Audios wav pytorch

audio
1

good day your support this error RuntimeError: mat1 dim 1 must match mat2 dim 0, I am working pytorch to classify wav audios,
BATCH_SIZE = 32 ###128 para 4conv
EPOCHS = 10
LEARNING_RATE = 0.001

ANNOTATIONS_FILE = “…/data_aymara/metadata/aymara_sound.csv”
AUDIO_DIR = “…/data_aymara/audio”
SAMPLE_RATE = 22050
NUM_SAMPLES = 22050

from torch import nn
from torchsummary import summary
class CNNNetwork(nn.Module):

def __init__(self):
    super().__init__()
    self.conv1 = nn.Sequential(
        nn.Conv2d(
            in_channels=1,
            out_channels=16,
            kernel_size=3,
            stride=1,
            padding=2
        ),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2)
    )
    self.conv2 = nn.Sequential(
        nn.Conv2d(
            in_channels=16,
            out_channels=32,
            kernel_size=3,
            stride=1,
            padding=2
        ),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2)
    )
  
    self.flatten = nn.Flatten()
    self.linear = nn.Linear(32 * 3 * 4, 3)####2 convoluciones ####3 son las clases de salida, 32 capas ocultas
    self.softmax = nn.Softmax(dim=1)

def forward(self, input_data):
    x = self.conv1(input_data)
    x = self.conv2(x)
    x = self.flatten(x)
    logits = self.linear(x)
    predictions = self.softmax(logits)
    return predictions
2

What’s the shape of input_data?

3

in one folder I have sound files in wav format and in another folder an excel csv containing the name of the wav sound file and the category it is and based on the two trainings.

4 
    solved by printing xshape and setting the value to linear
    print(x.shape)###con esto se sabe que debe ir en la seccion A
    x = self.flatten(x)
    
    x = x.view(x.size(0), -1)