I am building a speech recognition application to be run on Raspberry Pi 3. I have developed a Tensorflow model for this purpose that I am able to run on Raspberry Pi through command line.
How do I make a call to this model from my application (both on Raspberry Pi)? Should I install and run Tensoflow Serving on Raspberry Pi to serve the model (I tried this and got an Exec format error on running tensorflow_model_server)?
I want both the model and my speech recognition application to run locally on Raspberry Pi to avoid any network delay.