added a script for transcribing wav files to midi

jongwook / onsets-and-frames

A Pytorch implementation of Onsets and Frames (Hawthorne 2018)

MIT License

209 stars 66 forks source link

added a script for transcribing wav files to midi #7

Closed SargamMenghani closed 5 years ago

SargamMenghani commented 5 years ago

This is just a modification to the evaluate.py script so that we can directly transcribe a given wav file without running through the evaluation part.

jongwook commented 5 years ago

Thanks for the PR! It was definitely a missing part of this repo.

Since soundfile.read can read other formats than wav, should it be named just transcribe.py?

SargamMenghani commented 5 years ago

Yes, thanks for the suggestion! I have changed the filename to transcribe.py

jongwook commented 5 years ago

Thank you! I've made some cosmetic changes in the CLI before merging, to require the user to specify the model file and allow them to supply multiple FLAC files.

Please execuse the bunch of commits ended up listed above from my mismangement of the git tree😓