Michael Nguyen
Michael Nguyen
@Mrinal18 You mind sharing the changes you've made to the model?
Let's keep this open.
Getting the same. Any fix? @FactoDeepLearning @HawkAaron **EDIT** This was due to me not putting acts, labels, input_len, and label_len to .cuda() in pytorch. Fix now. **EDIT2** I'm still getting...
After some debugging, I think there might be a bug in this library @HawkAaron. I am printing the cost at this line here https://github.com/HawkAaron/warp-transducer/blob/master/pytorch_binding/warprnnt_pytorch/__init__.py#L37 and the `RuntimeError: CUDA error: an...
@yetiancn unfortunately no I did not find a solution :/ instead I just switched over to use the tensorflow ctc implementation
you'll have to train your own! https://github.com/kpu/kenlm. make sure you preprocess the kenlm training data same way you preprocess the speech recognition model data
looks like you're trying to train a speech recognition model. I think the size of your spectrogram is too big and maybe causing python to get stuck in a loop....
@haoxiangsnr ping! sorry for disturbance, this question has been lingering in my head for a while!
@MXGray Thank you so much! The one that you linked to doesn't seem to perform as well as the on https://keithito.github.io/audio-samples/. Are they the same model? Here is a sample...