diff --git a/funasr/utils/wav_utils.py b/funasr/utils/wav_utils.py
index 590ccdbc8..d7afe4acc 100644
--- a/funasr/utils/wav_utils.py
+++ b/funasr/utils/wav_utils.py
@@ -305,11 +305,11 @@ def filter_wav_text(data_dir, dataset):
         wav_dict[sample_name] = wav_path
     text_dict = {}
     for line in text_lines:
-        parts = line.strip().split(" ", 1)
+        parts = line.strip().split()
         if len(parts) < 2:
             continue
-        sample_name, txt = parts
-        text_dict[sample_name] = txt
+        sample_name = parts[0]
+        text_dict[sample_name] = " ".join(parts[1:])
     filter_count = 0
     with open(wav_file, "w") as f_wav, open(text_file, "w") as f_text:
         for sample_name, wav_path in wav_dict.items():
@@ -318,4 +318,4 @@ def filter_wav_text(data_dir, dataset):
                 f_text.write(sample_name + " " + text_dict[sample_name] + "\n")
             else:
                 filter_count += 1
-    print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))
\ No newline at end of file
+    print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))