Fix an encoding error

scripts/common.py

@@ -696,7 +696,7 @@ def _read_page_languages_hocr(f):
     if not content.strip():  # the file is empty
         return dict()
     html5_parser = etree.HTMLParser(huge_tree=True)
-    xml_document = etree.fromstring(content, html5_parser)
+    xml_document = etree.fromstring(content.encode('utf-8'), html5_parser)
 
     languages = defaultdict(lambda: 0.0)