audio_process.py

import torch
import torch.nn as nn


class AudioEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 64, (3,3), (2,1), (1,1))
        self.bn1 = nn.BatchNorm2d(64)
        self.relu1 = nn.ReLU()
        self.maxpool1 = nn.MaxPool2d((3,1),(2,1))
        self.conv2 = nn.Conv2d(64, 192, (3,3), (1,1), (1,1))
        self.bn2 = nn.BatchNorm2d(192)
        self.relu2 = nn.ReLU()
        self.maxpool2 = nn.MaxPool2d((3,3),(2,2))
        self.conv3 = nn.Conv2d(192, 384, (3,3), (1,1), (1,1))
        self.bn3 = nn.BatchNorm2d(384)
        self.relu3 = nn.ReLU()
        self.conv4 = nn.Conv2d(384, 256, (3,3), (1,1), (1,1))
        self.bn4 = nn.BatchNorm2d(256)
        self.relu4 = nn.ReLU()
        self.conv5 = nn.Conv2d(256, 256, (3,3), (1,1), (1,1))
        self.bn5 = nn.BatchNorm2d(256)
        self.relu5 = nn.ReLU()
        self.maxpool5 = nn.MaxPool2d((2,3),(2,2))
        self.conv6 = nn.Conv2d(256, 512, (4,3), (1,1), (0,1))
        self.bn6 = nn.BatchNorm2d(512)
        self.relu6 = nn.ReLU()
        self.conv7 = nn.Conv2d(512, 512, kernel_size=(1,1))
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu1(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu2(x)
        x = self.maxpool2(x)
        x = self.conv3(x)
        x = self.bn3(x)
        x = self.relu3(x)
        x = self.conv4(x)
        x = self.bn4(x)
        x = self.relu4(x)
        x = self.conv5(x)
        x = self.bn5(x)
        x = self.relu5(x)
        x = self.maxpool5(x)
        x = self.conv6(x)
        x = self.bn6(x)
        x = self.relu6(x)
        x = self.conv7(x)
        x = x.squeeze(-2)
        return x


if __name__ == "__main__":
    net = AudioEncoder()
    x = torch.randn(1, 1, 80, 20)
    y = net(x)
    print(y.shape)