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
Thank you for pointing this out! Based on the current implementation:
classTranslationVerbose(BaseModel):
duration: str"""The duration of the input audio."""
It seems the duration field is indeed expected as a string. This might be an oversight in either the documentation or the code itself—I'm not entirely sure yet.
To address this, I’ve created #2034, which updates the TranslationVerbose model to support both string and integer types for the duration field. This change ensures flexibility and aligns better with expected usage.
Please take a look at the PR and let me know your thoughts or any feedback you might have. Thanks!
Confirm this is an issue with the Python library and not an underlying OpenAI API
Describe the bug
As per title
To Reproduce
Code snippets
No response
OS
macOS
Python version
Python 3.11
Library version
1.52.1
The text was updated successfully, but these errors were encountered: