Closed kyoungmingo closed 1 year ago
Hi, The recipes can load the local dataset, but not download it (except Speech command). You have to do that manually, and unpack them in your data folder.
Applying the recipes - like you were doing - is the right way! All you need is the dataset first.
Thank you..
I looked at several python codes and it seems to be explained in detail very well.
Hello~
I want to test using transformer model with cw algorithm.
When I used "python fit_attacker.py attack_configs/LibriSpeech/universal/ctc_5000bpe_fit.yaml", I met this error
If possible, can you tell me how to use the CW algorithm attack method using the transformer model in this git,robust_speech?
Discussion in #9 for the last question
"We also provide data preparation and loading functions for the LibriSpeech, CommonVoice and SpeechCommands datasets, based on SpeechBrain recipes." in your git.
But, When I run the code according to the Recipe you shared, the following error appears.
How can I download data files??