Skip to content
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

Automatic lyric recognition Recipe #4129

Merged
merged 6 commits into from
Mar 7, 2022
Merged

Automatic lyric recognition Recipe #4129

merged 6 commits into from
Mar 7, 2022

Conversation

ftshijt
Copy link
Collaborator

@ftshijt ftshijt commented Mar 3, 2022

For 11-737 HW3

I will update pre-trained model and results later

@ftshijt ftshijt requested a review from simpleoier March 3, 2022 21:24
@ftshijt ftshijt added the ASR Automatic speech recogntion label Mar 3, 2022
@codecov
Copy link

codecov bot commented Mar 3, 2022

Codecov Report

Merging #4129 (66f21b6) into master (a04a98c) will not change coverage.
The diff coverage is n/a.

Impacted file tree graph

@@           Coverage Diff           @@
##           master    #4129   +/-   ##
=======================================
  Coverage   80.43%   80.43%           
=======================================
  Files         442      442           
  Lines       38557    38557           
=======================================
  Hits        31015    31015           
  Misses       7542     7542           
Flag Coverage Δ
test_integration_espnet1 67.13% <ø> (ø)
test_integration_espnet2 51.14% <ø> (ø)
test_python 66.51% <ø> (ø)
test_utils 24.45% <ø> (ø)

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


Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update a04a98c...66f21b6. Read the comment docs.

@sw005320 sw005320 added this to the v.0.10.7 milestone Mar 5, 2022
@sw005320 sw005320 added the Recipe label Mar 5, 2022
@ftshijt
Copy link
Collaborator Author

ftshijt commented Mar 7, 2022

The results seem promising, will merge the recipe first and update the results and pre-trained model in another PR

@ftshijt ftshijt merged commit 5e07066 into espnet:master Mar 7, 2022
Copy link
Collaborator

@simpleoier simpleoier left a comment

Choose a reason for hiding this comment

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

LGTM!

@@ -39,13 +39,13 @@ class ApplyKmeans(object):
def __init__(self, km_path):
self.km_model = joblib.load(km_path)
self.nc = self.km_model.cluster_centers_.transpose()
self.nc_norm = (self.nc ** 2).sum(0, keepdims=True)
self.nc_norm = (self.nc**2).sum(0, keepdims=True)
Copy link
Collaborator

Choose a reason for hiding this comment

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

Can you depress this modification?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I think the issue comes from the newer black version. The results are identical here?


def __call__(self, x):
if isinstance(x, torch.Tensor):
x = x.cpu().numpy()
probs = (
(x ** 2).sum(1, keepdims=True) - 2 * np.matmul(x, self.nc) + self.nc_norm
(x**2).sum(1, keepdims=True) - 2 * np.matmul(x, self.nc) + self.nc_norm
Copy link
Collaborator

Choose a reason for hiding this comment

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

Ditto.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ASR Automatic speech recogntion ESPnet2 README Recipe
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants