Extracting model weight matrices and doing the inference just by matrix multiplication

Is it possible to extract weights of a trained model, and after that, do the inference just by matrix multiplication in any language or system, without the need for torchscript or exporting model to other formats?

(My problem is that I have a model trained in python (Tacotron 2 for TTS), now I want to use this model in C++ and also in mobile devices, for this it is required to first use torchscript to compile the model, but it seems that this model is not scriptable! I’ve already posted about this here)