You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
At the start of waveglow training, i got the error: RuntimeError: Given transposed=1, weight of size 40 40 1024, expected input[12, 80, 81] to have 40 channels, but got 80 channels instead
I guess there is a place in the project where, a fixed mel size of 80 is expencted but i could not figure out where it is.
Thanks.
The text was updated successfully, but these errors were encountered:
fatihkiralioglu
changed the title
Reducing n_mel_channels 40: Error
Reducing n_mel_channels to 40: Error of size mismatch
Jun 5, 2020
Hi, I'm trying to model a 8khz tacotron2 and waveglow model. In this scheme, I also reduce the n_mel_channels to 40.
At the start of waveglow training, i got the error:
RuntimeError: Given transposed=1, weight of size 40 40 1024, expected input[12, 80, 81] to have 40 channels, but got 80 channels instead
I guess there is a place in the project where, a fixed mel size of 80 is expencted but i could not figure out where it is.
Thanks.
The text was updated successfully, but these errors were encountered: