-
Notifications
You must be signed in to change notification settings - Fork 2.2k
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
Update libri_trans asr recipe #1344
Conversation
hirofumi0810
commented
Nov 9, 2019
- Change RNN to Transformer
- Change character unit to BPE1k unit
Codecov Report
@@ Coverage Diff @@
## v.0.6.0 #1344 +/- ##
===========================================
+ Coverage 77.45% 77.69% +0.23%
===========================================
Files 110 110
Lines 10541 10776 +235
===========================================
+ Hits 8165 8372 +207
- Misses 2376 2404 +28
Continue to review full report at Codecov.
|
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, thanks!
- please consider uploading the model.
- what is the major difference between bpe and char transformer yaml files? Batchsize (due to the shorter output length with bpe?)? Can you add the comment to the yaml file?
@sw005320 I will update results with SpecAugment tomorrow. |
@sw005320 Ready to be merged. |
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.
Very cool!
The result is impressive.
egs/libri_trans/asr1/conf/tuning/train_pytorch_transformer_bpe_long.yaml
Show resolved
Hide resolved
LGTM |