Is your feature request related to a problem? Please describe.

I think the author has avoided the most important part in the long-context part - audio transcription. Due to the output size limitation, it may not be possible to get the transcription results in one go. So in the case of long-context, how can we get accurate transcription results without missing content?

Describe the solution you'd like

I would like to know the best practices for getting transcription results without loss of content for long audio due to output size constraints.

Describe alternatives you've considered

No response

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct