Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

AudioEmbedderResult

public abstract class AudioEmbedderResult

Represents the embedding results generated by AudioEmbedder.

Public Constructors

AudioEmbedderResult()

Public Methods

abstract List<EmbeddingResult>	embeddingResults() A list of of timpstamped `EmbeddingResult` objects, each contains one set of results per embedder head.
abstract long	timestampMs() Returns the timestamp that is associated with the task result object.

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface com.google.mediapipe.tasks.core.TaskResult

abstract long

timestampMs()

Returns the timestamp that is associated with the task result object.

Public Constructors

public AudioEmbedderResult ()

Public Methods

public abstract List<EmbeddingResult> embeddingResults ()

A list of of timpstamped EmbeddingResult objects, each contains one set of results per embedder head.

In the "audio stream" mode, the list only contains one element, representing the embedding result of the audio block that starts at ERROR(/EmbeddingResult.timestampMs) in the audio stream. Otherwise, in the "audio clips" mode, the list may include multiple EmbeddingResult objects, each contains the embedding of an interval of the entire audio clip that starts at ERROR(/EmbeddingResult.timestampMs).

public abstract long timestampMs ()

Returns the timestamp that is associated with the task result object.