Giter VIP home page Giter VIP logo

Comments (3)

hmartelb avatar hmartelb commented on June 3, 2024

In order to do that, you need to change how the note names are obtained. Just modify this function to suit your needs:

def _get_note_name(self, note, velocity, instrument, source_type, preset=None):
preset = preset if(preset is not None) else self.preset
return "%s_%s_%s-%s-%s.wav" % (instrument, source_type, str(preset).zfill(3), str(note).zfill(3), str(velocity).zfill(3))

If you work on some commonly used synthesizer samples that can be useful for others, feel free to submit a PR with the changes. Cheers!

from nsynth-midi-renderer.

jeremydeanw avatar jeremydeanw commented on June 3, 2024

Im not much of a python user.....I'm assuming I need to train nsynth on my own wav files first, do you know if there is a straight forward way of doing so?

from nsynth-midi-renderer.

hmartelb avatar hmartelb commented on June 3, 2024

I don't understand what your end goal is.

The code in this repository is only intended to generate audio from MIDI files using the existing audio samples in the NSynth dataset (thus, no need to train any model). It just takes the corresponding notes of the selected instrument and places them to match the arrangement of the MIDI file. As a result you get an audio render containing the MIDI file played with the selected instrument.

You can use any samples you want as long as they are annotated in a regular format that can be retrieved with the function I mentioned. I hope it helps

from nsynth-midi-renderer.

Related Issues (2)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.