model.py

import torch
import torch.nn as nn
import torch.nn.functional as F

class AudioCNN(nn.Module):
    def __init__(self, num_classes):
        super(AudioCNN, self).__init__()

        # 1D conv layers
        self.conv1 = nn.Conv1d(1, 16, kernel_size=3, stride=1, padding=1)
        self.pool1 = nn.MaxPool1d(2)
        self.conv2 = nn.Conv1d(16, 32, kernel_size=3, stride=1, padding=1)
        self.pool2 = nn.AdaptiveMaxPool1d(64)  # output length fixed at 64

        # Fully connected layers
        self.fc1 = nn.Linear(32 * 64, 128)
        self.fc2 = nn.Linear(128, num_classes)

    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x