Home Explore Help
Register Sign In
zhangyupeng
/
speech-denoiser
mirror of https://github.com/lucianodato/speech-denoiser.git
1
0
Fork 0
Files Issues 0 Wiki
Tree: 97f5fefc39
Branches Tags
speech-denoi...
/
rnnoise
Luciano Dato 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
..
doc 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
examples 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
include 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
m4 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
scripts 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
src 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
training 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
AUTHORS 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
COPYING 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
Makefile.am 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
README 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
TRAINING 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
autogen.sh 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
configure.ac 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
rnnoise-nu-uninstalled.pc.in 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago
rnnoise-nu.pc.in 54eb1a1fa6 Move to using git tree instead of a submodule 7 years ago

README

RNNoise is a noise suppression library based on a recurrent neural network.
RNNoise-nu is a modified version of RNNoise aimed to be a bit more general
purpose.

To compile, just type:
% autoreconf -i
% ./configure
% 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 [model to use] < input.raw > output.raw

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

For information on the neural network models available, see
https://github.com/GregorR/rnnoise-models