java 对接百度长语音识别 长语音转文字

  1. 登录百度智能云账号

  2. https://console.bce.baidu.com/ai/?_=1654758432357&fromai=1#/ai/speech/app/list 访问此链接创建应用
    java 对接百度长语音识别 长语音转文字_第1张图片

  3. 创建完成后点击应用列表,记录API Key 和 Secret Keyjava 对接百度长语音识别 长语音转文字_第2张图片

  4. 使用API Key 和 Secret Key 获取token

import org.json.JSONObject;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.List;
import java.util.Map;

/**
 * 获取token类
 */
public class AuthService {

    /**
     * 获取权限token
     * @return 返回示例:
     * {
     * "access_token": "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567",
     * "expires_in": 2592000
     * }
     */
    public static String getAuth() {
        // 官网获取的 API Key 更新为你注册的
        String clientId = "NcWgr1WofAsov";
        // 官网获取的 Secret Key 更新为你注册的
        String clientSecret = "wodN6GUcv0NRIBHfHjBA";
        return getAuth(clientId, clientSecret);
    }

    /**
     * 获取API访问token
     * 该token有一定的有效期,需要自行管理,当失效时需重新获取.
     * @param ak - 百度云官网获取的 API Key
     * @param sk - 百度云官网获取的 Secret Key
     * @return assess_token 示例:
     * "24.460da4889caad24cccdb1fea17221975.2592000.1491995545.282335-1234567"
     */
    public static String getAuth(String ak, String sk) {
        // 获取token地址
        String authHost = "https://aip.baidubce.com/oauth/2.0/token?";
        String getAccessTokenUrl = authHost
                // 1. grant_type为固定参数
                + "grant_type=client_credentials"
                // 2. 官网获取的 API Key
                + "&client_id=" + ak
                // 3. 官网获取的 Secret Key
                + "&client_secret=" + sk;
        try {
            URL realUrl = new URL(getAccessTokenUrl);
            // 打开和URL之间的连接
            HttpURLConnection connection = (HttpURLConnection) realUrl.openConnection();
            connection.setRequestMethod("GET");
            connection.connect();
            // 获取所有响应头字段
            Map<String, List<String>> map = connection.getHeaderFields();
            // 遍历所有的响应头字段
            for (String key : map.keySet()) {
                System.err.println(key + "--->" + map.get(key));
            }
            // 定义 BufferedReader输入流来读取URL的响应
            BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
            String result = "";
            String line;
            while ((line = in.readLine()) != null) {
                result += line;
            }
            /**
             * 返回结果示例
             */
            System.err.println("result:" + result);
            JSONObject jsonObject = new JSONObject(result);
            String access_token = jsonObject.getString("access_token");
            return access_token;
        } catch (Exception e) {
            System.err.printf("获取token失败!");
            e.printStackTrace(System.err);
        }
        return null;
    }

}


  1. 使用hutool工具包调用百度长语音识别接口创建语音转换进程
<dependency>
            <groupId>cn.hutool</groupId>
            <artifactId>hutool-all</artifactId>
            <version>5.7.19</version>
</dependency>
 Map<String,Object> body = new HashMap<>();
        body.put("speech_url","这里输入外网可访问的音频地址");
        body.put("format","m4a");//音频格式支持["mp3", "wav", "pcm","m4a","amr"]单声道,编码 16bits 位深
        body.put("pid","80001");
        body.put("rate","16000");
        String result = HttpUtil.post("https://aip.baidubce.com/rpc/2.0/aasr/v1/create?access_token=24.09fb9ae129423ec2f242048e4ad45fc6.2592000.1657344328.282335-26404843", JSONObject.valueToString(body));//需将获取到的token拼接到此处
        if (result != null) {
            JSONObject resultJson = new JSONObject(result);
            System.out.println("resultJson"+resultJson);
        }
  1. 将返回值中的task_id保存用于获取转换后的文字
//此处填写task_id多个视频需用逗号分割
String[] key = {"62a185bc72dec60c414b7f4b"};
        Map<String,Object> bodys = new HashMap<>();
        body.put("task_ids",key);
        String results = HttpUtil.post("https://aip.baidubce.com/rpc/2.0/aasr/v1/query?access_token=24.09fb9ae129423ec2f242048e4ad45fc6.2592000.1657344328.282335-26404843", JSONObject.valueToString(bodys));
        if (results != null) {
            JSONObject resultJsons = new JSONObject(results);
            JSONArray tasks_info = (JSONArray) resultJsons.get("tasks_info");

            JSONObject o = (JSONObject) tasks_info.get(0);
            JSONObject task_result = (JSONObject) o.get("task_result");
            JSONArray detailed_result = (JSONArray) task_result.get("detailed_result");
            for (int i = 0; i < detailed_result.length(); i ++){
                JSONObject o1 = (JSONObject) detailed_result.get(i);
                String res = o1.get("res").toString();
                System.out.println(res);
            }
        }

总结

以上代码是自己写的demo只提供思路如有错误望告知

你可能感兴趣的:(java,语音识别,开发语言)