Transcribing Long Audio Files
#2
by HBotond - opened
Hi!
What is the recommended approach for transcribing long audio files (around 30 minutes)? Can the model process the entire recording in a single request, or is it better to split the audio into smaller segments? If chunking is recommended, what segment length do you suggest?
Thanks in advance for your help!
Just make sure each segment is no longer than 30 seconds.