the use case of self.model attribute in the Chars2Vec class?

[buiminhhien2k]

I quite new to this field and I just read the source code, but I am quite confused a little bit with the actual role self.model the Chars2Vec class. Can I anyone explain for me how could I use the self.model or what is the role of it there? Because I don't see any method in Chars2Vec calling this param (except the fit method).

43        model_output = keras.layers.Dense(1, activation='sigmoid')(x)
44
45        self.model = keras.models.Model(inputs=[model_input_1, model_input_2], outputs=model_output)
46        self.model.compile(optimizer='adam', loss='mae')