stalevna

> Do you mean SEA? > > You refer to the SEA paper for training details. Hi! Could you point me to the SEA paper? I want to make sure...

Thank you so much! You are simply the best!

Hi! Could you kindly what are the appropriate loss_gens when training the model for experiments 1-4?

> Can you expand the entire stack frame and paste the entire error here. > > It's a Numba error when calculating the loss, it has probably little to do...

> Can you print out the system details - pytorch, Nemo, Numba versions. > > Seems to be the Numba kernels call for spec augment, but there shouldn't be a...

> Hmm, ivr never tried it with Numba 0.56. I will try it locally later this month, I'm on vacation till the 19th. Thank you so much for helping and...

checked with numba==0.53.1 everything worked

> Interesting. Also, numba just had a release of 0.56.2 which said it had cuda function caching bugfixes. Doubtful it's your case but could you try it ? Seems like...

As I understand it's an example from LJspeech dataset. I am also interested what's the minimum amount of wav files for train and dev? > > Your dataset should be...