ddsp
pedalboard
Our great sponsors
ddsp | pedalboard | |
---|---|---|
3 | 24 | |
2,777 | 4,846 | |
1.9% | 1.8% | |
1.5 | 8.3 | |
4 days ago | 2 days ago | |
Python | C++ | |
Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ddsp
-
Making Synthesized Sounds More Acoustic
You can actually use thousands of oscillators, which is what Magenta did with their differentiable DSP (DDSP) approach to modeling acoustic instruments including singing:
https://magenta.tensorflow.org/ddsp-vst
https://magenta.tensorflow.org/ddsp
I doesn't sound realistic but it is expressive in an unusual way.
-
I need to learn audio processing in Python.
Have you checked out DDSP from magenta? Iām not sure what kind of learning you are trying to implement but they provide a lot of standard signal processing components that are differentiable so you can use them as part of a neural net. There are a handful of collabs that serve as interactive tutorials and the documentation is not bad, I did my bachelors thesis on the topic so I got quite stuck into this for a while
-
Kornia: Differential Computer Vision
In case you're asking about the parent comment (s/Differential/Differentiable), it means the title should be "differentiable CV" (instead of "differential CV").
"Differentiable" describes some computation for which derivatives can be computed. "Differential" is a more general term which means that something has to do with differences, e.g. differential equations deal with equations that specify how things change together.
With the recent surge in deep learning came significant improvements in optimization techniques and hardware, making it feasible to formulate some computations in a differentiable manner. Doing that allows one to optimize the computation process relatively efficiently, at least in theory. Some other examples: differentiable programming[0] (other differentiable techniques are a subset of this), differentiable rendering[1], differentiable signal processing[2].
[0] https://en.wikipedia.org/wiki/Differentiable_programming
[1] https://arxiv.org/abs/2006.12057
[2] https://github.com/magenta/ddsp
pedalboard
-
Open Source Libraries
spotify/pedalboard: audio effects for Python and TensorFlow
-
Importing a library from GitHub?
pip install git+https://github.com/spotify/pedalboard.git
-
Python-based (or usable through command-line) synths and samplers
I haven't tried it yet, but pedalboard is probably your best bet. DawDreamer also looks interesting ...
-
Library for Audio Effects (Debian Raspberry Pi)
I found this really cool and promising library called "Pedalboard" but when I try to install it using PIP I get this error message:
- converting normal audio into 3D audio and 'changing the distance'
-
I need to learn audio processing in Python.
Perhaps Spotify Pedalboard might be of interest
-
This Week In Python
pedalboard ā A Python library for manipulating audio
-
Suggestions for processing ~12,000 audio files for ML?
Thanks for the suggestions, everybody! I'm going to try writing a python script using this library: https://github.com/spotify/pedalboard to loop through all files in my sample directory and save the processed outputs to a new folder. Hoping it doesn't melt my poor 2018 Macbook Pro - I'll try running it on a smaller folder at first and see how it goes.
-
Good solution to simply run VST directly without DAW?
Do you want to run the effect online or offline? You can do it offline with: https://github.com/spotify/pedalboard
-
Library for for generating audio from midi VST?
I think you could do it with this https://github.com/spotify/pedalboard
What are some alternatives?
awesome-python-scientific-audio - Curated list of python software and packages related to scientific research in audio
DawDreamer - Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors
audiogridder - DSP servers using general purpose computers and networks
element - Element Audio Plugin Host
JUCE - JUCE is an open-source cross-platform C++ application framework for desktop and mobile applications, including VST, VST3, AU, AUv3, LV2 and AAX audio plug-ins.
BespokeSynth - Software modular synth [Moved to: https://github.com/BespokeSynth/BespokeSynth]
VeeSeeVSTRack - Open-source virtual modular synthesizer
juce-plugin-ci - DEPRECATED: Cross-platform CI for JUCE audio plugins with Github Actions
SuperVirtualKeyboard - MIDI Plugin made with JUCE for interacting with microtonal piano layouts
ChowMatrix - Matrix delay effect
RenderMan - Command line C++ and Python VSTi Host library with MFCC, FFT, RMS and audio extraction and .wav writing.
diopser - A totally original phase rotation plugin