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.
Hui Zhang
dfdf450b22
|
3 years ago | |
---|---|---|
.. | ||
cmake | 3 years ago | |
docker | 3 years ago | |
examples | 3 years ago | |
patch | 3 years ago | |
speechx | 3 years ago | |
tools | 3 years ago | |
.gitignore | 3 years ago | |
CMakeLists.txt | 3 years ago | |
README.md | 3 years ago | |
build.sh | 3 years ago |
README.md
SpeechX -- All in One Speech Task Inference
Environment
We develop under:
- docker -
registry.baidubce.com/paddlepaddle/paddle:2.2.2-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
- First to launch docker container.
docker run --privileged --net=host --ipc=host -it --rm -v $PWD:/workspace --name=dev registry.baidubce.com/paddlepaddle/paddle:2.2.2-gpu-cuda10.2-cudnn7 /bin/bash
- More
Paddle
docker images you can see here.
- Build
speechx
andexamples
.
Do not source venv.
pushd /path/to/speechx
./build.sh
- 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 whendocker 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
Deepspeech2 with linear feature
- DecibelNormalizer: there is a small difference between the offline and online db norm. The computation of online db norm reads features chunk by chunk, which causes the feature size to be different different with offline db norm. In
normalizer.cc:73
, thesamples.size()
is different, which causes the different result.