ASR training from scratch #2968
Description
Describe the bug
I am trying to retrain an ASR model on LibriSpeech from scratch with this recipe /speechbrain/templates/speech_recognition/ASR.
We are training on an A100 GPU, and even with a low batch size of 8, the model is consuming a very large amount of memory. Could you advise why this might be happening?
We are observing that the training seems to not actually progress — the train loss doesn’t change, and CER and WER remain very high. Any insights on what could be causing this?
Thank you.
I attach ASR configuration: train.yaml.
Expected behaviour
The model should train normally on LibriSpeech from scratch, with train loss gradually decreasing and CER/WER improving over epochs, without consuming excessive GPU memory even at batch size 8.
To Reproduce
No response
Environment Details
No response
Relevant Log Output
Additional Context
No response