ModelBenchmark class

Model benchmark for comparing different Whisper models.

Constructors

ModelBenchmark({required String modelName, required String audioFile, required Duration transcriptionTime, required Duration audioDuration, int? wordCount, double? accuracy, int? memoryUsedMB})

const

Properties

accuracy → double?

Accuracy score (0-1) if reference available.

final

audioDuration → Duration

Audio duration.

final

audioFile → String

Audio file used.

final

hashCode → int

The hash code for this object.

no setter, inherited

memoryUsedMB → int?

Memory used in MB.

final

modelName → String

Model name.

final

realTimeFactor → double

Real-time factor (lower is better).

no setter

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

transcriptionTime → Duration

Time to transcribe.

final

wordCount → int?

Number of words transcribed.

final

wordsPerSecond → double?

Words per second.

no setter

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

override

Operators

operator ==(Object other) → bool

The equality operator.

inherited