audio_resampler.resample(frame) returns a list of one audio frame that doesn't provide to_ndarray() method. Changing the line to np_snd = audio_resampler.resample(frame)[0].to_ndarray() solves the issue on me laptop. I am unsure if someone faces the same issue, but I report here for reference.
Dear all:
thanks for publilshing such a insightful work. I am looking forward to download the dataset and reproduce your work. Please release the dataset as soon as possible.
When I use the official code to download the total 1918 files, request.get() often gets stuck, probably due to too frequent requests from the same ip address.
Could you package the whole dataset to a few zip files, so that we can download them manually?