-
Notifications
You must be signed in to change notification settings - Fork 1.9k
SpeechX Architecture
Hui Zhang edited this page Jan 26, 2022
·
11 revisions
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
- 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