make sure any empty segments are removed (#7155)

Signed-off-by: Elena Rastorgueva <erastorgueva@nvidia.com> Signed-off-by: jubick1337 <mattyson.so@gmail.com>
NVIDIA · Aug 8, 2023 · 2937b1f · 2937b1f
1 parent a880d3a
commit 2937b1f
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/tools/nemo_forced_aligner/utils/data_prep.py b/tools/nemo_forced_aligner/utils/data_prep.py
@@ -249,6 +249,8 @@ def get_utt_obj(
 
     # remove any spaces at start and end of segments
     segments = [seg.strip() for seg in segments]
+    # remove any empty segments
+    segments = [seg for seg in segments if len(seg) > 0]
 
     utt = Utterance(text=text, audio_filepath=audio_filepath, utt_id=utt_id,)