search

lucasnewman / best-rq-pytorch

Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.
MIT License
71 stars 7 forks source link

What are the GPU memory specs needed to run pretraining and kmeans? #5

Open xanguera opened 7 months ago

xanguera commented 7 months ago

Hi, I am trying to run the pretraining of the full model (which should have ~650M parameters) in a 24GB GPU card and it only runs if I set the batch size to 1 (totally useless training). What would be the memory necessary to run the full training with the preset batch size? Also, Once finished training, I tried to run the Kmeans fitting script and it seems to require even more memory. Any idea as well on what is needed?

Thanks!

xanguera commented 7 months ago

I solved the second part of the question by adding an audio file max length (like it already exists in pretrain.py).