AutomaticSpeechRecognitionPipeline

Speech recognition over an SttModel: a clip's mono 16-bit samples answer its transcript.

Properties

Name	Summary
model	[common] open override val model: SttModel The loaded model the pipeline runs.
task	[common] val task: String The task the pipeline serves, in transformers' spelling.

Name	Summary
close	[common] open fun close(): <Error class: unknown class>
invoke	[common] operator fun invoke(pcm16: ShortArray, sampleRate: Int, options: TranscribeOptions = TranscribeOptions()): String
transcribe	[common] fun transcribe(pcm16: ShortArray, sampleRate: Int, options: TranscribeOptions = TranscribeOptions()): Transcript The transcript with its report: the text, and among the report's facts the language the clip was read in.