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
Support LoRA based large model finetuning. #5400
Conversation
for more information, see https://pre-commit.ci
Codecov Report
@@ Coverage Diff @@
## master #5400 +/- ##
==========================================
- Coverage 77.14% 70.33% -6.82%
==========================================
Files 684 707 +23
Lines 62713 64932 +2219
==========================================
- Hits 48383 45673 -2710
- Misses 14330 19259 +4929
Flags with carried forward coverage won't be shown. Click here to find out more.
... and 102 files with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
Thanks, @pengchengguo! |
Sure, the HF model link will also be updated later. |
@pyf98, can you review this PR? @pengchengguo, can you add a test? |
a1b1f7a
to
40ddcce
Compare
Thanks! It looks good to me! |
Just one question: |
Yes, it supports all. |
I am changing this PR to "work in progress" because I also want to add Whisper fine-tuning to ST. The ST part is being refactored now and will be finished soon. |
6a9bed5
to
0e6bc6a
Compare
This pull request is now in conflict :( |
af33626
to
07f7e77
Compare
for more information, see https://pre-commit.ci
Can you remove “WIP” from the PR title? |
Sure, now I am trying to increase the codecov, it seems the CI test file misses some functions. |
87a4568
to
d1847a8
Compare
We seem to have an issue for CI. Can you check it? |
I fixed the CI issues and ST errors as I mentioned before. Now, Whisper fine-tuned ST shows better results compared with E-Branchformer (60.9 vs 53 BLEU scores on Fishercallhome dev sets). |
Thanks, @pengchengguo! |
What?
Support LoRA-based large model finetuning and also provide results of LoRA-based Whisper finetuning on Aishell corpus.
By finetuning the Whisper large model, we are able to achieve superior results of 2.5/2.7 CERs on dev/test sets, respectively.
See also