-
My full script is as below:
> conda create --name espnet
> conda activate espnet
> git clone https://github.com/espnet/espnet
> cd espnet
> pip install -e .
And there are many errors when ex…
-
OS: Ubuntu 16.04.3 LTS
CUDA version: 9.0
GPU: Tesla P100
I built and installed the tensorflow-bind and it seems no error. However, when I am trying the unit test by running
`python setup.py test…
-
I use pip-installed tensorflow-gpu. To complete the build, I changed the following (in addition to #5 ):
1)
../../external/nsync/public -> external/nsync/public
2) use `tf.sysconfig.get…
-
Hi,
I'm facing a segmentation fault as in [this issue](https://github.com/HawkAaron/warp-transducer/issues/6#issue-356494122) but in pytorch binding. In my case, all the built binary test can be p…
-
if . venv/bin/activate && python -c 'import torch as t;assert t.__version__[0] == "1"' &> /dev/null; then \
. venv/bin/activate && python -c "from distutils.version import LooseVersion as V;a…
-
What does it mean if the loss is negative. Do I have to wait more or is there anything wrong?
Attaching the required reference.
1/1561 [..............................] - ETA: 5:59:49 - loss: -…
-
I tried installing ESPNET on ubuntu 16.04 using command
`sudo make CUPY_VERSION='' -j 10`
I get the following error.
Any idea what the problem could be?
```
.
make[1]: Entering director…
-
Hi, @HawkAaron ,
According to your instruction, I finished the cmake command. But it seems that the step of Performing Test CMAKE_HAVE_LIBC_PTHREAD not work successfully. Here is the result of my…
-
Training with this command
```bash
python run_common_voice.py --mode train --data_dir data_p --batch_size 4 --steps_per_checkpoint 100 --eval_size 100
```
Started giving me NaN for loss in epo…
-
Hi @HawkAaron ,
according to Eq. (12) from your [note](https://github.com/HawkAaron/warp-transducer/blob/master/docs/rnnt_notes.pdf), the gradient to last blank transition is:
![image](https://user-…