* set the default encoding of stdout to utf-8

modelscope · Dec 30, 2024 · 6020a41 · 6020a41
1 parent 4805928
commit 6020a41
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/data_juicer/__init__.py b/data_juicer/__init__.py
@@ -10,6 +10,9 @@
 
 from data_juicer.utils.availability_utils import _is_package_available
 
+# set the default encoding to utf-8 explicitly
+sys.stdout.reconfigure(encoding='utf-8')
+
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 
 # For now, only INFO will be shown. Later the severity level will be changed