Update preprocess_mdcc.py

egs/mdcc/ASR/local/preprocess_mdcc.py

@@ -26,6 +26,7 @@ files in the directory "data/lang_char":
 """
 
 import argparse
+import logging
 from pathlib import Path
 from typing import List
 
@@ -86,6 +87,7 @@ def get_word_segments(lines: List[str]) -> List[str]:
     new_lines = []
 
     for line in tqdm(lines, desc="Segmenting lines"):
+        try:
             # code switching
             if len(line.split(" ")) > 1:
                 segments = []
@@ -98,6 +100,8 @@ def get_word_segments(lines: List[str]) -> List[str]:
             # not code switching
             else:
                 new_lines.append(" ".join(pycantonese.segment(line)) + "\n")
+        except:
+            logging.error(f"Failed to process line: {line}")
     return new_lines