Ai_GirlFriend/test_wav_asr.py

#!/usr/bin/env python3
"""
测试 WAV 格式 ASR
"""
import sys
import os
sys.path.append('.')

import requests
import base64
import wave
import struct
import math
import logging

# 设置日志
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def create_wav_file():
    """创建一个标准的 WAV 文件"""
    sample_rate = 16000
    duration = 3  # 3 秒
    
    # 生成音频样本
    samples = []
    for i in range(sample_rate * duration):
        t = i / sample_rate
        # 生成复合波形，模拟语音
        f0 = 200 + 100 * math.sin(2 * math.pi * 0.5 * t)  # 变化的基频
        sample = 0
        for harmonic in range(1, 5):
            amplitude = 1.0 / harmonic
            sample += amplitude * math.sin(2 * math.pi * f0 * harmonic * t)
        
        # 添加包络
        envelope = 0.5 * (1 + math.sin(2 * math.pi * 2 * t))
        final_sample = sample * envelope * 0.3
        
        # 转换为 16-bit 整数
        sample_int = int(16000 * final_sample)
        sample_int = max(-32767, min(32767, sample_int))
        samples.append(sample_int)
    
    # 写入 WAV 文件
    wav_file = "test_audio.wav"
    with wave.open(wav_file, 'wb') as wav:
        wav.setnchannels(1)  # 单声道
        wav.setsampwidth(2)  # 16-bit
        wav.setframerate(sample_rate)  # 16kHz
        
        # 写入样本数据
        for sample in samples:
            wav.writeframes(struct.pack('<h', sample))
    
    logger.info(f"创建 WAV 文件: {wav_file}, 时长: {duration} 秒")
    return wav_file

def test_wav_asr():
    """测试 WAV ASR"""
    
    # 创建 WAV 文件
    wav_file = create_wav_file()
    
    try:
        # 读取 WAV 文件
        with open(wav_file, 'rb') as f:
            wav_data = f.read()
        
        logger.info(f"WAV 文件大小: {len(wav_data)} 字节")
        
        # 转换为 base64
        wav_base64 = base64.b64encode(wav_data).decode('utf-8')
        logger.info(f"Base64 编码长度: {len(wav_base64)}")
        
        # 准备请求数据
        request_data = {
            'audio_data': wav_base64,
            'format': 'wav'
        }
        
        # 发送请求到后端
        url = "http://192.168.1.141:30102/voice/call/asr"
        headers = {
            'Content-Type': 'application/json',
            'Authorization': 'Bearer test_token'
        }
        
        logger.info(f"发送 ASR 请求到: {url}")
        
        response = requests.post(url, json=request_data, headers=headers, timeout=60)
        
        logger.info(f"响应状态码: {response.status_code}")
        logger.info(f"响应内容: {response.text}")
        
        if response.status_code == 200:
            result = response.json()
            logger.info(f"✅ ASR 请求成功")
            logger.info(f"识别结果: {result}")
            
            if 'data' in result and 'text' in result['data']:
                text = result['data']['text']
                logger.info(f"🎯 识别文本: {text}")
                
                # 检查结果
                if "未识别到语音内容" in text or "音频中未检测到有效语音" in text:
                    logger.info("✅ WAV 格式正确，但没有检测到语音（这是预期的，因为是纯音调）")
                    return True
                elif "音频格式解码失败" in text or "DECODE_ERROR" in text:
                    logger.error("❌ WAV 格式有问题")
                    return False
                else:
                    logger.info("✅ ASR 处理成功")
                    return True
            else:
                logger.warning("响应格式不符合预期")
                return False
        else:
            logger.error(f"❌ ASR 请求失败: {response.status_code}")
            return False
            
    except Exception as e:
        logger.error(f"❌ 测试失败: {e}")
        import traceback
        logger.error(f"错误堆栈: {traceback.format_exc()}")
        return False
    finally:
        # 清理文件
        try:
            if os.path.exists(wav_file):
                os.remove(wav_file)
        except:
            pass

if __name__ == "__main__":
    logger.info("开始测试 WAV ASR...")
    success = test_wav_asr()
    
    if success:
        logger.info("🎉 WAV ASR 测试成功！")
        logger.info("现在可以在前端测试录音功能了")
    else:
        logger.error("💥 WAV ASR 测试失败")
        sys.exit(1)