Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Recipe/ogi kids speech#5916

Merged
sw005320 merged 19 commits intoespnet:masterfrom
anyuyay:recipe/ogi_kids_speech
Oct 4, 2024
Merged

Recipe/ogi kids speech#5916
sw005320 merged 19 commits intoespnet:masterfrom
anyuyay:recipe/ogi_kids_speech

Conversation

@anyuyay
Copy link
Contributor

@anyuyay anyuyay commented Oct 3, 2024

What?

Commit the recipe ogi_kids_speech for ASR of OGI kids' speech corpus.

Also modify CONTRIBUTING.md to make it clearer.

@codecov
Copy link

codecov bot commented Oct 3, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 27.83%. Comparing base (088ef88) to head (4fa971b).
Report is 2 commits behind head on master.

❗ There is a different number of reports uploaded between BASE (088ef88) and HEAD (4fa971b). Click for more details.

HEAD has 8 uploads less than BASE
Flag BASE (088ef88) HEAD (4fa971b)
test_python_espnet2 4 0
test_utils 4 0
Additional details and impacted files
@@             Coverage Diff             @@
##           master    #5916       +/-   ##
===========================================
- Coverage   52.78%   27.83%   -24.95%     
===========================================
  Files         819      552      -267     
  Lines       75575    47732    -27843     
===========================================
- Hits        39895    13288    -26607     
+ Misses      35680    34444     -1236     
Flag Coverage Δ
test_integration_espnetez 27.83% <ø> (?)
test_python_espnet2 ?
test_utils ?

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link
Contributor

@sw005320 sw005320 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  • Please put the model link once you upload it to HF
  • The performance is too good. I'm concerned that the test set contamination may happen. Can you check this with @jctian98?

@@ -0,0 +1,27 @@
# RESULTS
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a comment that this is the short-sentence version?
Please explain the details of which portion in the directory you used, how many recordings, hours, etc.
You can also add TODO to deal with the long recording.

@@ -0,0 +1,33 @@
#!/usr/bin/env bash
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Again, please mention that this recipe is the short sentence version

@anyuyay
Copy link
Contributor Author

anyuyay commented Oct 3, 2024

  • Please put the model link once you upload it to HF
  • The performance is too good. I'm concerned that the test set contamination may happen. Can you check this with @jctian98?

Model uploaded.
Performance is not strange according to the paper for the corpus.
Descriptions for readme.md, run.sh added.

However, the new pull request fails in github code checking (the previous pull request passed the check). I check the test case, it raises warning for "test_multi_speaker_vits_generator_forward[model_dict7]", test/espnet2/asr/decoder/test_whisper_decoder.py, and some other files. I only add several lines of descriptions and comments, so I guess this is not my fault?

@sw005320
Copy link
Contributor

sw005320 commented Oct 3, 2024

Thanks for dealing with them!

However, the new pull request fails in github code checking (the previous pull request passed the check). I check the test case, it raises warning for "test_multi_speaker_vits_generator_forward[model_dict7]", test/espnet2/asr/decoder/test_whisper_decoder.py, and some other files. I only add several lines of descriptions and comments, so I guess this is not my fault?

This comes from the randomness of CI (if CI assigns to slow machines, they cannot conduct the test within the time limit). I reran the CI. I'll take care of the rest. Once the CI is passed fully, I'll merge this PR.

@sw005320 sw005320 merged commit 28ca848 into espnet:master Oct 4, 2024
@sw005320 sw005320 added this to the v.202412 milestone Oct 4, 2024
@sw005320
Copy link
Contributor

sw005320 commented Oct 4, 2024

Thanks, @anyuyay!

Shikhar-S pushed a commit to Shikhar-S/espnet that referenced this pull request Mar 13, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants