Skip to content

fix(asr): mask padded frames after feature normalization #15562

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

Merged
naymaraq merged 2 commits into from
Apr 14, 2026
Merged

fix(asr): mask padded frames after feature normalization #15562

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
82daf0d
TDT fix
arushidNV Mar 22, 2026
ed478e2
Merge branch 'main' into arushid/fix-partial-chunk-normalization
naymaraq Apr 9, 2026
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
4 changes: 3 additions & 1 deletion nemo/collections/asr/parts/preprocessing/features.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,9 @@ def normalize_batch(x, seq_len, normalize_type):
x_std = x_std.masked_fill(x_std.isnan(), 0.0) # edge case: only 1 frame in denominator
# make sure x_std is not zero
x_std += CONSTANT
return (x - x_mean.unsqueeze(2)) / x_std.unsqueeze(2), x_mean, x_std
normalized = (x - x_mean.unsqueeze(2)) / x_std.unsqueeze(2)
normalized.masked_fill_(~valid_mask.unsqueeze(1), 0.0)
return normalized, x_mean, x_std
elif normalize_type == "all_features":
x_mean = torch.zeros(seq_len.shape, dtype=x.dtype, device=x.device)
x_std = torch.zeros(seq_len.shape, dtype=x.dtype, device=x.device)
Expand Down
Loading