Closed bagavi closed 3 years ago
I'd recommend you increase warmup_ratio to 0.12. Also, your batch size is small - we never tried such small bs, but this means that you have to use smaller bs than in our experiments.
Could you clarify “you have to use smaller bs than in our experiment”. Do you mean smaller lr(learning rate)?
Also, what is the reason behind .12 warmup ratio for fine tuning vs .02 warmup ratio for training from scratch?
Thanks!
Goal: Fine tuning Quartznet 15x5 with test_clean_100 plus vacuum noise (10db snr).
Setting: I am using speech2text.py script to train with a single small GPU with
batch size=8, lr = 1e-4, warm_ratio=0.02, num_epochs = 200
and rest of the parameters are default. I have attached the screen shot of WandB board.Problem: The WER is stuck to 0.3 (with noise) and 0.2 (without noise) from epoch 4 to 14.
Questions:
Is it possible to share the WandB boards for the fine-tuning from your latest papers?
Thanks in advance and congratulations for this awesome work :)