Update preprocess_mdcc.py

2025-08-27 02:34:21 +00:00 · 2024-03-08 19:25:13 +08:00 · 2024-03-08 19:25:13 +08:00 · 7d22fef6f2
commit 7d22fef6f2
parent 336944c9b3
1 changed files with 2 additions and 0 deletions
--- a/egs/mdcc/ASR/local/preprocess_mdcc.py
+++ b/egs/mdcc/ASR/local/preprocess_mdcc.py
@ -92,6 +92,8 @@ def get_word_segments(lines: List[str]) -> List[str]:
            if len(line.strip().split(" ")) > 1:
                segments = []
                for segment in line.strip().split(" "):
+                    if segment.strip() == "":
+                        continue
                    try:
                        if not is_cjk(segment[0]):  # en segment
                            segments.append(segment)