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

Add implementations of USES2 speech enhancement models #5761

Open
wants to merge 11 commits into
base: master
Choose a base branch
from
Open

Add implementations of USES2 speech enhancement models #5761

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
9699f00
Add implementations of USES2 speech enhancement models (Swin and Comp)
Emrys365 Apr 24, 2024
6f2d4df
Merge branch 'tse_recipe' of https://github.com/Emrys365/espnet into …
Emrys365 Apr 24, 2024
fd95a85
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Apr 24, 2024
030a479
Merge branch 'master' of https://github.com/espnet/espnet into tse_re…
Emrys365 Jun 9, 2024
9d480c8
Add a recipe: egs2/urgent24/enh1
Emrys365 Jun 9, 2024
014a671
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 9, 2024
720e948
Revert
Emrys365 Jun 9, 2024
105045c
Revert
Emrys365 Jun 9, 2024
126a1b5
Add CI tests; Remove the dependency on timm
Emrys365 Jun 17, 2024
7d6abf1
Merge branch 'master' of https://github.com/espnet/espnet into tse_re…
Emrys365 Jun 17, 2024
bfd3000
Merge branch 'master' of https://github.com/espnet/espnet into tse_re…
Emrys365 Jul 14, 2024
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
Prev Previous commit
Next Next commit
[pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
  • Loading branch information
@pre-commit-ci
pre-commit-ci[bot] committed Jun 9, 2024
commit 014a671d8e75b745b47311a202af483649f2046f
6 changes: 3 additions & 3 deletions egs2/urgent24/enh1/conf/tuning/train_enh_bsrnn_large_noncausal.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,9 @@ separator_conf:
# The overlall loss in the multi-task learning will be:
# loss = weight_1 * loss_1 + ... + weight_N * loss_N
# The default `weight` for each sub-loss is 1.0
criterions:
criterions:
# The first criterion
- name: mr_l1_tfd
- name: mr_l1_tfd
conf:
window_sz: [256, 512, 768, 1024]
hop_sz: null
Expand All @@ -95,7 +95,7 @@ criterions:
wrapper_conf:
weight: 1.0
# The second criterion
- name: si_snr
- name: si_snr
conf:
eps: 1.0e-7
wrapper: fixed_order
Expand Down
6 changes: 3 additions & 3 deletions egs2/urgent24/enh1/conf/tuning/train_enh_conv_tasnet.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,9 +83,9 @@ separator_conf:
# The overlall loss in the multi-task learning will be:
# loss = weight_1 * loss_1 + ... + weight_N * loss_N
# The default `weight` for each sub-loss is 1.0
criterions:
criterions:
# The first criterion
- name: mr_l1_tfd
- name: mr_l1_tfd
conf:
window_sz: [256, 512, 768, 1024]
hop_sz: null
Expand All @@ -96,7 +96,7 @@ criterions:
wrapper_conf:
weight: 1.0
# The second criterion
- name: si_snr
- name: si_snr
conf:
eps: 1.0e-7
wrapper: fixed_order
Expand Down
6 changes: 3 additions & 3 deletions egs2/urgent24/enh1/conf/tuning/train_enh_tfgridnet.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,9 +87,9 @@ separator_conf:
# The overlall loss in the multi-task learning will be:
# loss = weight_1 * loss_1 + ... + weight_N * loss_N
# The default `weight` for each sub-loss is 1.0
criterions:
criterions:
# The first criterion
- name: mr_l1_tfd
- name: mr_l1_tfd
conf:
window_sz: [256, 512, 768, 1024]
hop_sz: null
Expand All @@ -100,7 +100,7 @@ criterions:
wrapper_conf:
weight: 1.0
# The second criterion
- name: si_snr
- name: si_snr
conf:
eps: 1.0e-7
wrapper: fixed_order
Expand Down
Loading