update training data maximum duration

.flake8

@@ -6,6 +6,8 @@ per-file-ignores =
     # line too long
     egs/librispeech/ASR/*/conformer.py: E501,
     egs/aishell/ASR/*/conformer.py: E501,
+    egs/tedlium3/ASR/*/conformer.py: E501,
+    egs/tedlium3/ASR/local/display_manifest_statistics.py: E501,
 
 exclude =
   .git,

egs/tedlium3/ASR/local/compute_fbank_tedlium.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
-# Copyright    2021  Xiaomi Corp.        (authors: Fangjun Kuang)
+# Copyright    2021  Xiaomi Corp.        (authors: Fangjun Kuang
+#                                                  Mingshuang Luo)
 #
 # See ../../../../LICENSE for clarification regarding multiple authors
 #
@@ -31,9 +32,10 @@ import torch
 from lhotse import CutSet, Fbank, FbankConfig, LilcomHdf5Writer
 from lhotse.recipes.utils import read_manifests_if_cached
 
+from icefall.utils import get_executor
+
 # from utils import read_manifests_if_cached
 
-from icefall.utils import get_executor
 
 # Torch's multithreaded behavior needs to be disabled or
 # it wastes a lot of CPU and slow things down.
@@ -71,7 +73,7 @@ def compute_fbank_tedlium():
             cut_set = CutSet.from_manifests(
                 recordings=m["recordings"],
                 supervisions=m["supervisions"],
-            )
+            ).trim_to_supervisions(keep_overlapping=False)
             if "train" in partition:
                 cut_set = (
                     cut_set

egs/tedlium3/ASR/local/display_manifest_statistics.py

@@ -31,8 +31,9 @@ from lhotse import load_manifest
 
 def describe(cuts) -> None:
     """
-    Print a message describing details about the ``CutSet`` - the number of cuts and the
-    duration statistics, including the total duration and the percentage of speech segments.
+    Print a message describing details about the ``CutSet`` - the number
+    of cuts and the duration statistics, including the total duration
+    and the percentage of speech segments.
 
     Example output:
         Cuts count: 804789
@@ -49,8 +50,6 @@ def describe(cuts) -> None:
             99.5%   14.9
             99.9%   16.6
             max     33.3
-
-    In the above example, we set 15(>14.9) as the maximum duration of training samples.
     """
     durations = np.array([c.duration for c in cuts])
     speech_durations = np.array(