程序包 cn.smartjavaai.speech.asr.model

类 WhisperRecognizer

java.lang.Object

cn.smartjavaai.speech.asr.model.WhisperRecognizer

所有已实现的接口:

SpeechRecognizer, AutoCloseable

public class WhisperRecognizer
extends Object
implements SpeechRecognizer

作者:

dwj

构造器概要

构造器

构造器	说明
WhisperRecognizer()

方法概要

修饰符和类型	方法	说明
void	close()
io.github.givimad.whisperjni.WhisperState	getWhisperState()	获取一个WhisperState对象
boolean	isFromFactory()
void	loadModel(AsrModelConfig config)	加载模型
io.github.givimad.whisperjni.WhisperGrammar	parseGrammar(String grammarText)
R<AsrResult>	recognize(byte[] audioData)
R<AsrResult>	recognize(byte[] audioData, RecParams params)
R<AsrResult>	recognize(ai.djl.modality.audio.Audio audio, RecParams params)
R<AsrResult>	recognize(InputStream audioStream)
R<AsrResult>	recognize(InputStream audioStream, RecParams params)
R<AsrResult>	recognize(String audioPath)
R<AsrResult>	recognize(String audioPath, RecParams params)
void	setFromFactory(boolean fromFactory)

从类继承的方法 java.lang.Object

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

从接口继承的方法 cn.smartjavaai.speech.asr.model.SpeechRecognizer

recognize

构造器详细资料

WhisperRecognizer

public WhisperRecognizer()

方法详细资料

loadModel

public void loadModel(AsrModelConfig config)

从接口复制的说明: SpeechRecognizer

加载模型

指定者:

loadModel 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(String audioPath,
                              RecParams params)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(byte[] audioData,
                              RecParams params)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(InputStream audioStream,
                              RecParams params)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(ai.djl.modality.audio.Audio audio,
                              RecParams params)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(String audioPath)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(byte[] audioData)

指定者:

recognize 在接口中 SpeechRecognizer

recognize

public R<AsrResult> recognize(InputStream audioStream)

指定者:

recognize 在接口中 SpeechRecognizer

parseGrammar

public io.github.givimad.whisperjni.WhisperGrammar parseGrammar(String grammarText)

close

public void close()
           throws Exception

指定者:

close 在接口中 AutoCloseable

抛出:

Exception

getWhisperState

public io.github.givimad.whisperjni.WhisperState getWhisperState()

获取一个WhisperState对象

返回:

setFromFactory

public void setFromFactory(boolean fromFactory)

指定者:

setFromFactory 在接口中 SpeechRecognizer

isFromFactory

public boolean isFromFactory()