语音转文本接口实现步骤

贩卖快乐的码农

于 2024-07-19 16:24:51 发布

阅读量96

点赞数 2

本文链接：https://blog.csdn.net/u014404087/article/details/140552224

版权

1.申请科大语音转写APPID

2.maven pom.xml引入

<dependency>
     <groupId>org.springframework</groupId>
     <artifactId>spring-mock</artifactId>
     <version>2.0.8</version>
</dependency>

<dependency>
	 <groupId>com.iflytek</groupId>
	 <artifactId>Msc</artifactId>
	 <version>1.0.1</version>
</dependency>

3.代码实现

package com.iflytek;

import com.iflytek.cloud.speech.*;
import org.apache.http.entity.ContentType;
import org.springframework.mock.web.MockMultipartFile;
import org.springframework.web.multipart.MultipartFile;
import java.io.*;

public class VoiceTool {

	/**
     * 音频文件
     */
    public static String audioPath = "D:\\***\\16k_10.pcm";///home/asr/my.pcm"; 也可转成wav格式
    private StringBuilder sb;
    private SpeechRecognizer speechRecognizer;
    private Object lock = new Object();
 
    public VoiceTool(String appId){
        SpeechUtility.createUtility(SpeechConstant.APPID + "=" + appId);
    }
 
    public String RecognizePcmfileByte(MultipartFile audioFile) {
        sb = new StringBuilder();
        try {
            if (speechRecognizer == null) {//参数可以在配置文件设置
                speechRecognizer = SpeechRecognizer.createRecognizer();
                speechRecognizer.setParameter(SpeechConstant.AUDIO_SOURCE, "-1");
                speechRecognizer.setParameter( SpeechConstant.RESULT_TYPE, "plain" );
                speechRecognizer.setParameter(SpeechConstant.VAD_BOS,"5000");//前端点超时，
                speechRecognizer.setParameter(SpeechConstant.VAD_EOS,"10000");//后端点超时要与运行SDK时配置的一样
            }
            speechRecognizer.startListening(recListener);
            byte[] buffer = audioFile.getBytes();
            if (buffer == null || buffer.length == 0) {
                speechRecognizer.cancel();
            } else {
                int lenRead = buffer.length;
                speechRecognizer.writeAudio( buffer, 0, lenRead );
                speechRecognizer.stopListening();
                synchronized (lock) {
                    lock.wait();//主线程等待
                }
                return sb.toString();
            }
 
        } catch (Exception e) {
            e.printStackTrace();
        }
        return null;
    }
    private RecognizerListener recListener = new RecognizerListener() {
        @Override
        public void onBeginOfSpeech() {
            
        }
        @Override
        public void onEndOfSpeech() {
            
        }
        /**
         * 获取听写结果
         */
        @Override
        public void onResult(RecognizerResult results, boolean islast) {
                //用json解析器解析为json格式
            String text = results.getResultString();
            sb.append(text);
            //log.info("解析结果："+curRet.toString());
            if( islast ) {
                synchronized (lock) {
                    lock.notify();//子线程唤醒
                }
            }
        }
        @Override
        public void onVolumeChanged(int volume) {
           
        }
 
        @Override
        public void onError(SpeechError error) {
            
        }
        @Override
        public void onEvent(int eventType, int arg1, int agr2, String msg) {
            
        }
    }; 
    
    public static void main(String args[]) throws IOException {
        VoiceTool iatTool = new VoiceTool("你的APPID");
        File file = new File(audioPath);
        FileInputStream fileInputStream = new FileInputStream(file);
        MultipartFile multipartFile = new MockMultipartFile(file.getName(), file.getName(),
                ContentType.APPLICATION_OCTET_STREAM.toString(), fileInputStream);
        String result = iatTool.RecognizePcmfileByte(multipartFile);
        System.out.println(result);
    }
	
}