Padding text input while generating captions

[dsikka]

Hello,

I am trying to run the caption generation workflow and was wondering what I have to do if the inputs to the TextTransformer model are always padded to a fixed length? How should the attn mask be updated in both the TextTransformer and the MultiModalDecoder? Currently, the input to the TextTransformer increases as the caption is generated but I'd like to pad the input to a fixed length.

Thanks.

@lucidrains @gpucce @iejMac