Fix existing bugs in the TSE task#4915
Merged
sw005320 merged 3 commits intoespnet:masterfrom Feb 8, 2023
Merged
Conversation
Codecov Report
@@ Coverage Diff @@
## master #4915 +/- ##
==========================================
- Coverage 80.68% 76.56% -4.12%
==========================================
Files 543 603 +60
Lines 48233 53744 +5511
==========================================
+ Hits 38917 41151 +2234
- Misses 9316 12593 +3277
Flags with carried forward coverage won't be shown. Click here to find out more.
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR fixes existing bugs in the newly added TSE task. Some of them are critical that severely impede model training. Thanks to @YoshikiMas for the discussion!
Bug fixes:
egs2/TEMPLATE/enh1/enh.sh: enroll_spk?.scp files can be now correctly processed in Stage 3.egs2/librimix/tse1/run.sh: fixed a typoespnet2/bin/enh_tse_inference.py:shared_encodercan now take effect correctly in the inference stage.espnet2/train/preprocessor.py: Fixed a critical bug that prepares wrong TSE training data when providedspeech_refdata does not sum up tospeech_mixTypo fixing:
espnet2/enh/espnet_model_tse.pyTo be discussed:
espnet2/iterators/chunk_iter_factory.py: To support chunk-based iterator for the TSE task, I have to add some hacks to this file. If you think the hacks make the script too messy, I can revert the change and think about other workarounds.