``
</pt>
<tf>
Tokenize the text and return theinput_ids` as TensorFlow tensors:

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("my_awesome_opus_books_model")
inputs = tokenizer(text, return_tensors="tf").input_ids

Use the [~transformers.generation_tf_utils.TFGenerationMixin.generate] method to create the translation.