richardassar/SampleRNN_torch
Torch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
This project helps musicians, sound designers, or researchers create new, original audio by learning patterns from existing sound recordings. You provide a collection of audio files, like piano performances or speech, and it generates entirely new audio that sounds similar in style and characteristics. It's for anyone looking to experiment with synthesizing realistic audio without manually composing or recording every sound.
156 stars. No commits in the last 6 months.
Use this if you want to generate unique musical phrases, sound effects, or vocalizations based on a dataset of existing audio examples.
Not ideal if you need to perform specific audio editing tasks, mix tracks, or apply effects to existing audio files.
Stars
156
Forks
25
Language
Lua
License
—
Category
Last pushed
May 21, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/richardassar/SampleRNN_torch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.