Skip to content

Fixed TransformerST bug with ASR masks #2984

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

Open
ffenix7 wants to merge 7 commits into
base: develop
Choose a base branch
from
Open

Fixed TransformerST bug with ASR masks #2984

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b4d2e28
Fixed TransformerST bug with masks
ffenix7 Oct 19, 2025
8f70551
Merge branch 'develop' into develop
TParcollet Nov 2, 2025
db1036c
import masks from TransformerASR
ffenix7 Nov 4, 2025
d3b1627
Merge branch 'develop' of https://github.com/ffenix7/speechbrain into…
ffenix7 Nov 4, 2025
b39574b
Merge branch 'develop' into develop
ffenix7 Nov 5, 2025
b42a49b
Merge branch 'develop' into develop
ffenix7 Dec 9, 2025
4f5563f
Merge branch 'develop' into develop
ffenix7 Dec 20, 2025
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
6 changes: 3 additions & 3 deletions speechbrain/lobes/models/transformer/TransformerST.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
get_key_padding_mask,
get_lookahead_mask,
)
from speechbrain.lobes.models.transformer.TransformerASR import TransformerASR
from speechbrain.lobes.models.transformer.TransformerASR import TransformerASR, make_transformer_src_tgt_masks
from speechbrain.nnet.activations import Swish
from speechbrain.nnet.containers import ModuleList
from speechbrain.utils.logger import get_logger
Expand Down Expand Up @@ -243,7 +243,7 @@ def forward_asr(self, encoder_out, src, tgt, wav_len, pad_idx=0):
tgt_key_padding_mask,
src_mask,
tgt_mask,
) = self.make_masks(src, tgt, wav_len, pad_idx=pad_idx)
) = make_transformer_src_tgt_masks(src, tgt, wav_len, pad_idx=pad_idx)

transcription = self.custom_asr_tgt_module(tgt)

Expand Down Expand Up @@ -434,4 +434,4 @@ def make_masks_for_mt(self, src, tgt, pad_idx=0):
src_mask = None
tgt_mask = get_lookahead_mask(tgt)

return src_key_padding_mask, tgt_key_padding_mask, src_mask, tgt_mask
return src_key_padding_mask, tgt_key_padding_mask, src_mask, tgt_mask