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
what's the value of (batch_size, feat_dim, chunk_len) , (batch_size, 30, ?) ?
I'm not sure if I understand the question. chunk_len is determined by kaldi when creating the archives. It represents the temporal dimension: number of MFCC frames in the utterance.
Is MFCC of the feature in your experiment?
Yes, each input sample is a matrix - a sequence of MFCC features.
Have you try other tools to extract features, such as librosa ...?
The most common reason (in this repo) was due to the stats pooling layer. If all inputs are zero or same, then var(0) seems to result in NaN loss.
Please use the -noiseEps to avoid this.
pytorch_xvectors/train_xent.py
Line 91 in 350e4b5
Thanks!
The text was updated successfully, but these errors were encountered: