New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Librispeech #36

Open

arattari opened this issue Sep 11, 2018 · 1 comment

arattari commented Sep 11, 2018 •

edited

Loading

Did you ever this this code running with the Librispeech data? I'm currently getting an error on training:

Traceback (most recent call last):
  File "train.py", line 158, in <module>
    run(config)
  File "train.py", line 113, in run
    run_state = run_epoch(model, optimizer, train_ldr, *run_state)
  File "train.py", line 32, in run_epoch
    loss = model.loss(batch)
  File "/Users/user/speech_sandbox/speech/speech/models/seq2seq.py", line 62, in loss
    size_average=False)

RuntimeError: Assertion 'cur_target >= 0 && cur_target < n_classes' failed.

How can I determine the output of the network size versus the number of classes that are trying to be fit?

The text was updated successfully, but these errors were encountered:

Author

arattari commented Oct 3, 2018

I guess a followup question would be if anything has successfully trained the seq2seq, if they could let me know how they did it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment