阅读量:4
1. 语音转文字
1.1 maven导入以下包
<!-- 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>5.7.0</version> </dependency> <dependency> <groupId>com.alphacephei</groupId> <artifactId>vosk</artifactId> <version>0.3.32</version> </dependency>
1.2 编写代码
import java.io.FileInputStream; import java.io.BufferedInputStream; import java.io.IOException; import java.io.InputStream; import javax.sound.sampled.AudioSystem; import javax.sound.sampled.UnsupportedAudioFileException; import org.vosk.LogLevel; import org.vosk.Recognizer; import org.vosk.LibVosk; import org.vosk.Model; public class DecoderDemo { public static void main(String[] argv) throws IOException, UnsupportedAudioFileException { LibVosk.setLogLevel(LogLevel.DEBUG); try (Model model = new Model("D:\\model\\vosk-model-small-cn-0.22"); InputStream ais = AudioSystem.getAudioInputStream(new BufferedInputStream(new FileInputStream("D:\\File\\badao.wav"))); Recognizer recognizer = new Recognizer(model, 16000)) { int bytes; byte[] b = new byte[4096]; while ((bytes = ais.read(b)) >= 0) { recognizer.acceptWaveForm(b, bytes); } System.out.println(recognizer.getFinalResult() + System.lineSeparator()); } } }
注意new Model("模型路径")是你下载的模型解压后的地址
InputStream ais = AudioSystem.getAudioInputStream(new BufferedInputStream(new FileInputStream("音频路径"))); 这个是你要识别的音频地址,我用的音频格式是 wav 其他格式还没试。
没有模型可以去网址: https://alphacephei.com/vosk/models 下载
选择 Chinese 下载这两个模型 (建议都下载 small模型识别快一点)
下载后记得解压在使用
2. 文字转语音
2.1 Maven导入以下包
<!-- 文字转语音 --> <dependency> <groupId>com.hynnet</groupId> <artifactId>jacob</artifactId> <version>1.18</version> </dependency>
2.2 编写代码
import com.jacob.activeX.ActiveXComponent; import com.jacob.com.Dispatch; import com.jacob.com.Variant; public class TxtToSoundUtils { public static void main(String[] args) { textToSpeech("打开卧室灯泡"); System.out.println("生成成功!"); } /** * 语音转文字并播放 * * @param text */ public static void textToSpeech(String text) { ActiveXComponent ax; try { ax = new ActiveXComponent("Sapi.SpVoice"); // 运行时输出语音内容 Dispatch spVoice = ax.getObject(); // 音量 0-100 ax.setProperty("Volume", new Variant(100)); // 语音朗读速度 -10 到 +10 ax.setProperty("Rate", new Variant(-2)); // 执行朗读 Dispatch.call(spVoice, "Speak", new Variant(text)); // 下面是构建文件流把生成语音文件 ax = new ActiveXComponent("Sapi.SpFileStream"); Dispatch spFileStream = ax.getObject(); ax = new ActiveXComponent("Sapi.SpAudioFormat"); Dispatch spAudioFormat = ax.getObject(); // 设置音频流格式 Dispatch.put(spAudioFormat, "Type", new Variant(22)); // 设置文件输出流格式 Dispatch.putRef(spFileStream, "Format", spAudioFormat); // 调用输出 文件流打开方法,创建一个.wav文件 Dispatch.call(spFileStream, "Open", new Variant("D:\\File\\TestFile.wav"), new Variant(3), new Variant(true)); // 设置声音对象的音频输出流为输出文件对象 Dispatch.putRef(spVoice, "AudioOutputStream", spFileStream); // 设置音量 0到100 Dispatch.put(spVoice, "Volume", new Variant(100)); // 设置朗读速度 Dispatch.put(spVoice, "Rate", new Variant(-2)); // 开始朗读 Dispatch.call(spVoice, "Speak", new Variant(text)); // 关闭输出文件 Dispatch.call(spFileStream, "Close"); Dispatch.putRef(spVoice, "AudioOutputStream", null); spAudioFormat.safeRelease(); spFileStream.safeRelease(); spVoice.safeRelease(); ax.safeRelease(); } catch (Exception e) { e.printStackTrace(); } } }
到此就完成了 语音转文字 文字转语音的功能了,希望能帮到你。有疑问评论
如Linux部署有问题可以参考这篇文章,希望对你有帮助
在Linux服务器上 运行vosk报错Could not initialize class org.vosk.LibVosk_服务器-CSDN问答