科大讯飞语音转文字以及中文分词的Java测试代码

阅读更多

我录了一段音存储在这个test.m4a文件里，语音内容为"测试一下Netweaver对于并发请求的响应性能"。

使用如下Java代码进行测试：

package com.iflytek.msp.lfasr;

import java.util.HashMap;
import org.apache.log4j.Logger;
import com.alibaba.fastjson.JSON;
import com.iflytek.msp.cpdb.lfasr.client.LfasrClientImp;
import com.iflytek.msp.cpdb.lfasr.exception.LfasrException;
import com.iflytek.msp.cpdb.lfasr.model.LfasrType;
import com.iflytek.msp.cpdb.lfasr.model.Message;
import com.iflytek.msp.cpdb.lfasr.model.ProgressStatus;

// SDK document: http://www.xfyun.cn/doccenter/lfasr#go_sdk_doc_v2
public class TestLfasr 
{
    // original media path
    private static final String local_file = "c:\\temp\\test.m4a";

    private static final LfasrType type = LfasrType.LFASR_STANDARD_RECORDED_AUDIO;
    
    private static int sleepSecond = 20;
    
    public static void main(String[] args) {
        LfasrClientImp lc = null;
        try {
            lc = LfasrClientImp.initLfasrClient();
        } catch (LfasrException e) {
            Message initMsg = JSON.parseObject(e.getMessage(), Message.class);
            System.out.println("ecode=" + initMsg.getErr_no());
            System.out.println("failed=" + initMsg.getFailed());
        }
                
        // get upload task id
        String task_id = "";
        HashMap params = new HashMap<>();
        params.put("has_participle", "true");
        try {
            Message uploadMsg = lc.lfasrUpload(local_file, type, params);
            int ok = uploadMsg.getOk();
            if (ok == 0) {
                task_id = uploadMsg.getData();
                System.out.println("task_id=" + task_id);
            } else {
                System.out.println("ecode=" + uploadMsg.getErr_no());
                System.out.println("failed=" + uploadMsg.getFailed());
            }
        } catch (LfasrException e) {
            Message uploadMsg = JSON.parseObject(e.getMessage(), Message.class);
            System.out.println("ecode=" + uploadMsg.getErr_no());
            System.out.println("failed=" + uploadMsg.getFailed());                  
        }
        while (true) {
            try {
                Thread.sleep(sleepSecond * 1000);
                System.out.println("waiting ...");
            } catch (InterruptedException e) {
            }
            try {
                Message progressMsg = lc.lfasrGetProgress(task_id);
                if (progressMsg.getOk() != 0) {
                    System.out.println("task was fail. task_id:" + task_id);
                    System.out.println("ecode=" + progressMsg.getErr_no());
                    System.out.println("failed=" + progressMsg.getFailed());
                    continue;
                } else {
                    ProgressStatus progressStatus = JSON.parseObject(progressMsg.getData(), ProgressStatus.class);
                    if (progressStatus.getStatus() == 9) {
                        System.out.println("task was completed. task_id:" + task_id);
                        break;  
                    } else {
                        System.out.println("task was incomplete. task_id:" + task_id + ", status:" + progressStatus.getDesc());
                        continue;
                    }
                }
            } catch (LfasrException e) {
                Message progressMsg = JSON.parseObject(e.getMessage(), Message.class);
                System.out.println("ecode=" + progressMsg.getErr_no());
                System.out.println("failed=" + progressMsg.getFailed());
            }
        }
        try {
            Message resultMsg = lc.lfasrGetResult(task_id);
            System.out.println(resultMsg.getData());
            if (resultMsg.getOk() == 0) {
                System.out.println(resultMsg.getData());
            } else {
                System.out.println("ecode=" + resultMsg.getErr_no());
                System.out.println("failed=" + resultMsg.getFailed());
            }
        } catch (LfasrException e) {
            Message resultMsg = JSON.parseObject(e.getMessage(), Message.class);
            System.out.println("ecode=" + resultMsg.getErr_no());
            System.out.println("failed=" + resultMsg.getFailed());
        }
    }
}

测试结果

(1) 所有中文均能成功转成文字; 但英文Netweaver的语音转换成了Net ball

(2) 智能分词也能按照期望工作，比如“测试一下”成功地分词成了“测试”和“一下”。

 

完整的Java项目在我的github上：https://github.com/i042416/voice2text
要获取更多Jerry的原创技术文章，请关注公众号"汪子熙"或者扫描下面二维码: