Speech enhancement baseline on the BinauralLibriSpeech data set #5963
Conversation
for more information, see https://pre-commit.ci
egs2/binaural_librispeech/enh1/conf/tuning/train_enh_beamformer_mvdr.yaml
Outdated
Show resolved
Hide resolved
|
After reflecting the above comments, it is better to run the following command for style check of the shell scripts under shellcheck -Calways -x -e SC2001 -e SC1091 -e SC2086 egs2/binaural_librispeech/enh1/local/*.shIn addition, can you also add the information about the current corpus in egs2/README.md? |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
All comments should be addressed.
|
|
Cool! |
|
To check the Python style issues, you can run the following command under directory: pycodestyle --exclude "egs2/TEMPLATE/asr1/utils,egs2/TEMPLATE/asr1/steps,egs2/TEMPLATE/tts1/sid,doc,tools,test_utils/bats-core,test_utils/bats-support,test_utils/bats-assert" --show-source --show-pep8 |
for more information, see https://pre-commit.ci
|
It seems like the rest of the unsuccessful checks are unrelated to this PR? |
|
You're right. |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #5963 +/- ##
===========================================
- Coverage 56.06% 38.20% -17.87%
===========================================
Files 830 566 -264
Lines 78031 51080 -26951
===========================================
- Hits 43749 19515 -24234
+ Misses 34282 31565 -2717
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
|
Can you add a result to README.md with a model link? |
Can you revisit it? |
What?
Added a baseline experiment for speech enhancement on the BinauralLibriSpeech data set.
Why?
Adds an example experiment for using BinauralLibriSpeech data.