Roman Vygon

Results 4 comments of Roman Vygon

Hi @bieltura! I am grateful for your response and sorry that the code didn't work as intended. I've added dists and probs files corresponding to the 12 and 35 classes...

Currently working on porting this code to a newer NeMo version, that would support multi-gpu balanced batches, but so far my only advice would be to decrease batch_classes while increasing...

Please see if uncommenting [this](https://github.com/roman-vygon/triplet_loss_kws/blob/master/layers/l2.py#L36) line helps, or the @ToughmanL's answer.

> Dear author, this google link seems invalid, can you just reshare the files 'convert_path_prefix.ipynb'? Thanks a lot! Hi! Terribly sorry for the missing files, I've lost access to them...