-
https://pytorch.org/blog/optimizing-cuda-rnn-with-torchscript/
samgd updated
5 years ago
-
We would like a keyword detection enhancement to DeepSpeech, i.e, the ability to detect a key word or phrase directly from a WAV audio file. We saw "keyword spotting" in the Meeting Notes as a potenti…
-
2019-04-22 10:46:08.222826: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at ctc_loss_op.cc:168 : Invalid argument: Saw a non-null label (index >= num_classes - 1) following a null…
-
2018-09-01 09:05:39.535363: W tensorflow/core/framework/op_kernel.cc:1192] Failed precondition: sequence_length(0)
-
Hello,
I noticed a number of CTC implementations in pure Theano and even Lasagne adaptation:
https://github.com/skaae/Lasagne-CTC
Although it needs some fixes to be compatible with RNN API recently m…
-
When I want to use the saved mode to get prediction based on that, it raises
```
File "/home/sgnbx/Downloads/projects/CRNN-with-STN-master/prediction.py", line 20, in
model = load_model('wei…
-
Really nice project btw!
the reason bi-lstm does not affect accuracy because lstm is more likely to model the language model(especially works for English words), but in Chinese, it depends on how y…
-
I only changed the dataset, when training more than 30W steps, the network cannot convergence, the edit lengths are always large(almost 1).
Any suggestions?
-
Hi, have you tried your code and any results?
I was using the same ctc loss, but it seems not stable. I was using SGD optimizer with learningrate-0.0001, but it can't converg.
-
I get the following warning while trying to use https://github.com/k2-fsa/icefall/pull/259
to restore the state dict of a sampler from a checkpoint.
```
lhotse/dataset/sampling/simple.py:144: UserW…