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

Instructions for real-time pitch detection #61

Open
DannySalem opened this issue Jul 5, 2020 · 3 comments
Open

Instructions for real-time pitch detection #61

DannySalem opened this issue Jul 5, 2020 · 3 comments

Comments

@DannySalem
Copy link

I'm interested in using crepe in an online app. I'd like to use crepe in a very similar way as it is used in the example website: marl.github.io/crepe/. The readme shows how to use it for wav files, is there somewhere I can find instructions on how to use it in real-time microphone input data?

@justinsalamon
Copy link
Collaborator

The crepe model uses a sampling rate of 16 kHz, and takes 1024 samples as input i.e. 64 milliseconds. You could pass every 1024 samples from your audio buffer into the model to get a prediction per 64 milliseconds. Of course you could use an even smaller hop size (e.g. 10ms as in the offline implementation). The only caveat to a real-time implementation is that you can't use the viterbi tracking to smooth the pitch curve. Hope this helps.

@DannySalem
Copy link
Author

@justinsalamon That helps thanks! I'd definitely be able to do it on my own but I was hoping the code for the github website would be available too somewhere but i couldnt find a repo for it. Is that available anywhere?

@0b01
Copy link

0b01 commented Jul 13, 2020

It's the gh-pages branch. Hope this helps.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants