Rafael Greca

I know that it is a old issue, but just set the requires_grad parameter to True (the default value is True), like this: ```python ## create the embedding layer self.embedding...

Any updates? I did the following workaround in the **decode** function on the **run_cnnlstm** file to avoid this error: ```python targets = targets.drop(['predicted-targets'], axis=1) targets.fillna(value=0, inplace=True) targets = targets.apply(pd.Series.explode).reset_index(drop=True) targets['utterance-id']...

Same problem here with VWCE and XEON stocks.

Upvote. I had the same issue with version 1.0.9 using the deb file and I also use Ubuntu 22.04. However, the AppImage worked just fine for me.

I had to uninstall and install it manually (using the .deb file available here on GitHub). However, the problem is still occurring in version 1.0.23.