oleges1 / quartznet-pytorch Goto Github PK

Hi,

I was trying to do exactly what you did. Its great that I came through your work which looks great. But I keep on getting this error everywhere I run this project.

AssertionError Traceback (most recent call last)
in ()
----> 1 train(config)

2 frames
/usr/local/lib/python3.7/dist-packages/wandb/data_types.py in _init_from_list(self, data, columns, optional, dtype)
175
176 def _init_from_list(self, data, columns, optional=True, dtype=None):
--> 177 assert type(data) is list, "data argument expects a list object"
178 self.data = []
179 self._assert_valid_columns(columns)

AssertionError: data argument expects a list object

If you've got any idea or insight on how to improve this, that would be great.

Hello,

Does this implementation give same results as the original implementation?

Thanks.

Hi @oleges1 ,
I have an error message when I launch 'train.py' with the LJSpeechDataset as config:
'LJSpeechDataset' object has no attribute '_walker'. Would you have any idea of ​​the problem, please?
Thanks a lot.