mat1 and mat2 shapes cannot be multiplied (1323x9248 and 1568x32)

sooftware / conformer

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

Apache License 2.0

958 stars 175 forks source link

Closed jcgeo9 closed 2 years ago

jcgeo9 commented 2 years ago

These are the shapes of my input, input_len, target, target_len where batch size=27

This is the setup I am running (only using first batch to check that is working before training with all the batches)

This is the error I am getting

I need some assistance here please:)

sooftware commented 2 years ago

Is this solved?

jcgeo9 commented 2 years ago

yes i had to transpose the input from [32, 201, 1162] to [32, 1162, 201] (batch, seq_len, dim)