-
Notifications
You must be signed in to change notification settings - Fork 2.1k
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.
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
[WIP] Branchformer Encoder in ESPnet2 #4400
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Codecov Report
@@ Coverage Diff @@
## master #4400 +/- ##
==========================================
+ Coverage 82.40% 82.47% +0.07%
==========================================
Files 481 484 +3
Lines 41238 41570 +332
==========================================
+ Hits 33982 34285 +303
- Misses 7256 7285 +29
Flags with carried forward coverage won't be shown. Click here to find out more.
📣 Codecov can now indicate which changes are the most critical in Pull Requests. Learn more |
@pengchengguo, can you review this PR, especially for espnet2/asr/encoder/branchformer_encoder.py? One discussion point is whether we will put various blocks in espnet2/asr/encoder/branchformer_encoder.py or under https://github.com/espnet/espnet/tree/master/espnet/nets/pytorch_backend |
No problem! I will do it this week. |
I prefer the current structure. Since most users are moving to the espnet2, we could make it more closed-loop. However, the |
Thank you for your comments. @sw005320 Should I move the definition of these modules into a separate directory? |
I think it is a good idea to move them to a separate directory.
Please consider two options and select more appropriate option. |
Hi @sw005320, I moved Now there is an error with |
Hi @sw005320, it seems the
|
I see. Thanks for the information. |
Hi @sw005320 I made a new PR to fix the |
Hi, can we re-run the CI tests for this PR? |
I think this PR is ready for review. |
LGTM! |
Hi, this PR adds the Branchformer encoder (Peng et al., ICML 2022) into ESPnet2 and releases some of the trained models. Also, we've achieved better Conformer baselines on some recipes, which will be updated as well.
The PR is in progress. I've cleaned and merged my previous code. Now I'm training models using the latest code (and config if exists).
The paper can be found here: https://proceedings.mlr.press/v162/peng22a.html or on arXiv: https://arxiv.org/abs/2207.02971
Please cite the following paper if you find our work helpful.
Updated recipes: