Not getting a prediction on speech example.

[tshields44]

Is this normal after all this time? I know it's the small dataset but it hasnt given one prediction at all since the beginning of just a blank space.

Epoch 88/inf, loss=6.077: 97%|█████████▋| 2352/2432 [25:49<00:45, 1.74samples/s]
[INFO 2017-04-01 23:52:55,254 kur.model.executor:369] Training loss: 6.077
Validating, loss=372.212: 94%|█████████▍| 256/271 [00:45<00:02, 6.13samples/s]
[INFO 2017-04-01 23:53:40,300 kur.model.executor:206] Validation loss: 372.212
Prediction: ""
Truth: "that's it on your account"
Total wall-clock time: 38h 20m 31s
Training wall-clock time: 37h 08m 23s
Validation wall-clock time: 01h 12m 08s
Batch wall-clock time: 37h 07m 42s

Thanks for all your help in advance.

[ajsyp]

No, it isn't. If your model only spits out spaces (or an empty string), you can bet something went wrong. I discovered a problem with Keras 2 that impacted the speech model, and pushed fixes yesterday (2017-03-31). If you try this update and still get spaces, let me know!

[tshields44]

This worked thank you.

[nkansal96]

I'm still getting this issue with version 0.7.0. I'm using the default examples/speech.yml Kurfile and I noticed that the loss isn't changing much across epochs as well.

Any tips on debugging?

EDIT: Here is a screenshot from the output:

Are you able to help @ajsyp?