mirrors/icefall
Archived
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

setting max duration

Browse Source
This commit is contained in:
Yuekai Zhang 2022-07-07 14:49:51 +08:00
parent 6d2641f2b9
commit 22af36a88e
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
egs/aishell2/ASR/pruned_transducer_stateless5/train.py
View File

@ -957,15 +957,15 @@ def run(rank, world_size, args):
train_cuts = aishell2.train_cuts() train_cuts = aishell2.train_cuts()
def remove_short_and_long_utt(c: Cut): def remove_short_and_long_utt(c: Cut):
# Keep only utterances with duration between 1 second and 20 seconds # Keep only utterances with duration between 1 second and 8 seconds
# #
# Caution: There is a reason to select 20.0 here. Please see # Caution: There is a reason to select 8.0 here. Please see
# ../local/display_manifest_statistics.py # ../local/display_manifest_statistics.py
# #
# You should use ../local/display_manifest_statistics.py to get # You should use ../local/display_manifest_statistics.py to get
# an utterance duration distribution for your dataset to select # an utterance duration distribution for your dataset to select
# the threshold # the threshold
return 1.0 <= c.duration <= 20.0 return 1.0 <= c.duration <= 8.0
train_cuts = train_cuts.filter(remove_short_and_long_utt) train_cuts = train_cuts.filter(remove_short_and_long_utt)