-
I have used your code in order to make recurrent batch normalization.
My encoder is a pyramidal bidirectional lstm.
Here is the error message.
```
InvalidArgumentError (see above for traceback…
-
Hi~ It's a wonderful code and thank you for your sharing :)
1) I notice that the train set and test set have been divided randomly and I want to replace the emodb with my corpus. Can i get the result…
-
Dear author, I find that you have given the config files about the experiment . And this experiment is based on SWB corpus. I tried using the this corpus reproduce your results. But I'm not familia…
-
Hi, thanks for your code!I have a question,can you give me some advice? I run your code,but only get F1 score 82.73,never get 83.13 in your log file.If you have time, thanks for your advice.
-
I'm creating a conda environment with Python 3.7 and then installing the requisites (numpy, scipy, cython, mido and pyfftw), but cannot install madmom.
Note: Before trying with 3.7, I had tried with …
-
Has anyone compaired the performance between k2 CTC loss implementation and the CTCLoss in PyTorch?
I tried to write a K2CTCLoss with k2 to replace torch.nn.CTCLoss and did some experiments using …
-
I need to train a multi-label classifier for text topic classification task. Having searched around the internet, I follow the suggestion to use sigmoid + binary_crossentropy. But I can't get good res…
-
Hi, Matthew
I am new to Speech Information Processing and Julia, and I am currently working on TIMIT database. I am very excited to find your recipe for timit training using Julia. (this repo is th…
-
**Environment:**
1. Framework: (TensorFlow, Keras, PyTorch, MXNet)
2. Framework version:
3. Horovod version:
4. MPI version:
5. CUDA version:
6. NCCL version:
7. Python version:
8. OS and vers…
-
作者您好，最近在重现您工作的时候，对于模型HUB模型第一层的输入有一些困惑，想要请教一下；
我看到您论文中描述，第一层的behavior gate是使用的是micro-behaviors的信息，那么这一层的input,即x使用的是哪一个embedding？也是behaviors吗？