Package ai.djl.modality.audio.translator

Class SpeechRecognitionTranslator

java.lang.Object

ai.djl.modality.audio.translator.SpeechRecognitionTranslator

All Implemented Interfaces:

NoBatchifyTranslator<Audio,java.lang.String>, PostProcessor<java.lang.String>, PreProcessor<Audio>, Translator<Audio,java.lang.String>

public class SpeechRecognitionTranslator
extends java.lang.Object
implements NoBatchifyTranslator<Audio,java.lang.String>

A Translator that post-process the Audio into String to get a text translation of the audio.

Constructor Summary

Constructors

Constructor	Description
SpeechRecognitionTranslator()

Method Summary

Modifier and Type	Method	Description
NDList	processInput(TranslatorContext ctx, Audio input)	Processes the input and converts it to NDList.
java.lang.String	processOutput(TranslatorContext ctx, NDList list)	Processes the output NDList to the corresponding output object.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface ai.djl.translate.NoBatchifyTranslator

getBatchifier

Methods inherited from interface ai.djl.translate.Translator

getExpansions, prepare, toBatchTranslator, toBatchTranslator

Constructor Detail

SpeechRecognitionTranslator

public SpeechRecognitionTranslator()

Method Detail

processInput

public NDList processInput(TranslatorContext ctx,
                           Audio input)
                    throws java.lang.Exception

Processes the input and converts it to NDList.

Specified by:

processInput in interface PreProcessor<Audio>

Parameters:

ctx - the toolkit for creating the input NDArray

input - the input object

Returns:

the NDList after pre-processing

Throws:

java.lang.Exception - if an error occurs during processing input

processOutput

public java.lang.String processOutput(TranslatorContext ctx,
                                      NDList list)
                               throws java.lang.Exception

Processes the output NDList to the corresponding output object.

Specified by:

processOutput in interface PostProcessor<java.lang.String>

Parameters:

ctx - the toolkit used for post-processing

list - the output NDList after inference, usually immutable in engines like PyTorch. @see Issue 1774

Returns:

the output object of expected type

Throws:

java.lang.Exception - if an error occurs during processing output