[
  {
    "shortDescription" : "Voxtral Audio Encoder (Mini) for Apple devices",
    "metadataOutputVersion" : "3.0",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32 1 × 375 × 3072)",
        "shortDescription" : "",
        "shape" : "[1, 375, 3072]",
        "name" : "audio_embeddings",
        "type" : "MultiArray"
      }
    ],
    "version" : "2.1.0",
    "modelParameters" : [

    ],
    "author" : "Voxtral Conversion",
    "specificationVersion" : 7,
    "storagePrecision" : "Float16",
    "mlProgramOperationTypeHistogram" : {
      "Ios16.cast" : 2,
      "Ios16.add" : 65,
      "Ios16.mul" : 32,
      "Ios16.matmul" : 64,
      "Ios16.softmax" : 32,
      "Transpose" : 129,
      "Ios16.gelu" : 35,
      "Ios16.linear" : 194,
      "Ios16.reshape" : 129,
      "Ios16.layerNorm" : 65,
      "Ios16.conv" : 2
    },
    "computePrecision" : "Mixed (Float16, Float32, Int32)",
    "stateSchema" : [

    ],
    "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"
    },
    "inputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float32",
        "formattedType" : "MultiArray (Float32 1 × 128 × 3000)",
        "shortDescription" : "",
        "shape" : "[1, 128, 3000]",
        "name" : "mel_spectrogram",
        "type" : "MultiArray"
      }
    ],
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.conversion_date" : "2026-01-29",
      "com.github.apple.coremltools.source" : "torch==2.7.0",
      "com.github.apple.coremltools.version" : "9.0",
      "com.github.apple.coremltools.source_dialect" : "TorchScript"
    },
    "generatedClassName" : "VoxtralEncoderMini",
    "method" : "predict"
  }
]