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 '1d862487c6'
${ noResults }
PaddleSpeech/speechx/examples/ds2_ol/decoder
History
Hui Zhang caf7225892
fix nnet model inputs and output name 		3 years ago
..
local refactor speechx egs 3 years ago
.gitignore refactor speechx egs 3 years ago
CMakeLists.txt add websocket 3 years ago
README.md format 3 years ago
ctc-prefix-beam-search-decoder-ol.cc fix nnet model inputs and output name 3 years ago
nnet-logprob-decoder-test.cc refactor speechx egs 3 years ago
path.sh refactor speechx egs 3 years ago
recognizer_test_main.cc add test script 3 years ago
run.sh fix nnet model inputs and output name 3 years ago
valgrind.sh refactor speechx egs 3 years ago
wfst-decoder-ol.cc fix nnet model inputs and output name 3 years ago

README.md

ASR Decoder

ASR Decoder test bins. We using theses bins to test CTC BeamSearch decoder and WFST decoder.

  • decoder_test_main.cc feed nnet output logprob, and only test decoder

  • offline_decoder_sliding_chunk_main.cc feed streaming audio feature, decode as streaming manner.

  • offline_wfst_decoder_main.cc feed streaming audio feature, decode using WFST as streaming manner.