<!--
{
  "availability" : [
    "iOS: 15.0.0 -",
    "iPadOS: 15.0.0 -",
    "macCatalyst: 15.0.0 -",
    "macOS: 10.15.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CreateML",
  "identifier" : "/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/init(validation:maxIterations:overlapFactor:)",
  "metadataVersion" : "0.1.0",
  "role" : "Initializer",
  "symbol" : {
    "kind" : "Initializer",
    "modules" : [
      "Create ML"
    ],
    "preciseIdentifier" : "s:8CreateML17MLSoundClassifierV15ModelParametersV10validation13maxIterations13overlapFactorA2E14ValidationDataO_SiSdtcfc"
  },
  "title" : "init(validation:maxIterations:overlapFactor:)"
}
-->

# init(validation:maxIterations:overlapFactor:)

Creates a new set of training parameters for a sound classifier with a validation dataset.

```
init(validation: MLSoundClassifier.ModelParameters.ValidationData = .split(strategy: .automatic), maxIterations: Int = 25, overlapFactor: Double = 0.5)
```

## Parameters

`validation`

A validation dataset represented by an
[`MLSoundClassifier.ModelParameters.ValidationData`](/documentation/CreateML/MLSoundClassifier/ModelParameters-swift.struct/ValidationData) instance.

`maxIterations`

The largest number of iterations the training session can use to train the sound
classifier.

`overlapFactor`

A proportion of overlap the training session uses to analyze two consecutive windows in
the audio data. The proportion must be in the range `[0.0, 1.0)`. Higher proportions generate more
training data, but also increases the training time.

    The default value is     `0.5`    , which represents a 50% overlap.

---

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)