1
$\begingroup$

I am looking for a relatively large amount of jazz (and other) solos to use for data science purposes - probably somewhere up to a 100 transctipts. Although that is not that much and many pdf transcripts are available, I want the data to be in a format where I can easily access all the information in Python (which note was played and at what beat). Manually writing all that data would, however, be very tedious and time-consuming.

Thus my question: does anyone know of any software that automatically reads pdf transcripts and puts it in a different file format, or alternatively of a website with transcripts already in a format in which I can access all the data easily from Python?

$\endgroup$
1
  • $\begingroup$ Any chance you can get the music as Midi files? $\endgroup$
    – Spacedman
    Jan 5 '17 at 7:55
1
$\begingroup$

I think you are looking for musical optical character recognition software. A google search pointed me to Wikipedia where links to two open source applications resides: Audiveris and OpenOMR. I can not vouch for either program.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.