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 'a840f85423'
${ noResults }
PaddleSpeech/deploy
History
Yibing Liu a840f85423
change probs' computation into log scale & add best path decoder 		8 years ago
..
README.md add setup and README for deployment 8 years ago
__init__.py change probs' computation into log scale & add best path decoder 8 years ago
ctc_beam_search_decoder.cpp change probs' computation into log scale & add best path decoder 8 years ago
ctc_beam_search_decoder.h change probs' computation into log scale & add best path decoder 8 years ago
ctc_beam_search_decoder.i add initial files for deployment 8 years ago
decoder_setup.py code cleanup for the deployment decoder 8 years ago
scorer.cpp change probs' computation into log scale & add best path decoder 8 years ago
scorer.h change probs' computation into log scale & add best path decoder 8 years ago
scorer.i add initial files for deployment 8 years ago
scorer_setup.py code cleanup for the deployment decoder 8 years ago
setup.sh enable loading language model in multiple format 8 years ago
swig_decoder.py change probs' computation into log scale & add best path decoder 8 years ago

README.md

Installation

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

git clone https://github.com/kpu/kenlm.git

Then run the setup

sh setup.sh

After the installation succeeds, go back to the parent directory

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