Minor update

espnet · Oct 1, 2023 · 1bba669 · 1bba669
1 parent 773831d
commit 1bba669
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/espnet2/fileio/multi_sound_scp.py b/espnet2/fileio/multi_sound_scp.py
@@ -17,9 +17,9 @@ class MultiSoundScpReader(collections.abc.Mapping):
         wav.scp is a text file that looks like the following:
 
         key1 /some/path/a1.wav /another/path/a2.wav /yet/another/path/a3.wav
-        key2 /some/path/b1.wav /another/path/b2.wav /yet/another/path/b3.wav
+        key2 /some/path/b1.wav /another/path/b2.wav
         key3 /some/path/c1.wav /another/path/c2.wav /yet/another/path/c3.wav
-        key4 /some/path/d1.wav /another/path/d2.wav /yet/another/path/d3.wav
+        key4 /some/path/d1.wav
         ...
 
         >>> reader = SoundScpReader('wav.scp', stack_axis=0)

diff --git a/espnet2/train/preprocessor.py b/espnet2/train/preprocessor.py
@@ -1106,7 +1106,13 @@ def _random_crop_range(self, data_dict, num_spk, uid=None, max_trials=10):
         ]
         length = speech_refs[0].shape[0]
         tgt_length = self.speech_segment
-        assert length >= self.speech_segment, (length, tgt_length)
+        if length <= tgt_length:
+            if length < tgt_length:
+                logging.warning(
+                    f"The sample ({uid}) is not cropped due to its short length "
+                    f"({length} < {tgt_length})."
+                )
+            return 0, length
 
         start = np.random.randint(0, length - tgt_length)
         count = 1