【JAVA】使用vosk实现windows实时语音转文字，解放双手

使用到的三方包
jna-5.11.0.jar jna-platform-5.11.0.jar vosk-0.3.45.jar
具体代码实现

package sample;import org.vosk.Model;
import org.vosk.Recognizer;import javax.sound.sampled.*;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;/*** https://alphacephei.com/vosk/models* vosk.alphacephei.com* https://repo1.maven.org/maven2/com/alphacephei/vosk/0.3.45/*/
public class VoskJavaExample {// 音频格式参数配置private static final AudioFormat.Encoding ENCODING = AudioFormat.Encoding.PCM_SIGNED;private static final float RATE = 44100.0f;     // 采样率private static final int SAMPLE_SIZE = 16;      // 采样位数private static final int CHANNELS = 1;          // 声道数（1-单声道，2-立体声）private static final boolean BIG_ENDIAN = true; // 字节顺序public static void main(String[] args) {writeOutResult(getVoiceDoc());}public static void writeOutResult(String wavPath){try {// 1. 加载模型（替换为你的模型路径，如"vosk-model-cn-0.22"）Model model = new Model("D:\\download\\vosk-model-small-cn-0.22\\vosk-model-small-cn-0.22");// 2. 初始化识别器（采样率必须与音频文件一致，此处为16000Hz）org.vosk.Recognizer recognizer = new org.vosk.Recognizer(model, 44100.0f);// 3. 读取音频文件（需为符合要求的WAV文件）try (FileInputStream fis = new FileInputStream(wavPath)) {byte[] buffer = new byte[4096]; // 缓冲区大小int bytesRead;// 4. 逐段处理音频流while ((bytesRead = fis.read(buffer)) != -1) {// 调用acceptWaveform，传入字节数组和实际读取的长度if (recognizer.acceptWaveForm(buffer, bytesRead)) {// 输出实时识别结果System.out.println("实时结果：" + recognizer.getResult());}}// 5. 处理剩余音频，输出最终结果System.out.println("最终结果：" + recognizer.getFinalResult());}// 释放资源model.close();recognizer.close();} catch (IOException e) {e.printStackTrace();}}public static String getVoiceDoc(){try {// 1. 设置音频格式AudioFormat format = new AudioFormat(ENCODING, RATE, SAMPLE_SIZE, CHANNELS,(SAMPLE_SIZE/8)*CHANNELS, RATE, BIG_ENDIAN);// 2. 获取音频输入设备（麦克风）DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);if (!AudioSystem.isLineSupported(info)) {System.err.println("不支持指定的音频格式");return null;}// 3. 打开并启动录音线路TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info);line.open(format);line.start();System.out.println("开始录音...（按回车键停止）");// 4. 创建音频输入流AudioInputStream audioInputStream = new AudioInputStream(line);// 5. 创建输出文件File audioFile = new File("D:\\download\\savedVoice\\recording.wav");// 6. 启动独立线程处理录音停止new Thread(() -> {try {// 等待用户输入停止System.in.read();line.stop();line.close();System.out.println("录音已停止");} catch (IOException e) {e.printStackTrace();}}).start();// 7. 将音频流写入文件AudioSystem.write(audioInputStream, AudioFileFormat.Type.WAVE, audioFile);System.out.println("录音已保存到：" + audioFile.getAbsolutePath());} catch (LineUnavailableException | IOException e) {e.printStackTrace();}return "D:\\download\\savedVoice\\recording.wav";}
}