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 '8ff6221d00'
${ noResults }
PaddleSpeech/deploy
History
Yibing Liu 8ff6221d00
enable finite-state transducer in beam search decoding 		7 years ago
..
README.md adapt to the last three commits 7 years ago
__init__.py change probs' computation into log scale & add best path decoder 8 years ago
ctc_decoders.cpp enable finite-state transducer in beam search decoding 7 years ago
ctc_decoders.h add the support of parallel beam search decoding in deployment 7 years ago
decoder_utils.cpp enable finite-state transducer in beam search decoding 7 years ago
decoder_utils.h enable finite-state transducer in beam search decoding 7 years ago
decoders.i Merge branch 'ctc_decoder_deploy' of https://github.com/kuke/models into ctc_decoder_deploy 7 years ago
path_trie.cpp convert data structure for prefix from map to trie tree 7 years ago
path_trie.h convert data structure for prefix from map to trie tree 7 years ago
scorer.cpp enable finite-state transducer in beam search decoding 7 years ago
scorer.h enable finite-state transducer in beam search decoding 7 years ago
setup.py Make setup.py to support parallel processing. 7 years ago
swig_decoders_wrapper.py add the support of parallel beam search decoding in deployment 7 years ago

README.md

Installation

The build of the decoder for deployment depends on several open-sourced projects, first clone or download them to current directory (i.e., deep_speech_2/deploy)

  • KenLM: Faster and Smaller Language Model Queries
git clone https://github.com/kpu/kenlm.git
  • OpenFst: A library for finite-state transducers
wget http://www.openfst.org/twiki/pub/FST/FstDownload/openfst-1.6.3.tar.gz
tar -xzvf openfst-1.6.3.tar.gz

  • SWIG: Compiling for python interface requires swig, please make sure swig being installed.

  • ThreadPool: A library for C++ thread pool

git clone https://github.com/progschj/ThreadPool.git

Then run the setup

python setup.py install --num_processes 4
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