I have trained a Sentence piece model using generate_sp_model()``. I used the pre-trained model for
sentencepiece_numericalizer``` to change my text to numeric values before converting to tensors. I then went ahead to train my transformer model. Now I have outputs how do I get the text back from my transformer output (i.e Decode from ids to text). For example
>>> from torchtext.data.functional import sentencepiece_numericalizer
>>> sp_id_generator = sentencepiece_numericalizer(sp_model)
>>> list_a = ["sentencepiece encode as pieces", "examples to try!"]
>>> list(sp_id_generator(list_a))
[[9858, 9249, 1629, 1305, 1809, 53, 842],
[2347, 13, 9, 150, 37]]
How do get I "sentencepiece encode as pieces", "examples to try!"
back from the ids