Skip to content

N
nls-sdk-java-demo

OpenDocCN / nls-sdk-java-demo

通知 2
Star 1
Fork 0
N
nls-sdk-java-demo

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 0a53be05 编写于 作者: 凌洛云's avatar 凌洛云 提交者： GitHub
浏览文件
操作

Merge pull request #3 from lihangqi/master 

Update README.md
上级 e97c1909 cf50127e
隐藏空白更改
内联 并排
Showing with 116 addition and 114 deletion
README.md
浏览文件 @ 0a53be05
......@@ -56,124 +56,130 @@ Demo中使用了SDK内置的默认实时语音识别服务的外网访问URL，
**示例**
```java
import java.io.InputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import com.alibaba.nls.client.protocol.InputFormatEnum;
import com.alibaba.nls.client.protocol.NlsClient;
import com.alibaba.nls.client.protocol.SampleRateEnum;
import com.alibaba.nls.client.protocol.asr.SpeechTranscriber;
import com.alibaba.nls.client.protocol.asr.SpeechTranscriberListener;
import com.alibaba.nls.client.protocol.asr.SpeechTranscriberResponse;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizer;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizerListener;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizerResponse;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* 实时语音识别Demo
* 此示例演示了
* ASR一句话识别API调用
* 动态获取token
* 通过本地文件模拟实时流发送
* 识别耗时计算
* (仅作演示，需用户根据实际情况实现)
*/
public class SpeechTranscriberDemo {
public class SpeechRecognizerDemo {
private static final Logger logger = LoggerFactory.getLogger(SpeechRecognizerDemo.class);
private String appKey;
private String accessToken;
NlsClient client;
public SpeechTranscriberDemo(String appKey, String token) {
public SpeechRecognizerDemo(String appKey, String id, String secret, String url) {
this.appKey = appKey;
this.accessToken = token;
//创建NlsClient实例,应用全局创建一个即可,用户指定服务地址
client = new NlsClient(token, accessToken);
}
public SpeechTranscriberDemo(String appKey, String token, String url) {
this.appKey = appKey;
this.accessToken = token;
//创建NlsClient实例,应用全局创建一个即可,用户指定服务地址
client = new NlsClient(url, accessToken);
//TODO 重要提示 创建NlsClient实例,应用全局创建一个即可,生命周期可和整个应用保持一致,默认服务地址为阿里云线上服务地址
//TODO 这里简单演示了获取token 的代码，该token会过期，实际使用时注意在accessToken.getExpireTime()过期前再次获取token
AccessToken accessToken = new AccessToken(id, secret);
try {
accessToken.apply();
System.out.println("get token: " + accessToken.getToken() + ", expire time: " + accessToken.getExpireTime());
// TODO 创建NlsClient实例,应用全局创建一个即可
if(url.isEmpty()) {
client = new NlsClient(accessToken.getToken());
}else {
client = new NlsClient(url, accessToken.getToken());
}
} catch (IOException e) {
e.printStackTrace();
}
}
private static SpeechTranscriberListener getTranscriberListener() {
SpeechTranscriberListener listener = new SpeechTranscriberListener() {
private static SpeechRecognizerListener getRecognizerListener(int myOrder, String userParam) {
SpeechRecognizerListener listener = new SpeechRecognizerListener() {
//识别出中间结果.服务端识别出一个字或词时会返回此消息.仅当setEnableIntermediateResult(true)时,才会有此类消息返回
@Override
public void onTranscriptionResultChange(SpeechTranscriberResponse response) {
System.out.println("task_id: " + response.getTaskId() +
", name: " + response.getName() +
//状态码 20000000 表示正常识别
", status: " + response.getStatus() +
//句子编号，从1开始递增
", index: " + response.getTransSentenceIndex() +
//当前的识别结果
", result: " + response.getTransSentenceText() +
//当前已处理的音频时长，单位是毫秒
", time: " + response.getTransSentenceTime());
}
@Override
public void onTranscriberStart(SpeechTranscriberResponse response) {
System.out.println("task_id: " + response.getTaskId() +
", name: " + response.getName() +
", status: " + response.getStatus());
public void onRecognitionResultChanged(SpeechRecognizerResponse response) {
//事件名称 RecognitionResultChanged、 状态码(20000000 表示识别成功)、语音识别文本
System.out.println("name: " + response.getName() + ", status: " + response.getStatus() + ", result: " + response.getRecognizedText());
}
//识别完毕
@Override
public void onSentenceBegin(SpeechTranscriberResponse response) {
System.out.println("task_id: " + response.getTaskId() +
", name: " + response.getName() +
", status: " + response.getStatus());
}
//识别出一句话.服务端会智能断句,当识别到一句话结束时会返回此消息
@Override
public void onSentenceEnd(SpeechTranscriberResponse response) {
System.out.println("task_id: " + response.getTaskId() +
", name: " + response.getName() +
//状态码 20000000 表示正常识别
", status: " + response.getStatus() +
//句子编号，从1开始递增
", index: " + response.getTransSentenceIndex() +
//当前的识别结果
", result: " + response.getTransSentenceText() +
//置信度
", confidence: " + response.getConfidence() +
//开始时间
", begin_time: " + response.getSentenceBeginTime() +
//当前已处理的音频时长，单位是毫秒
", time: " + response.getTransSentenceTime());
public void onRecognitionCompleted(SpeechRecognizerResponse response) {
//事件名称 RecognitionCompleted, 状态码 20000000 表示识别成功, getRecognizedText是识别结果文本
System.out.println("name: " + response.getName() + ", status: " + response.getStatus() + ", result: " + response.getRecognizedText());
}
//识别完毕
@Override
public void onTranscriptionComplete(SpeechTranscriberResponse response) {
System.out.println("task_id: " + response.getTaskId() +
", name: " + response.getName() +
", status: " + response.getStatus());
public void onStarted(SpeechRecognizerResponse response) {
System.out.println("myOrder: " + myOrder + "; myParam: " + userParam + "; task_id: " + response.getTaskId());
}
@Override
public void onFail(SpeechTranscriberResponse response) {
System.out.println(
"task_id: " + response.getTaskId() +
//状态码 20000000 表示识别成功
", status: " + response.getStatus() +
//错误信息
", status_text: " + response.getStatusText());
public void onFail(SpeechRecognizerResponse response) {
// TODO 重要提示： task_id很重要，是调用方和服务端通信的唯一ID标识，当遇到问题时，需要提供此task_id以便排查
System.out.println("task_id: " + response.getTaskId() + ", status: " + response.getStatus() + ", status_text: " + response.getStatusText());
}
};
return listener;
}
public void process(InputStream ins) {
SpeechTranscriber transcriber = null;
/// 根据二进制数据大小计算对应的同等语音长度
/// sampleRate 仅支持8000或16000
public static int getSleepDelta(int dataSize, int sampleRate) {
// 仅支持16位采样
int sampleBytes = 16;
// 仅支持单通道
int soundChannel = 1;
return (dataSize * 10 * 8000) / (160 * sampleRate);
}
public void process(String filepath, int sampleRate) {
SpeechRecognizer recognizer = null;
try {
//创建实例,建立连接
transcriber = new SpeechTranscriber(client, getTranscriberListener());
transcriber.setAppKey(appKey);
//输入音频编码方式
transcriber.setFormat(InputFormatEnum.PCM);
//输入音频采样率
transcriber.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
//是否返回中间识别结果
transcriber.setEnableIntermediateResult(false);
//是否生成并返回标点符号
transcriber.setEnablePunctuation(true);
//是否将返回结果规整化,比如将一百返回为100
transcriber.setEnableITN(false);
// 传递用户自定义参数
String myParam = "user-param";
int myOrder = 1234;
SpeechRecognizerListener listener = getRecognizerListener(myOrder, myParam);
recognizer = new SpeechRecognizer(client, listener);
recognizer.setAppKey(appKey);
//设置音频编码格式 TODO 如果是opus文件，请设置为 InputFormatEnum.OPUS
recognizer.setFormat(InputFormatEnum.PCM);
//设置音频采样率
if(sampleRate == 16000) {
recognizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
} else if(sampleRate == 8000) {
recognizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_8K);
}
//设置是否返回中间识别结果
recognizer.setEnableIntermediateResult(true);
//此方法将以上参数设置序列化为json发送给服务端,并等待服务端确认
transcriber.start();
//语音数据来自声音文件用此方法,控制发送速率;若语音来自实时录音,不需控制发送速率直接调用 transcriber.sent(ins)即可
transcriber.send(ins, 3200, 100);
long now = System.currentTimeMillis();
recognizer.start();
logger.info("ASR start latency : " + (System.currentTimeMillis() - now) + " ms");
File file = new File(filepath);
FileInputStream fis = new FileInputStream(file);
byte[] b = new byte[3200];
int len;
while ((len = fis.read(b)) > 0) {
logger.info("send data pack length: " + len);
recognizer.send(b);
// TODO 重要提示：这里是用读取本地文件的形式模拟实时获取语音流并发送的，因为read很快，所以这里需要sleep
// TODO 如果是真正的实时获取语音，则无需sleep, 如果是8k采样率语音，第二个参数改为8000
int deltaSleep = getSleepDelta(len, sampleRate);
Thread.sleep(deltaSleep);
}
//通知服务端语音数据发送完毕,等待服务端处理完成
transcriber.stop();
now = System.currentTimeMillis();
// TODO 计算实际延迟: stop返回之后一般即是识别结果返回时间
logger.info("ASR wait for complete");
recognizer.stop();
logger.info("ASR stop latency : " + (System.currentTimeMillis() - now) + " ms");
fis.close();
} catch (Exception e) {
System.err.println(e.getMessage());
} finally {
if (null != transcriber) {
transcriber.close();
//关闭连接
if (null != recognizer) {
recognizer.close();
}
}
}
......@@ -181,31 +187,27 @@ public class SpeechTranscriberDemo {
client.shutdown();
}
public static void main(String[] args) throws Exception {
String appKey = null;
String token = null;
String url = null;
SpeechTranscriberDemo demo =null;
if (args.length == 2) {
appKey = args[0];
token = args[1];
//default url is wss://nls-gateway.cn-shanghai.aliyuncs.com/ws/v1
demo = new SpeechTranscriberDemo(appKey, token);
}else if(args.length == 3){
appKey = args[0];
token = args[1];
url = args[2];
demo = new SpeechTranscriberDemo(appKey, token, url);
}else{
System.err.println("SpeechTranscriberDemo need params(url is optional): " +
"<app-key> <token> [<url>]");
String appKey = null; // "填写你的appkey";
String id = null; // "填写你在阿里云网站上的AccessKeyId";
String secret = null; // "填写你在阿里云网站上的AccessKeySecret";
String url = ""; // 默认即可，默认值：wss://nls-gateway.cn-shanghai.aliyuncs.com/ws/v1
if (args.length == 3) {
appKey = args[0];
id = args[1];
secret = args[2];
} else if (args.length == 4) {
appKey = args[0];
id = args[1];
secret = args[2];
url = args[3];
} else {
System.err.println("run error, need params(url is optional): " + "<app-key> <AccessKeyId> <AccessKeySecret> [url]");
System.exit(-1);
}
InputStream ins = SpeechTranscriberDemo.class.getResourceAsStream("/nls-sample-16k.wav");
if (null == ins) {
System.err.println("open the audio file failed!");
return;
}
demo.process(ins);
SpeechRecognizerDemo demo = new SpeechRecognizerDemo(appKey, id, secret, url);
// TODO 重要提示： 这里用一个本地文件来模拟发送实时流数据，实际使用时，用户可以从某处实时采集或接收语音流并发送到ASR服务端
demo.process("./nls-sample-16k.wav", 16000);
//demo.process("./nls-sample.opus", 16000);
demo.shutdown();
}
}
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或