Dylan Fox

You can also try increasing the data you're training on. By default the max wav length is set to 10 seconds (https://github.com/baidu-research/ba-dls-deepspeech/blob/master/data_generator.py#L53-L54) which excludes a good portion of the data...

I'm seeing this issue too. I switched to using the Keras optimizer instead of Lasagne's, making the same changes that @aglotero cited above. For the first 8990 (out of 12188)...

FWIW I fixed this by dropping the learning rate and removing the dropout layers I added. I left the clipnorm value at 100.

@a00achild1 I don't think you want clipnorm set to 1. Were you getting NaNs before with the clipnorm set to a higher val (~100)?

What is your learning rate? Trying dropping that and keeping the clipnorm higher.

FWIW, I ran into this issue too. I just dropped down to Ubuntu 14.04 (from 16.04), and that solved this (and other) issues.