-
## Checklist
- [x] I have searched in [existing issues](https://github.com/BrikerMan/Kashgari/issues?utf8=%E2%9C%93&q=is%3Aissue+) but did not find the same one.
## Environment
* OS [e.g. Mac…
-
`loaded_model = torch.load('BLSTM-CRF_bie_model_best.pt')`
`torch.onnx.export(loaded_model, inputs, "BLSTM_onnx.pt")`
*`inputs` is a dummy input that is in correct form for the built model
I'm t…
-
## ❓ Questions and Help
### Please note that this issue tracker is not a help form and this issue will be closed.
We have a set of [listed resources available on the website](https://pytorch.org…
-
I switched to Keras backend, and I noticed that changing the learning_rate in the config files has no effect on the training process (tried 0.000001 to 0.9). I always get the exact same validation err…
-
### Expected behaviour
`pip install madmom` should work
### Actual behaviour
```python
sibonyves$ pip install madmom
Collecting madmom
Using cached https://files.pythonhosted.org/package…
-
I'm using Tensorflow 1.0 and I got an error message as below while running model.py.
> AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'bidirectional_rnn'
I looked up this pro…
-
@jpuigcerver Hi, thanks for sharing this well written code. Did you try to convert convert the pretrained model to pytorch model ? Actually, I am trying to do it but still having problems
-
Do you have any comment on using 2 encoder (listener) layers (as per your code 1 BLSTM + 1 pBLSTM) against 4 encoder layers ( 1 BLSTM + 3 pBLSTM as given in paper LAS)?
-
@kan-bayashi, @jnishi, and me discussed the following development plan, which mainly cleans and refactors codes. We'll mainly work on https://github.com/espnet/espnet/tree/dev branch, then marge the b…
-
Hi,
Does Speech_emotion_recognition_BLSTM work with other languages or only in German?