mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-27 02:34:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove utterance more than 30s in test_net

Browse Source
This commit is contained in:
Yuekai Zhang 2024-01-29 10:08:10 +08:00
parent d8a329eca5
commit 4826f0801c
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
egs/wenetspeech/ASR/whisper/decode.py
View File

@ -481,7 +481,18 @@ def main():
dev_cuts = wenetspeech.valid_cuts() dev_cuts = wenetspeech.valid_cuts()
dev_dl = wenetspeech.valid_dataloaders(dev_cuts) dev_dl = wenetspeech.valid_dataloaders(dev_cuts)
def remove_long_utt(c: Cut):
# Keep only utterances with duration in 30 seconds
#
if c.duration > 30.0:
# logging.warning(
# f"Exclude cut with ID {c.id} from training. Duration: {c.duration}"
# )
return False
return True
test_net_cuts = wenetspeech.test_net_cuts() test_net_cuts = wenetspeech.test_net_cuts()
test_net_cuts = test_net_cuts.filter(remove_long_utt)
test_net_dl = wenetspeech.test_dataloaders(test_net_cuts) test_net_dl = wenetspeech.test_dataloaders(test_net_cuts)
test_meeting_cuts = wenetspeech.test_meeting_cuts() test_meeting_cuts = wenetspeech.test_meeting_cuts()