This project is a practice to use different LLM models. The summarisation is simply done through getting the transcription of the video and directed to the model with prompt to summarise the video focusing and highlighting of important aspects explained in the video.
A user interface was added to simplify the process and to practice python GUI library PyQT.
Three models were used Llama3.2, Bart and TF_IDF. Best summarisation was done using llama3.2 but it took more time to view response.