Open JunLi0514 opened 1 year ago
Thanks to syousen, for offline egs, get_chunk_egs()
in subtools/pytorch/pipeline/onestep/get_chunk_egs.py
will generate num_targets file.
I find after the train, val set split, the num_spkrs of the train set is reduced because some speakers will be removed since their utterances are all split to the val set.
While it has no influence on the utt2spk label utt2spk_int
, because it's not updated in filter()
of the KaldiDataset
in subtools/pytorch/libs/egs/kaldi_dataset.py
. Only attributes belong to 'utt_first_files' and 'spk_first_files' are changed in filter()
function.
So I recommend in subtools/pytorch/pipeline/onestep/get_chunk_egs.py
, use dataset.num_spks
instead of trainset.num_spks
to generate the */info/num_targets
file.
Hi, I try to run the CNCeleb recipe, but a RuntimeError appears:
That means the num_speakers output of FC classifier is less than the label. And I find the num_targets in
exp/egs/train_sequential/info
is 2687, while the max label in train.egs.csv is 2711. So could you please tell me which script generates theexp/egs/train_sequential/info/num_targets
?