音频增强测试：使用 PyTorch 生成增强音频

该代码演示了如何使用预训练的生成器模型来增强音频。

import argparse
import os
import wave

import numpy as np
import torch
import torch.nn as nn
from scipy.io import wavfile
from torch.autograd import Variable
from tqdm import tqdm
import matplotlib.pyplot as plt

from data_preprocess import slice_signal, window_size, sample_rate
from model import Generator
from utils import emphasis

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Test Single Audio Enhancement')
    parser.add_argument('--file_name', type=str, required=True, help='audio file name')
    parser.add_argument('--epoch_name', type=str, required=True, help='generator epoch name')

    opt = parser.parse_args()
    FILE_NAME = opt.file_name
    EPOCH_NAME = opt.epoch_name

    generator = Generator()
    generator.load_state_dict(torch.load('epochs/' + EPOCH_NAME, map_location='cpu'))
    if torch.cuda.is_available():
        generator.cuda()

    noisy_slices = slice_signal(FILE_NAME, window_size, 1, sample_rate)
    enhanced_speech = []
    for noisy_slice in tqdm(noisy_slices, desc='Generate enhanced audio'):
        z = nn.init.normal(torch.Tensor(1, 1024, 8))
        noisy_slice = torch.from_numpy(emphasis(noisy_slice[np.newaxis, np.newaxis, :])).type(torch.FloatTensor)
        if torch.cuda.is_available():
            noisy_slice, z = noisy_slice.cuda(), z.cuda()
        noisy_slice, z = Variable(noisy_slice), Variable(z)
        generated_speech = generator(noisy_slice, z).data.cpu().numpy()
        generated_speech = emphasis(generated_speech, emph_coeff=0.95, pre=False)
        generated_speech = generated_speech.reshape(-1)
        enhanced_speech.append(generated_speech)

    enhanced_speech = np.array(enhanced_speech).reshape(1, -1)
    file_name = os.path.join(os.path.dirname(FILE_NAME),
                             'enhanced_{}.wav'.format(os.path.basename(FILE_NAME).split('.')[0]))
    wavfile.write(file_name, sample_rate, enhanced_speech.T)



    # 读取音频文件
    w1 = wave.open('p232_036.wav', 'rb')
    w2 = wave.open('enhanced_p232_036.wav', 'rb')

    # 获取声道数、采样宽度和帧率
    channels1 = w1.getnchannels()
    channels2 = w2.getnchannels()
    sample_width1 = w1.getsampwidth()
    sample_width2 = w2.getsampwidth()
    framerate1 = w1.getframerate()
    framerate2 = w2.getframerate()

    # 读取音频数据
    frames1 = w1.readframes(-1)
    frames2 = w2.readframes(-1)

    # 将音频数据转换为numpy数组
    signal1 = np.frombuffer(frames1, dtype='int16')
    signal2 = np.frombuffer(frames2, dtype='int16')

    # 计算音频时长
    duration1 = len(signal1) / (framerate1 * channels1)
    duration2 = len(signal2) / (framerate2 * channels2)

    # 生成时间轴
    time1 = np.linspace(0, duration1, len(signal1))
    time2 = np.linspace(0, duration2, len(signal2))

    # 绘制波形图
    plt.figure()
    plt.subplot(2, 1, 1)
    plt.plot(time1, signal1)
    plt.title('Waveform of Audio 1')
    plt.xlabel('Time (s)')
    plt.ylabel('Amplitude')
    plt.subplot(2, 1, 2)
    plt.plot(time2, signal2)
    plt.title('Waveform of Audio 2')
    plt.xlabel('Time (s)')
    plt.ylabel('Amplitude')
    plt.show()

    # 关闭音频文件
    w1.close()
    w2.close()

错误解析：

wave.Error: unknown format: 3 这个错误通常是因为音频文件格式不受支持导致的。

解决方法：

1. 确保使用支持的音频格式，例如 WAV 格式。
2. 使用其他库，例如 pydub，来打开和处理音频文件。
3. 检查音频文件的元数据以确保它们符合所需的格式。