audio-deepfake-adversarial-attacks
audio-deepfake-adversarial-attacks copied to clipboard
how to arrange the directory of datasets
I want to train the model using asvspoof dataset . I already downloaded all of them including DF subsets. However whenever I tried to run .There is always error around the path(dir) configuration. Just want to know how to arrange them to make it work.
Hi, could you provide a detailed stacktrace? One of the possible errors you could get would be because at the time of the paper being written there were no exact labels for ASVSpoof2021 DF, so we based on this keys&metadata file.
Could you please try running code with these labels?
Could you please provide information on where exactly KeyError: 'attack type'
happens? It is used in couple of places and I cannot find its location in this stacktrace.
To only use ASVspoof you have to set proper paths (wavefake_path
and fakeavceleb_path
) as None - please refer to this function.