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
{{ message }}
This repository has been archived by the owner on Aug 3, 2021. It is now read-only.
Following the paper Jason Li et al. Jasper: An End-to-End Convolutional Neural Acoustic Model, 2019 https://arxiv.org/pdf/1904.03288.pdf, I have been training jasper models with different configurations. When training 10x3 and 10x5 configurations it seems that saved model.pt are the same size (around 2.5gb). I do not understand this point as I was expecting 10x3 to be much lighter (both in disk space and in GPU RAM for inference).
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Following the paper Jason Li et al. Jasper: An End-to-End Convolutional Neural Acoustic Model, 2019 https://arxiv.org/pdf/1904.03288.pdf, I have been training jasper models with different configurations. When training 10x3 and 10x5 configurations it seems that saved model.pt are the same size (around 2.5gb). I do not understand this point as I was expecting 10x3 to be much lighter (both in disk space and in GPU RAM for inference).
The text was updated successfully, but these errors were encountered: