A transformer-based network model for pitch detection

Re:A transformer-based network model for pitch detection by rrherr on Tuesday December 19, 2023 @11:53AM (#38698005)

How does the accuracy of this compare to CREPE?

https://github.com/maxrmorrison/torchcrepe

Does anyone know what the current state of the art is, within the Music Information Retrieval community?

[ Parent | on HN ]

Re:A transformer-based network model for pitch detection by CMLab on Tuesday December 19, 2023 @01:05PM (#38699136)

CREPE generally has high latency and error rates in instrument pitch recognition, especially for guitar instruments. Our team will release benchmark test data and results later.

[ Parent | on HN ]

Re:A transformer-based network model for pitch detection by rrherr on Tuesday December 19, 2023 @01:41PM (#38699688)

Thanks. I’d love to try TuneNN! Are you releasing a pretrained model? How do I run it on a wav file?

[ Parent | on HN ]

Re:A transformer-based network model for pitch detection by xavriley on Tuesday December 19, 2023 @05:35PM (#38702844)

High latency - agreed but it depends on whether a GPU is available or not. If it is then theoretically CREPE could be real-time. The error rates for pitch recognition are still quite good though for the full CREPE model. I’m interested to see the data on this claim.

[ Parent | on HN ]