When using wav2vec2 inference, does the quantitation being used?

According to wav2vec model:

enter image description here

it seems that quantitation enter image description here only used on training phase (in order to train the transformer layer to quantitative the data to use small number of discrete values).

So my question is:
when using inference, does this quantitation unit (circle purple in the figure above) being used ? (I guess no, am I right ?)