-
#### Issue Description
I trained a 4 layer BLSTM model in Keras and tried to import this model using:
ComputationGraph net = KerasModelImport.importKerasModelAndWeights
but when I tried to f…
-
https://github.com/arity-r/ChimeraNet/blob/6341383c61f238a83a0be8c7d4972aac4e7d958a/chimeranet/model.py#L57-L69
Correct me if I am wrong. One can simply change this block of code with `Dense`, and …
-
Hello everyone!
To transcribe a wav file I use _recog_wav.sh_.
Everything works fine, but afaik, model loading takes quite some time. So my idea is to make an API, which will load the models at …
vcjob updated
5 years ago
-
**Describe the bug**
When trying to run an evaluation run with the iemocap example after training a model it fails with:
```
Traceback (most recent call last):
File "../../delta/delta/main.py", …
-
## 🐛 Bug
Hello,
I am trying to test out the **torchfilters** branch of this project. It works fine on shorter audio clips, but when the audio file is around 4 to 5 minutes in length, the pro…
-
Hello all,
I trained a simple nnet3 model using train_dnn.py that gave perfect results while I decoded audio files through steps/online/nnet3/decode.sh after preparing online directory (using steps/o…
-
Hi,
It's quite unclear what you do with the pressure and timestamp features (see Indermühle et al.).
In `writing.py` it seems that you extract features like pressure from the data but when using the…
-
I've converted the ckpt file the author gave into pb format by referring to [this solution](https://stackoverflow.com/a/45868106).
The value I set for param 'output_node_names' was 'rpn_cls_prob'.
T…
-
请问下，我这边数字识别精度挺好的，中文识别率为何这么低，而且我的字典里就19个特定的中文字，图片像素也调过，训练数据也产生了1000多w的，是否需要调节模型一些参数？还是crnn里尝试blstm？
-