[
  {
    "metadataOutputVersion" : "3.0",
    "storagePrecision" : "Float16",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 1280 × 1 × 1500)",
        "shortDescription" : "",
        "shape" : "[1, 1280, 1, 1500]",
        "name" : "encoder_output_embeds",
        "type" : "MultiArray"
      }
    ],
    "modelParameters" : [

    ],
    "specificationVersion" : 7,
    "mlProgramOperationTypeHistogram" : {
      "Concat" : 672,
      "Ios16.rsqrt" : 65,
      "Ios16.mul" : 2690,
      "SliceByIndex" : 4480,
      "Ios16.sub" : 65,
      "Transpose" : 32,
      "Ios16.einsum" : 5120,
      "Ios16.conv" : 194,
      "Ios16.add" : 130,
      "Ios16.reduceMean" : 130,
      "Ios16.softmax" : 2560,
      "Ios16.gelu" : 34,
      "Ios16.batchNorm" : 65
    },
    "computePrecision" : "Mixed (Float16, Int32)",
    "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"
    },
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.source_dialect" : "TorchScript",
      "com.github.apple.coremltools.version" : "7.1",
      "com.github.apple.coremltools.source" : "torch==2.2.2"
    },
    "inputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 128 × 1 × 3000)",
        "shortDescription" : "",
        "shape" : "[1, 128, 1, 3000]",
        "name" : "melspectrogram_features",
        "type" : "MultiArray"
      }
    ],
    "generatedClassName" : "AudioEncoder",
    "method" : "predict"
  }
]