---
title: featureExtractionTimeWindowSize
framework: createml
role: symbol
role_heading: Instance Property
path: createml/mlsoundclassifier/modelparameters-swift.struct/featureextractiontimewindowsize
---

# featureExtractionTimeWindowSize

A time duration, in seconds, the training session uses for each audio sample it reads from an audio file in a dataset.

## Declaration

```swift
var featureExtractionTimeWindowSize: TimeInterval { get set }
```

## Discussion

Discussion The time-window size value defaults to 0.975 seconds and must be in the range [0.5, 15.0]. Training sessions that use MLSoundClassifier.ModelParameters.FeatureExtractorType.vggish(revision:) ignore this value and always use a time-window size of 0.975 seconds.

## See Also

### Accessing the training parameters

- [validation](createml/mlsoundclassifier/modelparameters-swift.struct/validation.md)
- [maxIterations](createml/mlsoundclassifier/modelparameters-swift.struct/maxiterations.md)
- [overlapFactor](createml/mlsoundclassifier/modelparameters-swift.struct/overlapfactor.md)
- [algorithm](createml/mlsoundclassifier/modelparameters-swift.struct/algorithm.md)