快速开始

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

import pyaudio
import dashscope
from dashscope.audio.asr import (Recognition, RecognitionCallback,
                                 RecognitionResult)

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

mic = None
stream = None

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_event(self, result: RecognitionResult) -> None:
        print('RecognitionCallback sentence: ', result.get_sentence())

callback = Callback()
recognition = Recognition(model='paraformer-realtime-v2',
                          format='pcm',
                          sample_rate=16000,
                          callback=callback)
recognition.start()

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

recognition.stop()

package org.example.recognition;

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.BackpressureStrategy;
import io.reactivex.Flowable;
import java.nio.ByteBuffer;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.TargetDataLine;

public class Main {

    public static void main(String[] args) throws NoApiKeyException {
        // 创建一个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();
                                            // 录音30s并进行实时转写
                                            while (System.currentTimeMillis() - start < 300000) {
                                                int read = targetDataLine.read(buffer.array(), 0, buffer.capacity());
                                                if (read > 0) {
                                                    buffer.limit(read);
                                                    // 将录音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，防止cpu占用过高，休眠一小会儿
                                                    Thread.sleep(20);
                                                }
                                            }
                                            // 通知结束转写
                                            emitter.onComplete();
                                        } catch (Exception e) {
                                            emitter.onError(e);
                                        }
                                    })
                                    .start();
                        },
                        BackpressureStrategy.BUFFER);

        // 创建Recognizer
        Recognition recognizer = new Recognition();
        // 创建RecognitionParam，audioFrames参数中传入上面创建的Flowable<ByteBuffer>
        RecognitionParam param =
                RecognitionParam.builder()
                        .model("paraformer-realtime-v2")
                        .format("pcm")
                        .sampleRate(16000)
                        .apiKey("your-dashscope-api-key")
                        .build();

        // 流式调用接口
        recognizer
                .streamCall(param, audioSource)
                // 调用Flowable的subscribe方法订阅结果
                .blockingForEach(
                        result -> {
                            // 打印最终结果
                            if (result.isSentenceEnd()) {
                                System.out.println("Fix:" + result.getSentence().getText());
                            } else {
                                System.out.println("Result:" + result.getSentence().getText());
                            }
                        });
        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/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')
if result.status_code == HTTPStatus.OK:
    with open('asr_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/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);
      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')
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(result);
      fos.write(result.getBytes());
    } catch (Exception e) {
      e.printStackTrace();
    }
    System.exit(0);
  }
}