msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'd1189a7950'
${ noResults }
PaddleSpeech/deploy
History
Yibing Liu d1189a7950
refine wrapper for swig and simplify setup 		8 years ago
..
README.md refine wrapper for swig and simplify setup 8 years ago
__init__.py change probs' computation into log scale & add best path decoder 8 years ago
ctc_decoders.cpp reorganize cpp files 8 years ago
ctc_decoders.h reorganize cpp files 8 years ago
decoder_utils.cpp reorganize cpp files 8 years ago
decoder_utils.h reorganize cpp files 8 years ago
decoders.i refine wrapper for swig and simplify setup 8 years ago
scorer.cpp reorganize cpp files 8 years ago
scorer.h reorganize cpp files 8 years ago
setup.py refine wrapper for swig and simplify setup 8 years ago
swig_decoders_wrapper.py refine wrapper for swig and simplify setup 8 years ago

README.md

Installation

The setup of the decoder for deployment depends on the source code of kenlm and openfst, first clone kenlm and download openfst to current directory (i.e., deep_speech_2/deploy)

git clone https://github.com/kpu/kenlm.git
wget http://www.openfst.org/twiki/pub/FST/FstDownload/openfst-1.6.3.tar.gz
tar -xzvf openfst-1.6.3.tar.gz

Then run the setup

python setup.py install
cd ..

Deployment

For GPU deployment

CUDA_VISIBLE_DEVICES=0 python deploy.py

For CPU deployment

python deploy.py --use_gpu=False

More help for arguments

python deploy.py --help