.add" : 49,
      "Ios16.mul" : 24,
      "Ios16.batchNorm" : 49,
      "Ios16.gelu" : 26,
      "Ios16.reshape" : 96,
      "Ios16.matmul" : 48,
      "Ios16.layerNorm" : 49,
      "Ios16.conv" : 146
    },
    "computePrecision" : "Mixed (Float16, Int32)",
    "isUpdatable" : "0",
    "stateSchema" : [

    ],
    "availability" : {
      "macOS" : "13.0",
      "tvOS" : "16.0",
      "visionOS" : "1.0",
      "watchOS" : "9.0",
      "iOS" : "16.0",
      "macCatalyst" : "16.0"
    },
    "modelType" : {
      "name" : "MLModelType_mlProgram"
    },
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.version" : "8.2",
      "com.github.apple.coremltools.source" : "torch==2.5.0",
      "com.github.apple.coremltools.source_dialect" : "TorchScript"
    },
    "inputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 80 × 1 × 3000)",
        "shortDescription" : "",
        "shape" : "[1, 80, 1, 3000]",
        "name" : "melspectrogram_features",
        "type" : "MultiArray"
      }
    ],
    "generatedClassName" : "AudioEncoder",
    "method" : "predict"
  }
]