当前位置：首页 > news >正文

jdk21使用Vosk实现语音文字转换，免费的语音识别

news 来源：原创 2025/5/16 8:20:08

1.下载vosk的model

vosk官网：https://alphacephei.com/vosk/models
我这里使用较小的vosk-model-small-cn-0.22

2.添加相关pom文件

 <!-- 获取音频信息 -->
        <dependency>
            <groupId>org</groupId>
            <artifactId>jaudiotagger</artifactId>
            <version>2.0.3</version>
        </dependency>

        <!-- 语音识别 -->
        <dependency>
            <groupId>net.java.dev.jna</groupId>
            <artifactId>jna</artifactId>
            <version>5.16.0</version>
        </dependency>
        <dependency>
            <groupId>com.alphacephei</groupId>
            <artifactId>vosk</artifactId>
            <version>0.3.45</version>
        </dependency>

3.代码

添加model和使用的音频，我这里用的wav格式的，不同格式的参数会不一样


import org.vosk.LibVosk;
import org.vosk.LogLevel;
import org.vosk.Model;
import org.vosk.Recognizer;

import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.UnsupportedAudioFileException;
import java.io.*; 

public class testVosk {
    public static void main(String[] argv) throws IOException, UnsupportedAudioFileException {
        LibVosk.setLogLevel(LogLevel.DEBUG);

        try (Model model = new Model("E:\\srk\\bigData\\vosk-model-small-cn-0.22");
             InputStream fis = AudioSystem.getAudioInputStream(new BufferedInputStream(new FileInputStream("C:\\Users\\Administrator\\Downloads\\mdhs1-5ob2k.wav")));
             Recognizer recognizer = new Recognizer(model, 16000)) {
            int bytes;
            byte[] b = new byte[4096];
            while ((bytes = fis.read(b)) >= 0) {
                if (recognizer.acceptWaveForm(b, bytes)) {
                    System.out.println(recognizer.getResult());
                } else {
                    System.out.println(recognizer.getPartialResult());
                }
            }
            String result = recognizer.getFinalResult();
            System.out.println(result);
        }

    }
}