Op type not registered 'SentencepieceEncodeSparse'

[Gorodecki]

import tensorflow as tf
import tensorflow_text
from tensorflow_text import SentencepieceTokenizer

saved_model_path = '../M-USE-CNN-FiT-RuSentiment'
model = tf.saved_model.load(saved_model_path)

NotFoundError: Op type not registered 'SentencepieceEncodeSparse' in binary running on alboyarskiy. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) tf.contrib.resampler should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.

How can I run this model on my data and do additional training on my dataset?