定制热词

import os
import dashscope
from dashscope.audio.asr import VocabularyService, Recognition

# 从环境变量获取API Key
# 若没有配置环境变量，请用百炼API Key将下行替换为：dashscope.api_key = "sk-xxx"
dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")

def run_hotword_recognition_workflow():
    """一个完整的创建、使用和管理热词表的示例。"""
    
    service = VocabularyService()
    vocabulary_id = None
    
    # 1. 定义热词数据和目标模型
    target_model = "paraformer-realtime-v2"
    my_vocabulary_data = [
        {"text": "阿里云", "weight": 4, "lang": "zh"},
        {"text": "DashScope", "weight": 4, "lang": "en"},
        {"text": "语音识别", "weight": 3, "lang": "zh"}
    ]

    try:
        # 2. 创建热词表
        # SDK的create_vocabulary方法是同步的，它会等待异步任务完成后再返回ID
        print("正在创建热词表...")
        vocabulary_id = service.create_vocabulary(
            prefix="mycompany",  # 自定义前缀，用于分类管理
            target_model=target_model,
            vocabulary=my_vocabulary_data
        )
        print(f"热词表创建成功，ID: {vocabulary_id}")

        # 3. 查询并验证热词表内容
        retrieved_vocab = service.query_vocabulary(vocabulary_id)
        print("查询到的热词表内容:", retrieved_vocab)

        # 4. 使用热词表进行语音识别
        # 确保有一个名为 test_audio.wav 的16kHz采样率的音频文件
        print("\n正在使用热词表进行识别...")
        recognition = Recognition(
            model=target_model,
            format='wav',
            sample_rate=16000,
            callback=None,
            vocabulary_id=vocabulary_id,
            language_hints=['zh', 'en']  # 激活中英文热词
        )
        
        # [需要确认：请确保本地存在名为 test_audio.wav 的音频文件]
        result = recognition.call('asr_example.wav')
        print("识别结果：", result.output)

    except Exception as e:
        print(f"操作过程中发生错误: {e}")
        
    finally:
        # 5. 清理资源（在生产环境中根据需要决定是否删除）
        if vocabulary_id:
            print(f"\n准备删除热词表: {vocabulary_id}")
            service.delete_vocabulary(vocabulary_id)
            print("热词表已删除。")
            pass

if __name__ == "__main__":
    run_hotword_recognition_workflow()

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.audio.asr.vocabulary.VocabularyService;
import com.alibaba.dashscope.audio.asr.vocabulary.Vocabulary;
import com.alibaba.dashscope.exception.ApiException;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;

import java.io.File;
import java.util.ArrayList;
import java.util.List;

public class Main {
    // 若没有配置环境变量，请用百炼API Key将下行替换为：private static final String API_KEY = "sk-xxx";
    private static final String API_KEY = System.getenv("DASHSCOPE_API_KEY");

    public static void main(String[] args) {
        String targetModel = "paraformer-realtime-v2";
        String vocabularyId = null;
        VocabularyService service = new VocabularyService(API_KEY);

        try {
            // 1. 准备热词数据
            JsonArray vocabulary = new JsonArray();
            List<Hotword> wordList = new ArrayList<>();
            wordList.add(new Hotword("吴贻弓", 4, "zh"));
            wordList.add(new Hotword("阙里人家", 4, "zh"));

            for (Hotword word : wordList) {
                JsonObject jsonObject = new JsonObject();
                jsonObject.addProperty("text", word.text);
                jsonObject.addProperty("weight", word.weight);
                jsonObject.addProperty("lang", word.lang);
                vocabulary.add(jsonObject);
            }

            // 2. 创建热词表
            System.out.println("正在创建热词表...");
            Vocabulary myVocabulary = service.createVocabulary(
                    targetModel,
                    "mycompany",
                    vocabulary
            );
            vocabularyId = myVocabulary.getVocabularyId();
            System.out.println("热词表创建成功，ID: " + vocabularyId);

            // 3. 配置识别参数
            RecognitionParam param = RecognitionParam.builder()
                    .model("paraformer-realtime-v2")
                    .format("wav")
                    .sampleRate(16000)
                    .apiKey(API_KEY)
                    .vocabularyId(vocabularyId)
                    // “language_hints”只支持paraformer-v2和paraformer-realtime-v2模型
                    .parameter("language_hints", new String[] {"zh"})
                    .build();

            // 4. 执行识别
            // [需要确认：请确保项目根目录存在名为 test_audio.wav 的音频文件]
            System.out.println("\n正在使用热词表进行识别...");
            Recognition recognizer = new Recognition();
            String resultJson = recognizer.call(param, new File("asr_example.wav"));

            System.out.println("识别结果: " + resultJson);

        } catch (ApiException e) {
            System.err.println("API 操作失败: " + e.getMessage());
            System.err.println("HTTP状态码: " + e.getStatus());
        } catch (Exception e) {
            System.err.println("发生未知错误: " + e.getMessage());
            e.printStackTrace();
        } finally {
            // 5. 清理资源
            if (vocabularyId != null) {
                System.out.println("\n准备删除热词表: " + vocabularyId);
                try {
                    service.deleteVocabulary(vocabularyId);
                    System.out.println("热词表已删除。");
                } catch (Exception e) {
                    System.err.println("删除热词表失败: " + e.getMessage());
                }
            }
            System.exit(0);
        }
    }

    static class Hotword {
        String text;
        int weight;
        String lang;

        public Hotword(String text, int weight, String lang) {
            this.text = text;
            this.weight = weight;
            this.lang = lang;
        }
    }
}