impress_asr_input/src/main.ts

/**
 * Impress ASR Input - 主入口
 * 命令行模式入口文件
 */

import { Command } from 'commander';
import { SpeechRecognizer, RecognitionResult } from './core/speech-recognizer.js';
import { TextOutput } from './core/text-output.js';
import { readFileSync } from 'fs';
import { fileURLToPath } from 'url';
import { dirname, join } from 'path';

const __dirname = dirname(fileURLToPath(import.meta.url));
const packageJson = JSON.parse(
  readFileSync(join(__dirname, '../package.json'), 'utf-8')
);

const program = new Command();

program
  .name('impress-asr-input')
  .description('基于 ONNX 的本地语音识别输入工具')
  .version(packageJson.version);

program
  .command('start')
  .description('开始语音识别')
  .option('-l, --language <lang>', '识别语言', 'zh')
  .option('-m, --model <path>', '模型文件路径（可选，无模型时以配置模式启动）')
  .option('-o, --output <mode>', '输出模式：clipboard|keyboard|both', 'clipboard')
  .action(async (options) => {
    console.log('🎤 Impress ASR Input');
    console.log(`   版本：${packageJson.version}`);
    console.log(`   语言：${options.language}`);
    console.log(`   输出：${options.output}`);

    // 检查模型文件是否存在
    const { existsSync } = await import('fs');
    const modelPath = options.model || join(__dirname, '../models/model.onnx');

    if (!existsSync(modelPath)) {
      console.log('\n⚠️  未检测到模型文件，以配置模式启动');
      console.log('\n📥 模型下载指引:');
      console.log('   1. SenseVoice (推荐): https://huggingface.co/FunAudioLLM/SenseVoice');
      console.log('   2. Whisper: https://huggingface.co/onnx-community/whisper-base');
      console.log('   3. Paraformer: https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punct');
      console.log('\n📁 将下载的模型文件放入以下目录之一:');
      console.log('   - ./models/sensevoice.onnx');
      console.log('   - ./models/whisper.onnx');
      console.log('   - ./models/paraformer.onnx');
      console.log('\n💡 或使用 --model 参数指定模型路径');
      console.log('   示例：npm start -- start -m /path/to/your/model.onnx');
      return;
    }

    console.log(`   模型：${modelPath}`);

    const recognizer = new SpeechRecognizer({
      modelPath,
      language: options.language,
      useVad: true,
      beamSize: 5,
    });

    const textOutput = new TextOutput({
      outputMode: options.output as 'clipboard' | 'keyboard' | 'both',
      autoPaste: true,
      delayMs: 50,
    });

    // 绑定事件
    recognizer.on('ready', () => {
      console.log('✅ 模型加载完成，开始识别...');
      recognizer.start();
    });

    recognizer.on('result', (result: RecognitionResult) => {
      console.log(`📝 ${result.text}`);
      textOutput.output(result);
    });

    recognizer.on('error', (error: Error) => {
      console.error('❌ 识别错误:', error.message);
      process.exit(1);
    });

    // 初始化并开始
    try {
      await recognizer.initialize();
      // 注意：音频采集在纯 Node.js 环境需要额外处理
      // 这里仅作为框架演示
      console.log('⚠️  当前为演示模式，完整功能需要 Electron 环境');
    } catch (error) {
      console.error('❌ 启动失败:', error);
      process.exit(1);
    }

    // 优雅退出
    process.on('SIGINT', async () => {
      console.log('\n🛑 停止识别...');
      recognizer.stop();
      await recognizer.release();
      process.exit(0);
    });
  });

program
  .command('transcribe')
  .description('转写音频文件')
  .argument('<file>', '音频文件路径')
  .option('-l, --language <lang>', '识别语言', 'zh')
  .option('-m, --model <path>', '模型文件路径')
  .option('-o, --output <file>', '输出文件路径')
  .action(async (file, options) => {
    console.log(`🎵 转写文件：${file}`);
    console.log(`   语言：${options.language}`);

    // TODO: 实现文件转写功能
    console.log('⚠️  文件转写功能开发中...');
  });

program
  .command('list-devices')
  .description('列出可用音频设备')
  .action(() => {
    console.log('🎧 可用音频设备:');
    // TODO: 实现设备列表功能
    console.log('⚠️  设备列表功能开发中...');
  });

program.parse();