You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
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.
@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?
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?
The text was updated successfully, but these errors were encountered: