快速开始

# For prerequisites running the following sample, visit https://help.aliyun.com/zh/model-studio/getting-started/first-api-call-to-qwen
import os
import signal  # for keyboard events handling (press "Ctrl+C" to terminate recording and translation)
import sys

import dashscope
import pyaudio
from dashscope.audio.asr import *

mic = None
stream = None

# Set recording parameters
sample_rate = 16000  # sampling rate (Hz)
channels = 1  # mono channel
dtype = 'int16'  # data type
format_pcm = 'pcm'  # the format of the audio data
block_size = 3200  # number of frames per buffer


def init_dashscope_api_key():
    """
        Set your DashScope API-key. More information:
        https://github.com/aliyun/alibabacloud-bailian-speech-demo/blob/master/PREREQUISITES.md
    """

    if 'DASHSCOPE_API_KEY' in os.environ:
        dashscope.api_key = os.environ[
            'DASHSCOPE_API_KEY']  # load API-key from environment variable DASHSCOPE_API_KEY
    else:
        dashscope.api_key = '<your-dashscope-api-key>'  # set API-key manually


# Real-time speech recognition callback
class Callback(RecognitionCallback):
    def on_open(self) -> None:
        global mic
        global stream
        print('RecognitionCallback open.')
        mic = pyaudio.PyAudio()
        stream = mic.open(format=pyaudio.paInt16,
                          channels=1,
                          rate=16000,
                          input=True)

    def on_close(self) -> None:
        global mic
        global stream
        print('RecognitionCallback close.')
        stream.stop_stream()
        stream.close()
        mic.terminate()
        stream = None
        mic = None

    def on_complete(self) -> None:
        print('RecognitionCallback completed.')  # translation completed

    def on_error(self, message) -> None:
        print('RecognitionCallback task_id: ', message.request_id)
        print('RecognitionCallback error: ', message.message)
        # Stop and close the audio stream if it is running
        if 'stream' in globals() and stream.active:
            stream.stop()
            stream.close()
        # Forcefully exit the program
        sys.exit(1)

    def on_event(self, result: RecognitionResult) -> None:
        sentence = result.get_sentence()
        if 'text' in sentence:
            print('RecognitionCallback text: ', sentence['text'])
            if RecognitionResult.is_sentence_end(sentence):
                print(
                    'RecognitionCallback sentence end, request_id:%s, usage:%s'
                    % (result.get_request_id(), result.get_usage(sentence)))


def signal_handler(sig, frame):
    print('Ctrl+C pressed, stop translation ...')
    # Stop translation
    recognition.stop()
    print('Translation stopped.')
    print(
        '[Metric] requestId: {}, first package delay ms: {}, last package delay ms: {}'
        .format(
            recognition.get_last_request_id(),
            recognition.get_first_package_delay(),
            recognition.get_last_package_delay(),
        ))
    # Forcefully exit the program
    sys.exit(0)


# main function
if __name__ == '__main__':
    init_dashscope_api_key()
    print('Initializing ...')

    # Create the translation callback
    callback = Callback()

    # Call recognition service by async mode, you can customize the recognition parameters, like model, format,
    # sample_rate For more information, please refer to https://help.aliyun.com/document_detail/2712536.html
    recognition = Recognition(
        model='paraformer-realtime-v2',
        # 'paraformer-realtime-v1'、'paraformer-realtime-8k-v1'
        format=format_pcm,
        # 'pcm'、'wav'、'opus'、'speex'、'aac'、'amr', you can check the supported formats in the document
        sample_rate=sample_rate,
        # support 8000, 16000
        semantic_punctuation_enabled=False,
        callback=callback)

    # Start translation
    recognition.start()

    signal.signal(signal.SIGINT, signal_handler)
    print("Press 'Ctrl+C' to stop recording and translation...")
    # Create a keyboard listener until "Ctrl+C" is pressed

    while True:
        if stream:
            data = stream.read(3200, exception_on_overflow=False)
            recognition.send_audio_frame(data)
        else:
            break

    recognition.stop()

package com.alibaba.dashscope.sample.recognition.quickstart;

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.ApiKey;
import io.reactivex.BackpressureStrategy;
import io.reactivex.Flowable;
import java.awt.event.KeyAdapter;
import java.awt.event.KeyEvent;
import java.nio.ByteBuffer;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.TargetDataLine;
import javax.swing.*;

/**
 * This demo showcases how to use Alibaba Cloud's DashScope model for recognition from microphone
 * audio input to text Type 'q' to finish recording and recognition.
 */
public class RecognizeSpeechFromMicrophoneUsingFlowable {

  public static void main(String[] args) {
    // set exit flags
    boolean[] shouldExit = {false};
    Object exitFlag = new Object();

    // Start a new thread to record and recognize
    new Thread(
            () -> {
              try {
                startRecordingAndRecognition(exitFlag, shouldExit);
              } catch (Exception e) {
                e.printStackTrace();
                System.exit(0);
              }
            })
        .start();
    // Exit the program
    waitForExitSignal(exitFlag, shouldExit);
  }

  // Wait for exit signal by key press.
  private static void waitForExitSignal(Object exitFlag, boolean[] shouldExit) {

    // Create a hidden JFrame to capture key events
    JFrame frame = new JFrame();
    frame.setUndecorated(true);
    frame.setSize(1, 1);
    frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);

    System.out.println("Press 'Ctrl+C' to stop recording and recognition...");
    frame.addKeyListener(
        new KeyAdapter() {
          @Override
          public void keyPressed(KeyEvent e) {
            if (e.isControlDown() && e.getKeyCode() == KeyEvent.VK_C) {
              synchronized (exitFlag) {
                shouldExit[0] = true;
                exitFlag.notifyAll(); // 通知录音线程退出
              }
              System.out.println("Exit signal received. Exiting...");
            }
          }
        });
    frame.setVisible(true);
  }

  private static void startRecordingAndRecognition(Object exitFlag, boolean[] shouldExit)
      throws NoApiKeyException {
    // Create a Flowable<ByteBuffer> for streaming audio data
    Flowable<ByteBuffer> audioSource = createAudioSourceWithControl(exitFlag, shouldExit);
    // Create speech Recognizer
    Recognition recognizer = new Recognition();
    // Create RecognitionParam, pass the Flowable<ByteBuffer> to audioFrames parameter
    RecognitionParam param =
        RecognitionParam.builder()
            .model("paraformer-realtime-v2")
            .format("pcm")
            .sampleRate(16000)
            .apiKey(getDashScopeApiKey()) // set your apikey in config.Environments.yourApikey
            .parameter("semantic_punctuation_enabled", false)
            .build();

    // Stream call interface for streaming audio to recognizer
    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());
              }
            });
    System.out.println("Recognition onComplete! , exit program...");

    System.out.println(
        "[Metric] requestId: "
            + recognizer.getLastRequestId()
            + ", first package delay ms: "
            + recognizer.getFirstPackageDelay()
            + ", last package delay ms: "
            + recognizer.getLastPackageDelay());

    System.exit(0);
  }

  private static Flowable<ByteBuffer> createAudioSourceWithControl(
      Object exitFlag, boolean[] shouldExit) {
    // Create a Flowable<ByteBuffer> for streaming audio data
    return Flowable.create(
        emitter -> {
          try {
            AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
            TargetDataLine targetDataLine = AudioSystem.getTargetDataLine(audioFormat);
            targetDataLine.open(audioFormat);
            targetDataLine.start();
            ByteBuffer buffer = ByteBuffer.allocate(1024);

            while (!shouldExit[0]) {
              int read = targetDataLine.read(buffer.array(), 0, buffer.capacity());
              if (read > 0) {
                buffer.limit(read);
                emitter.onNext(buffer);
                buffer = ByteBuffer.allocate(1024);
                Thread.sleep(20); // Small delay to control CPU usage
              }
              synchronized (exitFlag) {
                if (shouldExit[0]) {
                  emitter.onComplete();
                  break;
                }
              }
            }
          } catch (Exception e) {
            emitter.onError(e);
            System.exit(0);
          }
        },
        BackpressureStrategy.BUFFER);
  }

  /**
   * Set your DashScope API key. More information: <a
   * href="https://help.aliyun.com/document_detail/2712195.html">...</a> In fact, if you have set
   * DASHSCOPE_API_KEY in your environment variable, you can ignore this, and the SDK will
   * automatically get the api_key from the environment variable
   */
  private static String getDashScopeApiKey() throws NoApiKeyException {
    String dashScopeApiKey = null;
    try {
      ApiKey apiKey = new ApiKey();
      dashScopeApiKey = apiKey.getApiKey(null); // Retrieve from environment variable.
    } catch (NoApiKeyException e) {
      System.out.println("No API key found in environment.");
    }
    if (dashScopeApiKey == null) {
      // If you cannot set api_key in your environment variable,
      // you can set it here by code
      dashScopeApiKey = "your-dashscope-api-key";
    }
    return dashScopeApiKey;
  }
}

# For prerequisites running the following sample, visit https://help.aliyun.com/document_detail/611472.html

import requests
from http import HTTPStatus

import dashscope
from dashscope.audio.asr import Recognition

dashscope.api_key = '<your-dashscope-api-key>'

r = requests.get(
    'https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav'
)
with open('asr_example.wav', 'wb') as f:
    f.write(r.content)

recognition = Recognition(model='paraformer-realtime-v2',
                          format='wav',
                          sample_rate=16000,
                          callback=None)
result = recognition.call('asr_example.wav')


print(
    '[Metric] requestId: {}, first package delay ms: {}, last package delay ms: {}'
    .format(
        recognition.get_last_request_id(),
        recognition.get_first_package_delay(),
        recognition.get_last_package_delay(),
    ))

if result.status_code == HTTPStatus.OK:
    with open('asr_result.txt', 'w+') as f:
        for sentence in result.get_sentence():
            print(sentence['text'])
            f.write(str(sentence) + '\n')
    print('Recognition done!')
else:
    print('Error: ', result.message)

package com.alibaba.dashscope.sample.recognition.quickstart;

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.nio.file.StandardCopyOption;

public class Main {

  public static void main(String[] args) {
    // 用户可忽略url下载文件部分，可以直接使用本地文件进行相关api调用进行识别
    String exampleWavUrl =
        "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav";
    try {
      InputStream in = new URL(exampleWavUrl).openStream();
      Files.copy(in, Paths.get("asr_example.wav"), StandardCopyOption.REPLACE_EXISTING);
    } catch (IOException e) {
      System.out.println("error: " + e);
      System.exit(1);
    }

    // 创建Recognition实例
    Recognition recognizer = new Recognition();
    // 创建RecognitionParam，请在实际使用中替换真实apiKey
    RecognitionParam param =
        RecognitionParam.builder()
            .model("paraformer-realtime-v2")
            .format("wav")
            .sampleRate(16000)
            .apiKey("your-dashscope-api-key")
            .build();
    // 直接将结果保存到script.txt中
    try (FileOutputStream fos = new FileOutputStream("asr_result.txt")) {
      String result = recognizer.call(param, new File("asr_example.wav"));
      System.out.println(result);
      System.out.println(
          "[Metric] requestId: "
              + recognizer.getLastRequestId()
              + ", first package delay ms: "
              + recognizer.getFirstPackageDelay()
              + ", last package delay ms: "
              + recognizer.getLastPackageDelay());      
      fos.write(result.getBytes());
    } catch (Exception e) {
      e.printStackTrace();
    }
    System.exit(0);
  }
}

# For prerequisites running the following sample, visit https://help.aliyun.com/document_detail/611472.html

import requests
from http import HTTPStatus

import dashscope
from dashscope.audio.asr import Recognition

dashscope.api_key = '<your-dashscope-api-key>'

r = requests.get(
    'https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/welcome_female_16k_mono_japanese.wav'
)
with open('asr_japanese_example.wav', 'wb') as f:
    f.write(r.content)

recognition = Recognition(model='paraformer-realtime-v2',
                          format='wav',
                          sample_rate=16000,
                          language_hints=['ja'],  # “language_hints”只支持paraformer-v2和paraformer-realtime-v2模型
                          callback=None)
result = recognition.call('asr_japanese_example.wav')

print(
    '[Metric] requestId: {}, first package delay ms: {}, last package delay ms: {}'
    .format(
        recognition.get_last_request_id(),
        recognition.get_first_package_delay(),
        recognition.get_last_package_delay(),
    ))

if result.status_code == HTTPStatus.OK:
    with open('asr_japanese_result.txt', 'w+') as f:
        for sentence in result.get_sentence():
            f.write(str(sentence) + '\n')
    print('Recognition done!')
else:
    print('Error: ', result.message)

package com.alibaba.dashscope.sample.recognition.quickstart;

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.nio.file.StandardCopyOption;

public class Main {

  public static void main(String[] args) {
    // 用户可忽略url下载文件部分，可以直接使用本地文件进行相关api调用进行识别
    String exampleWavUrl =
        "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/welcome_female_16k_mono_japanese.wav";
    try {
      InputStream in = new URL(exampleWavUrl).openStream();
      Files.copy(in, Paths.get("asr_japanese_example.wav"), StandardCopyOption.REPLACE_EXISTING);
    } catch (IOException e) {
      System.out.println("error: " + e);
      System.exit(1);
    }

    // 创建Recognition实例
    Recognition recognizer = new Recognition();
    // 创建RecognitionParam，请在实际使用中替换真实apiKey
    RecognitionParam param =
        RecognitionParam.builder()
            .model("paraformer-realtime-v2")
            .format("wav")
            .sampleRate(16000)
            .apiKey("your-dashscope-api-key")
            // “language_hints”只支持paraformer-v2和paraformer-realtime-v2模型
            .parameter("language_hints", new String[]{"ja"})
            .build();
    // 直接将结果保存到script.txt中
    try (FileOutputStream fos = new FileOutputStream("asr_japanese_result.txt")) {
      String result = recognizer.call(param, new File("asr_japanese_example.wav"));
      System.out.println(
          "[Metric] requestId: "
              + recognizer.getLastRequestId()
              + ", first package delay ms: "
              + recognizer.getFirstPackageDelay()
              + ", last package delay ms: "
              + recognizer.getLastPackageDelay());      
      System.out.println(result);
      fos.write(result.getBytes());
    } catch (Exception e) {
      e.printStackTrace();
    }
    System.exit(0);
  }
}