Skip to content

Conversation

@Likhithsai2580
Copy link

Fixes #76

Add a check in the vocode method to handle cases where the kernel size is greater than the input size.

  • Add a check in the vocode method to ensure the kernel size is not greater than the input size.
  • Log an appropriate error message if the kernel size is greater than the input size.
  • Return an empty tensor if the kernel size is greater than the input size.
  • Add an alternative method to handle the case when the kernel size is greater than the input size by using a different bandwidth_id.

Fixes Camb-ai#76

Add a check in the `vocode` method to handle cases where the kernel size is greater than the input size.

* Add a check in the `vocode` method to ensure the kernel size is not greater than the input size.
* Log an appropriate error message if the kernel size is greater than the input size.
* Return an empty tensor if the kernel size is greater than the input size.
* Add an alternative method to handle the case when the kernel size is greater than the input size by using a different bandwidth_id.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] RuntimeError: Calculated padded input size per channel: (6). Kernel size: (7). Kernel size can't be greater than actual input size

1 participant