Fun-ASR realtime Java SDK

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.utils.Constants;

import java.io.File;

public class Main {
  public static void main(String[] args) {
    Constants.baseWebsocketApiUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/inference";
    // 创建 Recognition 实例
    Recognition recognizer = new Recognition();
    // 创建 RecognitionParam
    RecognitionParam param =
        RecognitionParam.builder()
            .model("fun-asr-realtime")
            // 如果未配置环境变量，请将下行替换为您的 API Key：.apiKey("sk-xxx")
            .apiKey(System.getenv("DASHSCOPE_API_KEY"))
            .format("wav")
            .sampleRate(16000)
            .parameter("language_hints", new String[]{"zh", "en"})
            .build();

    try {
      System.out.println("Recognition result: " + recognizer.call(param, new File("asr_example.wav")));
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      // 任务完成后关闭 WebSocket 连接
      recognizer.getDuplexApi().close(1000, "bye");
    }
    System.out.println(
        "[Metric] requestId: "
            + recognizer.getLastRequestId()
            + ", first package delay ms: "
            + recognizer.getFirstPackageDelay()
            + ", last package delay ms: "
            + recognizer.getLastPackageDelay());
    System.exit(0);
  }
}

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import io.reactivex.BackpressureStrategy;
import io.reactivex.Flowable;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.TargetDataLine;
import java.nio.ByteBuffer;

public class Main {
  public static void main(String[] args) throws NoApiKeyException {
    Constants.baseWebsocketApiUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/inference";
    // 创建 Flowable<ByteBuffer>
    Flowable<ByteBuffer> audioSource =
        Flowable.create(
            emitter -> {
              new Thread(
                  () -> {
                    try {
                      // 创建音频格式
                      AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
                      // 根据格式匹配默认录音设备
                      TargetDataLine targetDataLine =
                          AudioSystem.getTargetDataLine(audioFormat);
                      targetDataLine.open(audioFormat);
                      // 开始录音
                      targetDataLine.start();
                      ByteBuffer buffer = ByteBuffer.allocate(1024);
                      long start = System.currentTimeMillis();
                      // 录制 50 秒并实时转写
                      while (System.currentTimeMillis() - start < 50000) {
                        int read = targetDataLine.read(buffer.array(), 0, buffer.capacity());
                        if (read > 0) {
                          buffer.limit(read);
                          // 将录制的音频数据发送给流式识别服务
                          emitter.onNext(buffer);
                          buffer = ByteBuffer.allocate(1024);
                          // 录音速率有限，短暂休眠以避免 CPU 占用过高
                          Thread.sleep(20);
                        }
                      }
                      // 通知转写完成
                      emitter.onComplete();
                    } catch (Exception e) {
                      emitter.onError(e);
                    }
                  })
                  .start();
            },
            BackpressureStrategy.BUFFER);

    // 创建 Recognition 实例
    Recognition recognizer = new Recognition();
    // 创建 RecognitionParam，通过 audioFrame 参数传入 Flowable<ByteBuffer>
    RecognitionParam param = RecognitionParam.builder()
        .model("fun-asr-realtime")
        // 如果未配置环境变量，请将下行替换为您的 API Key：.apiKey("sk-xxx")
        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
        .format("pcm")
        .sampleRate(16000)
        .build();

    // 调用流式接口
    recognizer
        .streamCall(param, audioSource)
        .blockingForEach(
            result -> {
              // 订阅输出结果
              if (result.isSentenceEnd()) {
                System.out.println("Final Result: " + result.getSentence().getText());
              } else {
                System.out.println("Intermediate Result: " + result.getSentence().getText());
              }
            });
    // 任务完成后关闭 WebSocket 连接
    recognizer.getDuplexApi().close(1000, "bye");
    System.out.println(
        "[Metric] requestId: "
            + recognizer.getLastRequestId()
            + ", first package delay ms: "
            + recognizer.getFirstPackageDelay()
            + ", last package delay ms: "
            + recognizer.getLastPackageDelay());
    System.exit(0);
  }
}

RecognitionParam param = RecognitionParam.builder()
  .model("fun-asr-realtime")
  .format("pcm")
  .sampleRate(16000)
  .parameter("language_hints", new String[]{"zh", "en"})
  .build();

ResultCallback<RecognitionResult> callback = new ResultCallback<RecognitionResult>() {
  @Override
  public void onEvent(RecognitionResult result) {
    System.out.println("RequestId is: " + result.getRequestId());
    // 在此处实现语音识别结果的处理逻辑
  }

  @Override
  public void onComplete() {
    System.out.println("Task complete");
  }

  @Override
  public void onError(Exception e) {
    System.out.println("Task failed: " + e.getMessage());
  }
};