Skip to content

SpeechX Architecture

Hui Zhang edited this page Jan 26, 2022 · 11 revisions

Layout of Source File

The layout structure is as follows:

speechx/
├── CMakeLists.txt
├── docker    # dockerfiles
├── examples  # asr, tts examples
└── speechx   # lib .a/.so
    ├── CMakeLists.txt
    ├── decoder   # decoder
    │   └── CMakeLists.txt
    ├── frontend  # feature
    │   ├── CMakeLists.txt
    │   ├── audio
    │   │   └── CMakeLists.txt
    │   └── text
    │       └── CMakeLists.txt
    ├── kaldi    # kaldi libs
    ├── model    # inference engine
    │   └── CMakeLists.txt
    ├── protocol # http/websoket/grpc
    │   └── CMakeLists.txt
    ├── third_party
    │   └── CMakeLists.txt
    └── utils
        └── CMakeLists.txt

12 directories, 10 files

Common Modules

  • gflag,glog,gtest:openfst 使用的是 gflag/glog,替换KALDI_WARN等。
  • utils: absl-cpp
  • config:使用 kaldi config
  • protobuf: grpc用
  • tcmalloc
  • mempool
  • threadpool: https://github.com/progschj/ThreadPool
  • queue
  • decode task

Clone this wiki locally