-
Last 50 lines of output:
```[...truncated 431.63 KB...]
[ 88%] Building CXX object externals/tflite-1.13.1/CMakeFiles/tensorflowlite-1.13.1.dir/externals/TENSORFLOW-1.13.1/tensorflow/lite/kernels/batc…
-
Hi
I try to use data_thchs30 dataset（about 33hours） to train chinese models ,train success ,but I cannot decoder out any word ,I don't konw what‘s the problem ,
the train.cfg:
--datadir=/home/…
-
#### Description
The GL implementation added in 0.7 #843 operates on linear spectrograms. At some point in the discussion, we raised the idea of having it work on CQT as well, but dropped the idea…
-
Hi, I use mtl_transformer_sp.json for Fine-tuning stage. It finished the epoch 0, but error occurs at some point of epoch 1.
BTW, when I run it without `"speed_permutation": [0.9, 1.0, 1.1]`, it work…
-
I am using the same Resnet architecture from the SOTA recipe.
This is what I am getting:
> I0606 00:52:02.980521 1392 Train.cpp:253] [Network Params: 283635715]
I0606 00:52:02.980557 1392 Trai…
-
Hi, I am trying to get the probability p(token|feats) for each frame in a CTC model, which should be
the Emission Set. But when I export the data, it's filled with float number which does not look …
-
I want to try specializing the streaming_convnets model. `continue model/` failed, and I don't blame it, but fork also fails with this:
```
terminate called after throwing an instance of 'af::except…
-
I am training for SOTA librispeech with Transformer CTC - it works fine.
For seq2seq, I am getting above error. Pls find below some details. Let me know if you need any more inputs.
Command:
no…
-
I am trying to train a dataset of around 250 hours with different architectures such as resnet, TDS and transformer mentioned in the recipe section. But my computer automatically restarts when I use t…
-
Hi
First thanks a lot for such an excellent tool for speech separation. I have tried the deep clustering part of wsj0-mix
[https://github.com/mpariente/asteroid/tree/master/egs/wsj0-mix/DeepClusteri…