How could I do about creating my own subword representation file?

How could I create a subword representations file like ende_32k.subword used in the following example

# Tokenize a sentence.
sentence = 'It is nice to learn new things today!'
tokenized = list(trax.data.tokenize(iter([sentence]),  # Operates on streams.
                                    vocab_dir='gs://trax-ml/vocabs/',
                                    vocab_file='ende_32k.subword'))[0]

I want to create my own subword vocab like the one used in deeplearning.ai . how could I do about creating my own subword representation file?
regards

Hi AliMij001,

An example of how this works can be found here.