提升識別準確率

Python

import dashscope
from dashscope.audio.asr import *
import os


# 北京與新加坡地區的 API Key 不同。擷取 API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# 未配置環境變數時，將下行替換為：dashscope.api_key = "sk-xxx"
dashscope.api_key = os.environ.get('DASHSCOPE_API_KEY')

# 以下為新加坡地區URL，調用時請將WorkspaceId替換為真實的業務空間ID，各地區的URL不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# 以下為新加坡地區WebSocket URL，調用時請將WorkspaceId替換為真實的業務空間ID，各地區的URL不同。
dashscope.base_websocket_api_url = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference'
prefix = 'testpfx'
target_model = "fun-asr-realtime"

my_vocabulary = [
    {"text": "語音實驗室", "weight": 4}
]

service = VocabularyService()
vocabulary_id = service.create_vocabulary(
      prefix=prefix,
      target_model=target_model,
      vocabulary=my_vocabulary)

try:
    if service.query_vocabulary(vocabulary_id)['status'] == 'OK':
        recognition = Recognition(model=target_model,
                              format='wav',
                              sample_rate=16000,
                              callback=None,
                              vocabulary_id=vocabulary_id)
        result = recognition.call('asr_example.wav')
        print(result.output)
finally:
    # 無論識別成功與否都刪除熱詞列表，避免佔用配額
    service.delete_vocabulary(vocabulary_id)

Java

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.audio.asr.vocabulary.Vocabulary;
import com.alibaba.dashscope.audio.asr.vocabulary.VocabularyService;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
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 {
    // 北京與新加坡地區的 API Key 不同。擷取 API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // 未配置環境變數時，將下行替換為：public static String apiKey = "sk-xxx"
    public static String apiKey = System.getenv("DASHSCOPE_API_KEY");

    public static void main(String[] args) throws NoApiKeyException, InputRequiredException {
        // 以下為新加坡地區URL，調用時請將WorkspaceId替換為真實的業務空間ID，各地區的URL不同。
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
        // 以下為新加坡地區WebSocket URL，調用時請將WorkspaceId替換為真實的業務空間ID，各地區的URL不同。
        Constants.baseWebsocketApiUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";

        String targetModel = "fun-asr-realtime";

        JsonArray vocabularyJson = new JsonArray();
        List<Hotword> wordList = new ArrayList<>();
        wordList.add(new Hotword("語音實驗室", 4));

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

        VocabularyService service = new VocabularyService(apiKey);
        Vocabulary vocabulary = service.createVocabulary(targetModel, "testpfx", vocabularyJson);

        try {
            if ("OK".equals(service.queryVocabulary(vocabulary.getVocabularyId()).getStatus())) {
                Recognition recognizer = new Recognition();
                RecognitionParam param =
                        RecognitionParam.builder()
                                .model(targetModel)
                                .apiKey(apiKey)
                                .format("wav")
                                .sampleRate(16000)
                                .vocabularyId(vocabulary.getVocabularyId())
                                .build();

                try {
                    System.out.println("識別結果：" + recognizer.call(param, new File("asr_example.wav")));
                } catch (Exception e) {
                    e.printStackTrace();
                } finally {
                    // 關閉 WebSocket 串連
                    recognizer.getDuplexApi().close(1000, "bye");
                }
            }
        } finally {
            // 無論識別成功與否都刪除熱詞列表，避免佔用配額
            service.deleteVocabulary(vocabulary.getVocabularyId());
        }
        System.exit(0);
    }
}

class Hotword {
    String text;
    int weight;

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

詞表增強

通過 user（input_text）傳入領域術語詞表，無需 assistant 訊息。

{
    "model": "fun-asr-flash-2026-06-15",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "Kubernetes Istio Envoy service mesh sidecar proxy"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "當前待識別的音頻URL或Base64"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {}
}

多輪對話上下文

傳入前幾輪的識別結果（user / input_text）和大模型回複（assistant / text）。

{
    "model": "fun-asr-flash-2026-06-15",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_text",
                        "text": "前輪使用者語音的識別結果"
                    }
                ]
            },
            {
                "role": "assistant",
                "content": [
                    {
                        "type": "text",
                        "text": "前輪大模型的回複內容"
                    }
                ]
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "當前待識別的音頻URL或Base64"
                        }
                    }
                ]
            }
        ]
    },
    "parameters": {}
}