Qwen-Audio-ASR-Streaming Java SDK

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 {
        // 以下為新加坡地區的配置，調用時請將"{WorkspaceId}"替換為真實的業務空間ID，各地區的配置不同。
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
        // 建立一個Flowable<ByteBuffer>
        Flowable<ByteBuffer> audioSource =
                Flowable.create(
                        emitter -> {
                            new Thread(
                                    () -> {
                                        try {
                                            // 建立音頻格式
                                            AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
                                            // 根據格式匹配預設錄音裝置
                                            TargetDataLine targetDataLine =
                                                    AudioSystem.getTargetDataLine(audioFormat);
                                            targetDataLine.open(audioFormat);
                                            // 開始錄音
                                            targetDataLine.start();
                                            ByteBuffer buffer = ByteBuffer.allocate(1024);
                                            long start = System.currentTimeMillis();
                                            // 錄音50s並進行即時轉寫
                                            while (System.currentTimeMillis() - start < 50000) {
                                                int read = targetDataLine.read(buffer.array(), 0, buffer.capacity());
                                                if (read > 0) {
                                                    buffer.limit(read);
                                                    // 將錄音音頻資料發送給流式識別服務
                                                    emitter.onNext(buffer);
                                                    buffer = ByteBuffer.allocate(1024);
                                                    // 錄音速率有限，防止cpu佔用過高，休眠一小會兒
                                                    Thread.sleep(20);
                                                }
                                            }
                                            // 通知結束轉寫
                                            emitter.onComplete();
                                        } catch (Exception e) {
                                            emitter.onError(e);
                                        }
                                    })
                                    .start();
                        },
                        BackpressureStrategy.BUFFER);

        // 建立Recognizer
        Recognition recognizer = new Recognition();
        // 建立RecognitionParam，audioFrames參數中傳入上面建立的Flowable<ByteBuffer>
        RecognitionParam param = RecognitionParam.builder()
                .model("qwen-audio-3.0-asr-flash-streaming")
                // 新加坡地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                // 若沒有配置環境變數，請用百鍊API Key將下行替換為：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .format("pcm")
                .sampleRate(16000)
                .build();

        // 流式調用介面
        recognizer
                .streamCall(param, audioSource)
                .blockingForEach(
                        result -> {
                            // Subscribe to the output result
                            if (result.isSentenceEnd()) {
                                System.out.println("Final Result: " + result.getSentence().getText());
                            } else {
                                System.out.println("Intermediate Result: " + result.getSentence().getText());
                            }
                        });
        // 任務結束後關閉 Websocket 串連
        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);
    }
}