Closed kachiem closed 4 years ago
What's the error? I think h5py is pretty standard
I'm wondering if I'm missing some structure for either the .h5 files or for .txt files. Currently my training lists are txt files containing a list of .wav file ids. My h5's are also a single group of wav files from train, test, and dev sets. I tried to preserve the hierarchical structure of the LibriSpeech corpus.
your key name is incorrect. You may need to modify the original script.
Hi, thanks for sharing your implementation of CPC. I've been trying to run it out of the box but am having issues shaping the input data correctly. Is there another script that encodes the wav file directories into .h5?