Fei

Hi, I know we have new framework SpeechBrain now (which is very fantastic), but I still have old model trained with pytorch-kaldi. I would like to use it in Pytorch...

Can we resume training from the epoch we got interruption

4

Hi, my computer's power was down and the experiment was interrupted at epoch 13. Can we resume the training from where it was interrupted? Thank you.

How can I load a trained model in python with torch?

2

Hi, I have followed the librispeech cfg to train a model. Now I would like to load it in python code with torch. I will use it as a pretrained...

Training on multi-gpu very slow

4

I am training my ASR model with pytorch-kaldia, and notice the training time is very slow, 10% of 1 chunk is 10 mins. I have 10 chunk and will run...

The loss is 0

1

Hi, dear all, Recently, I ran experiment with CTC loss, which is based on Baidu's warp-ctc library. I use the default SGD optimizer. My data timestep is about 3500, the...

CSVLogger does not work

2

Hi, I would like to log the experiments on local only, so I changed the logger to CSVLogger in the `lasaft/trainer.py`: ``` log = args['log'] if log == 'False': args['logger']...

how can we replace a source with another one in a generated room

1

I need to test several individual sources in the same generated room. Now I iteratively generated the same room with the same parameters. Is there a way that we can...

problem with new keras

1

Hi, dear all, After I update the keras and seq2seq, I have a problem with the network running and get the error as below: Input 0 of the graph (indices...

issues when download the AVA dataset

3

It turns out that we don't have the permission to the google drive storing the cvs files. Could you share turn on the access?