.. torchsynth documentation master file, created by
sphinx-quickstart on Tue Mar 9 01:30:39 2021.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
torchsynth is based upon traditional modular synthesis written in pytorch. It is GPU-optional and differentiable.
Most synthesizers are fast in terms of latency. torchsynth is fast in terms of throughput. It synthesizes audio 16200x faster than realtime (714MHz) on a single GPU. This is of particular interest to audio ML researchers seeking large training corpora.
Additionally, all synthesized audio is returned with the underlying latent parameters used for generating the corresponding audio. This is useful for multi-modal training regimes.
If you'd like to hear torchsynth, check out
synth1K1, a dataset of
1024 4-second sounds rendered from the {class}~torchsynth.synth.Voice
synthesizer, or listen to the following SoundCloud embed:
Here is another set of sounds created with the {class}~torchsynth.synth.Voice
Drum Nebula. In torchsynth a nebula is a set of hyperparameters that defines how
synthesizer parameters are sampled. The hyperparameters of the Drum Nebula were hand-tuned
to increase the likelihood of the {class}~torchsynth.synth.Voice
producing percussive
samples.
---
maxdepth: 1
name: getting_started
caption: Getting started
---
getting-started/installation
getting-started/quickstart
getting-started/detailed-walkthrough
---
maxdepth: 1
name: performance
caption: Performance
---
performance/batch-processing
performance/multi-gpu
---
maxdepth: 1
name: modular_design
caption: Modular Design
---
modular-design/modular-principles
modular-design/new-synths
---
maxdepth: 1
name: reproducibility
caption: Reproducibility
---
reproducibility/reproducibility
reproducibility/synth1B1
---
maxdepth: 1
name: contributing
caption: Contributing
---
contributing/contributing
---
maxdepth: 3
name: modules
caption: API
---
api/config
api/module
api/parameter
api/signal
api/synth
api/util
---
maxdepth: 1
name: docmap
caption: INDICES AND TABLES
---
genindex
search