How to implement summarize Modelrunning on local PC?

hi!

We want to implement a summarize Model which runs on the local PC (powerful nvidia with cuda). We typcially want to summarize
1: Meetings transcriptions (text) with several people, which can contain conversations of 1-2 hours
2: Trainer and Trainee session, which can contain conversation text of 1 to 1.5 hours

Do you have any recommendations what I should look out for?

thanks!

1 Like