<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 11.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType",
  "metadataVersion" : "0.1.0",
  "role" : "Enumeration",
  "symbol" : {
    "kind" : "Enumeration",
    "modules" : [
      "Create ML",
      "CreateML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLSoundClassifierV15ModelParametersV20FeatureExtractorTypeO"
  },
  "title" : "MLSoundClassifier.ModelParameters.FeatureExtractorType"
}
-->

# MLSoundClassifier.ModelParameters.FeatureExtractorType

The feature-extractor options for a sound-classifier training algorithm.

```
enum FeatureExtractorType
```

## Overview

Use the [`MLSoundClassifier.ModelParameters.FeatureExtractorType.audioFeaturePrint(type:revision:)`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType/audioFeaturePrint(type:revision:))
feature extractor to create a model with the following advantages over `vggish`:

- More accurate predictions
- Lower latency
- Smaller model file size
- Less training time

Use [`MLSoundClassifier.ModelParameters.FeatureExtractorType.vggish(revision:)`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType/vggish(revision:)) to support older
OS versions.

## Topics

### Designating a feature extractor

[`case audioFeaturePrint(type: MLSoundClassifier.ModelParameters.FeaturePrintType, revision: Int)`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType/audioFeaturePrint(type:revision:))

Represents the Audio Feature Print extractor.

[`enum FeaturePrintType`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeaturePrintType)

The type options for an Audio Feature Print feature extractor.

[`case vggish(revision: Int)`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType/vggish(revision:))

Represents the VGGish feature extractor, which is compatible with older OS versions.

### Describing a feature extractor

[`var description: String`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/FeatureExtractorType/description)

A text representation of the feature-extractor type.

## Relationships

### Conforms To

[`SendableMetatype`](/documentation/Swift/SendableMetatype)

[`Sendable`](/documentation/Swift/Sendable)

[`CustomStringConvertible`](/documentation/Swift/CustomStringConvertible)

[`Equatable`](/documentation/Swift/Equatable)

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)