A modular synthesizer in pytorch, GPU-optional and differentiable
Project description
torchsynth
The fastest synth in the universe.
Introduction
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 15000x faster than realtime on a single GPU.
Installation
pip3 install torchsynth
Note that torchsynth requires PyTorch version 1.8 or greater.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torchsynth-0.9.2.tar.gz
(28.9 kB
view hashes)
Built Distribution
torchsynth-0.9.2-py3-none-any.whl
(30.3 kB
view hashes)
Close
Hashes for torchsynth-0.9.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 91a24469b9d977750c8e56c7dfba5fefe0f2305c528d8b55e662b2633a1f3fa3 |
|
MD5 | 4cb92ec87db8c1ad035865a778b51419 |
|
BLAKE2b-256 | c023a8469158726c247a8107c4f29c1af01a1e4524d41d6a8641e84c87d83a9c |