Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Modified train.py of tedlium3 models #597

Merged
merged 7 commits into from
Oct 2, 2022
Merged

Modified train.py of tedlium3 models #597

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
519947a
Modified pruned_transducer_stateless/train.py
shcxlee Oct 1, 2022
3ebe6fc
Modified transducer_stateless/train.py
shcxlee Oct 2, 2022
2614235
Deleted variable 'num_in_total'
shcxlee Oct 2, 2022
966b7e4
Deleted variable 'num_in_total'
shcxlee Oct 2, 2022
70343b3
Merged latest master
shcxlee Oct 2, 2022
e7b2b2e
Merged latest master
shcxlee Oct 2, 2022
a41f19e
Merge remote-tracking branch 'shcxlee-icefall/master' into tedlium2_p…
shcxlee Oct 2, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 0 additions & 10 deletions egs/tedlium3/ASR/pruned_transducer_stateless/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -658,18 +658,8 @@ def remove_short_and_long_utt(c: Cut):
# Keep only utterances with duration between 1 second and 17 seconds
return 1.0 <= c.duration <= 17.0

num_in_total = len(train_cuts)

train_cuts = train_cuts.filter(remove_short_and_long_utt)

num_left = len(train_cuts)
num_removed = num_in_total - num_left
removed_percent = num_removed / num_in_total * 100

logging.info(f"Before removing short and long utterances: {num_in_total}")
logging.info(f"After removing short and long utterances: {num_left}")
logging.info(f"Removed {num_removed} utterances ({removed_percent:.5f}%)")

train_dl = tedlium.train_dataloaders(train_cuts)
valid_cuts = tedlium.dev_cuts()
valid_dl = tedlium.valid_dataloaders(valid_cuts)
Expand Down
10 changes: 0 additions & 10 deletions egs/tedlium3/ASR/transducer_stateless/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -627,18 +627,8 @@ def remove_short_and_long_utt(c: Cut):
# Keep only utterances with duration between 1 second and 17 seconds
return 1.0 <= c.duration <= 17.0

num_in_total = len(train_cuts)

train_cuts = train_cuts.filter(remove_short_and_long_utt)

num_left = len(train_cuts)
num_removed = num_in_total - num_left
removed_percent = num_removed / num_in_total * 100

logging.info(f"Before removing short and long utterances: {num_in_total}")
logging.info(f"After removing short and long utterances: {num_left}")
logging.info(f"Removed {num_removed} utterances ({removed_percent:.5f}%)")

train_dl = tedlium.train_dataloaders(train_cuts)
valid_cuts = tedlium.dev_cuts()
valid_dl = tedlium.valid_dataloaders(valid_cuts)
Expand Down