Is it necessary to trim the audio tracks in the dataset to under 30 seconds?

[ducchung2444]

Thank you for the amazing open-source project. However, I am facing an issue when inference, so I have two questions.

1. Is it necessary to separate the vocals and the music from each other? (I have separated using demucsv4)
2. Is it necessary to trim the audio tracks in the dataset to under 30 seconds? (I have not trimmed the audio tracks)

Best regards