Tom Dörr

Since there seems to be a permission issue, you could try to use rootless docker: https://docs.docker.com/engine/security/rootless/ As the name says, it doesn't require root permissions and therefore you might not...

Glad you got it to work. :) I was able to train it, but it was a long time ago. I don't remember which configuration I used or what losses...

Don't know about that. You might want to also post it in the main TecoGAN repo where more people will see this.

I don't know what causes the issue, but it seems to be related to your DeepSpeech setup. DeepSpeech gets set up automatically if you use the code on my fork:...

There's another issue for this (https://github.com/carlini/audio_adversarial_examples/issues/33). The script your executing tries to download the ds-ctcdecoder, which is not available any more on the server. Rogthlu from issue https://github.com/carlini/audio_adversarial_examples/issues/33 seems to...

Just pushed them. For the GPU version run: ``` docker run --gpus all -it --mount src=$(pwd),target=/audio_adversarial_examples,type=bind -w /audio_adversarial_examples tomdoerr/aae_deepspeech_041_gpu ``` For the CPU-only version: ``` docker run -it --mount src=$(pwd),target=/audio_adversarial_examples,type=bind...

You could just extract the `.whl` file from one of the docker images in case you don't want to use them.

@JeetShah10 I just uploaded the ctcdecoder `.whl` file: https://github.com/tom-doerr/audio_adversarial_examples/blob/master/ds_ctcdecoder-0.4.1-cp35-cp35m-linux_x86_64.whl

@kkfkk Sorry, didn't see your comment. In case you still want to get it running: There were some issues with the docker images due to a numpy update. I fixed...

You might need to upgrade the CUDA version that is used inside the docker container in order for it to work on the RTX 3090.