<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 12.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLSoundClassifier/FeatureExtractionParameters/init(overlapFactor:featureExtractor:featureExtractionTimeWindowSize:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLSoundClassifierV27FeatureExtractionParametersV13overlapFactor16featureExtractor0jF14TimeWindowSizeAESd_AC05ModelG0V0eK4TypeOSdSgtcfc"
  },
  "title" : "init(overlapFactor:featureExtractor:featureExtractionTimeWindowSize:)"
}
-->

# init(overlapFactor:featureExtractor:featureExtractionTimeWindowSize:)

Creates the parameters for a feature-extraction session.

```
init(overlapFactor: Double = __Defaults.overlapFactor, featureExtractor: MLSoundClassifier.ModelParameters.FeatureExtractorType = __Defaults.featureExtractor, featureExtractionTimeWindowSize: TimeInterval?)
```

## Parameters

`overlapFactor`

A portion of overlap between consecutive audio analysis windows. The value must be in
the range `[0.0, 1.0)`.

`featureExtractor`

An algorithm type the session uses to extract features from audio files.

`featureExtractionTimeWindowSize`

A time duration, in seconds, the feature-extraction session uses for
each audio sample it reads from an audio file in a dataset. The value must be in the range
`[0.5, 15.0]`.

---

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)