-
Notifications
You must be signed in to change notification settings - Fork 297
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.
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
Nan outputs from encoder #1731
Comments
There should be some logs telling you how to do with it. Have you followed the logs? |
I am using a pretrained model to decode.I am not sure about which logs you are talking about |
Would you mind posting all of the logs? The info you give is toooo limited. |
These are the args i used :
|
Also, would you mind sharing the command you are using? More details are always helpful. |
Sorry ,i just clicked enter before pasting all ,here are the code blocks i am using These are the args i used : #initiated the model using above args and i used librispeech cuts dataset args1=Namespace(epoch=30, avg=1, use_averaged_model=True, exp_dir='../../../../../icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/exp/', lang_dir='../../../../../icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/data/lang_bpe_500/', decoding_method='fast_beam_search', iter=0, context_size=2, max_sym_per_frame=1, return_cuts=True, on_the_fly_feats=False, input_strategy='PrecomputedFeatures', max_duration=10, num_workers=2) librispeech = LibriSpeechAsrDataModule(args1) test_clean_dl = librispeech.test_dataloaders(test_clean_cuts) test_sets = ["test-clean", "test-other"] #Used first input to decode #i,j are feature=j["inputs"] import torch feature = torch.nn.functional.pad( Here for encoder_out i am getting nans |
Could you share the complete file? You can upload your code file as an attachment in the comment. |
will this works? |
Could you post a runnable PYTHON CODE FILE? We need to know which script you are using. |
By the way, I suggest that you follow the doc |
thats the ipynb file i am using to run ,i am unable to attach py or ipynb file.I am trying to implement this https://github.com/k2-fsa/icefall/blob/master/egs/librispeech/ASR/pruned_transducer_stateless2/beam_search.py#L444 for stateless7 streaming model ,I am trying to see the outputs at each timestep. |
I think have loaded the model dict of pretrained model pretty much the same ,you guys have implemented.For model.decoder i am able to see the model is predicting numbers .I dont know why encoder is predicting nan |
I am getting nan outputs from the encoder of pruned transducer streaming model.
tensor([[[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan, ..., nan, nan, nan],
...,
[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan, ..., nan, nan, nan]]], grad_fn=)
I am running on mac cpu.Any suggestions?
The text was updated successfully, but these errors were encountered: