Add sentencepiece to BERT model

[zhangguanheng66]

In the XLM-R model, SentencePiece is used to tokenize the strings. We enable the sentencepiece processing pipeline here for the BERT workflow.

[codecov[bot]]

Codecov Report

Merging #1124 (7d50cd8) into master (9053d95) will not change coverage. The diff coverage is n/a.

@@           Coverage Diff           @@
##           master    #1124   +/-   ##
=======================================
  Coverage   79.46%   79.46%           
=======================================
  Files          47       47           
  Lines        3175     3175           
=======================================
  Hits         2523     2523           
  Misses        652      652           

---

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 9053d95...7d50cd8. Read the comment docs.