You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I found the code in getitem function in LibriSpeechSegTupleWavDataset just remove the uttname in the neighbors, and it will remove it in the self.neighbor_prefixes as well, and finally the neighbors is zero. I dont know it's a bug or you design it on purpose.
Besides, I found the code unsupervised_data_cfg_librispeech.py process the speaker is strange, if the valid or test split have the same speaker, it's not included in both "data_cfg['speakers']" and "data_cfg['valid']['speakers']", but the valid set comes from the training scp, which means they will have the same speaker, and finally the "data_cfg['valid']['speakers']" is empty.
The text was updated successfully, but these errors were encountered:
I found the code in getitem function in LibriSpeechSegTupleWavDataset just remove the uttname in the neighbors, and it will remove it in the self.neighbor_prefixes as well, and finally the neighbors is zero. I dont know it's a bug or you design it on purpose.
Besides, I found the code unsupervised_data_cfg_librispeech.py process the speaker is strange, if the valid or test split have the same speaker, it's not included in both "data_cfg['speakers']" and "data_cfg['valid']['speakers']", but the valid set comes from the training scp, which means they will have the same speaker, and finally the "data_cfg['valid']['speakers']" is empty.
The text was updated successfully, but these errors were encountered: