-
Notifications
You must be signed in to change notification settings - Fork 157
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
performance on MIK-1K #82
Comments
@Dream-High to help with debugging, could you copy-paste the code into a comment here instead of using a screenshot? |
Below is my code
The following is my split details. I evaluate crepe on test datasetsplit_details.json
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Recently, I evaluate crepe on MIR-1K dataset using the open model. The step_size=20, corresponding to MIR-1K label.
![image](https://user-images.githubusercontent.com/28179137/167845785-28cd38be-6d47-49a5-8dd5-512390f82436.png)
![image](https://user-images.githubusercontent.com/28179137/167846012-862428b3-3f72-414a-8dd0-04f9df04ef90.png)
And transfer MIR-1K pitch label to frequency using f = np.power(2, (m-69)/12)*440. However, the performance is not very well.
Is there something bug in my code.
The text was updated successfully, but these errors were encountered: