Adressing first pass of comments.

2025-08-23 16:49:27 +00:00 · 2020-09-23 11:29:17 +02:00
parent 1cd4824273
commit 8f8156fd2c
10 changed files with 196 additions and 125 deletions
--- a/bindings/python/examples/train_bert_wordpiece.py
+++ b/bindings/python/examples/train_bert_wordpiece.py
@ -32,7 +32,10 @@ if not files:

 # Initialize an empty tokenizer
 tokenizer = BertWordPieceTokenizer(
-    clean_text=True, handle_chinese_chars=True, strip_accents=True, lowercase=True,
+    clean_text=True,
+    handle_chinese_chars=True,
+    strip_accents=True,
+    lowercase=True,
 )

 # And then train