基于Vue + SpringBoot实现离线MP3转文字的具体方案

<template>
  <div>
    <input type="file" accept=".mp3" @change="handleFileUpload" />
    <button @click="transcribe" :disabled="!file">转换</button>
    <div v-if="result">{{ result }}</div>
    <div v-if="loading">转换中...</div>
  </div>
</template>
 
<script setup>
import { ref } from 'vue';
import axios from 'axios';
 
const file = ref(null);
const result = ref('');
const loading = ref(false);
 
const handleFileUpload = (event) => {
  file.value = event.target.files[0];
};
 
const transcribe = async () => {
  if (!file.value) return;
  
  loading.value = true;
  result.value = '';
  
  const formData = new FormData();
  formData.append('file', file.value);
  
  try {
    const response = await axios.post('/api/transcribe', formData, {
      headers: {
        'Content-Type': 'multipart/form-data'
      }
    });
    result.value = response.data.text;
  } catch (error) {
    console.error('转换失败:', error);
    result.value = '转换失败，请重试';
  } finally {
    loading.value = false;
  }
};
</script>

<dependencies>
    <!-- Spring Boot Web -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    
    <!-- JNA for native library access -->
    <dependency>
        <groupId>net.java.dev.jna</groupId>
        <artifactId>jna</artifactId>
        <version>5.10.0</version>
    </dependency>
    
    <!-- FFmpeg wrapper (optional) -->
    <dependency>
        <groupId>org.bytedeco</groupId>
        <artifactId>javacv-platform</artifactId>
        <version>1.5.6</version>
    </dependency>
</dependencies>

@RestController
@RequestMapping("/api")
public class TranscriptionController {
    
    @PostMapping("/transcribe")
    public ResponseEntity<TranscriptionResult> transcribeAudio(@RequestParam("file") MultipartFile file) {
        try {
            // 1. 保存上传的文件到临时目录
            Path tempFile = Files.createTempFile("audio_", ".mp3");
            file.transferTo(tempFile);
            
            // 2. 转换音频格式（如果需要）
            Path wavFile = convertToWav(tempFile);
            
            // 3. 调用语音识别引擎
            String text = SpeechRecognitionEngine.transcribe(wavFile);
            
            // 4. 清理临时文件
            Files.deleteIfExists(tempFile);
            Files.deleteIfExists(wavFile);
            
            return ResponseEntity.ok(new TranscriptionResult(text));
        } catch (Exception e) {
            return ResponseEntity.status(HttpStatus.INTERNAL_SERVER_ERROR)
                    .body(new TranscriptionResult("转换失败: " + e.getMessage()));
        }
    }
    
    private Path convertToWav(Path inputFile) throws Exception {
        // 使用FFmpeg将MP3转换为WAV（如果需要）
        // 实现略...
        return inputFile; // 简化示例
    }
}
 
class TranscriptionResult {
    private String text;
    
    // 构造函数、getter和setter
}

public class SpeechRecognitionEngine {
    
    private static Model model;
    private static Recognizer recognizer;
    
    static {
        // 初始化Vosk模型
        String modelPath = "path/to/vosk-model";
        model = new Model(modelPath);
        recognizer = new Recognizer(model, 16000.0f);
    }
    
    public static String transcribe(Path audioFile) throws IOException, UnsupportedAudioFileException {
        // 读取音频文件
        AudioInputStream ais = AudioSystem.getAudioInputStream(audioFile.toFile());
        AudioFormat format = ais.getFormat();
        
        // 确保音频格式兼容
        if (format.getSampleRate() != 16000 || format.getSampleSizeInBits() != 16) {
            throw new UnsupportedAudioFileException("不支持的音频格式");
        }
        
        // 读取音频数据
        byte[] buffer = new byte[4096];
        int bytesRead;
        StringBuilder result = new StringBuilder();
        
        while ((bytesRead = ais.read(buffer)) >= 0) {
            // 处理音频数据
            int status = recognizer.acceptWaveForm(buffer, bytesRead);
            if (status > 0) {
                result.append(recognizer.getResult()).append(" ");
            }
        }
        
        // 获取最终结果
        result.append(recognizer.getFinalResult());
        ais.close();
        
        return result.toString();
    }
}