Stellar clusters often host massive stars that heat up and ionize the gas surrounding low-mass stars. The large amounts of far-ultraviolet radiation produced by these stars can deplete the gas from the outer layers of the disk around a low-mass star, an effect known as external photoevaporation. We have chosen to study this effect in Trumpler 14 (Tr14), a young stellar cluster in the Carina Nebula Complex. Specifically, we focus on the center of Tr14 and introduce a new, more robust methodology to extract stellar spectra from previously obtained VLT/MUSE spectroscopic data. To classify the young, low-mass stars, we employ a deep learning approach in the form of a conditional invertible neural network (cINN). We describe the results of testing the network on our new set of data as well as the need to extend the current method to include hotter stars.