Hi! I can see that BackTranslationAug has an argument max_length to specify the maximum length of the output text, but I am wondering if there is any way to specify the max length of the input text, similar to how HF Tokenizers lets you truncate text with a tokenizer.
Hi! I can see that
BackTranslationAug
has an argumentmax_length
to specify the maximum length of the output text, but I am wondering if there is any way to specify the max length of the input text, similar to how HF Tokenizers lets you truncate text with a tokenizer.