GitHub - NarrationBox/rnnoise: Recurrent neural network for audio noise reduction

This branch is 1 commit ahead of, 5 commits behind xiph/rnnoise:master.

Name	Name	Last commit message	Last commit date
Latest commit Chetan Malhotra Update README May 15, 2021 01ba11d · May 15, 2021 History 89 Commits
doc	doc	Adding build system	Aug 17, 2017
examples	examples	Access files in binary mode	Jun 28, 2020
include	include	Document the API	Jan 22, 2021
m4	m4	Adding build system	Aug 17, 2017
src	src	Correct #endif in rnn.h.	Jan 22, 2021
training	training	Adding instructions on training.	May 29, 2019
AUTHORS	AUTHORS	Adding build system	Aug 17, 2017
COPYING	COPYING	Initial license and README	Aug 3, 2017
Makefile.am	Makefile.am	Neural network model files	May 29, 2019
README	README	Update README	May 15, 2021
TRAINING-README	TRAINING-README	rename TRAINING -> TRAINING-README for case insensitive file system	Jun 28, 2020
autogen.sh	autogen.sh	Adding build system	Aug 17, 2017
configure.ac	configure.ac	Adding build system	Aug 17, 2017
rnnoise-uninstalled.pc.in	rnnoise-uninstalled.pc.in	Adding build system	Aug 17, 2017
rnnoise.pc.in	rnnoise.pc.in	Adding build system	Aug 17, 2017
update_version	update_version	Adding build system	Aug 17, 2017

Repository files navigation

RNNoise is a noise suppression library based on a recurrent neural network.

To compile, just type:
1. brew install automake autoconf libtool (For mac users only)
2. ./autogen.sh
3. ./configure
4. make

Optionally:
% make install

While it is meant to be used as a library, a simple command-line tool is
provided as an example. It operates on RAW 16-bit (machine endian) mono
PCM files sampled at 48 kHz. It can be used as:

./examples/rnnoise_demo <noisy speech> <output denoised>

The output is also a 16-bit raw PCM file.

The latest version of the source is available from
https://gitlab.xiph.org/xiph/rnnoise .  The github repository
is a convenience copy.