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 '380afbbc5d'
${ noResults }
PaddleSpeech/speechx
History
Hui Zhang 5e4783e12a
rm license 		3 years ago
..
cmake fix openfst patch 3 years ago
docker
…
examples update aishell rsl 3 years ago
patch
…
speechx ds2 ol aishell egs 3 years ago
tools rm license 3 years ago
.gitignore
…
CMakeLists.txt
…
README.md fix typo 3 years ago
build.sh more comment of code; 3 years ago

README.md

SpeechX -- All in One Speech Task Inference

Environment

We develop under:

  • docker - registry.baidubce.com/paddlepaddle/paddle:2.1.1-gpu-cuda10.2-cudnn7
  • os - Ubuntu 16.04.7 LTS
  • gcc/g++/gfortran - 8.2.0
  • cmake - 3.16.0

We make sure all things work fun under docker, and recommend using it to develop and deploy.

Build

  1. First to launch docker container.
nvidia-docker run --privileged  --net=host --ipc=host -it --rm -v $PWD:/workspace --name=dev registry.baidubce.com/paddlepaddle/paddle:2.1.1-gpu-cuda10.2-cudnn7 /bin/bash

  • More Paddle docker images you can see here.

  • If you want only work under cpu, please download corresponded image, and using docker instead nvidia-docker.

  1. Build speechx and examples.

Do not source venv.

pushd /path/to/speechx
./build.sh
  1. Go to examples to have a fun.

More details please see README.md under examples.

Valgrind (Optional)

If using docker please check --privileged is set when docker run.

  • Fatal error at startup: a function redirection which is mandatory for this platform-tool combination cannot be set up
apt-get install libc6-dbg
  • Install
pushd tools
./setup_valgrind.sh
popd

TODO

  • DecibelNormalizer: there is a little bit difference between offline and online db norm. The computation of online db norm read feature chunk by chunk, which causes the feature size is different with offline db norm. In normalizer.cc:73, the samples.size() is different, which causes the difference of result.