xuning / sherpaonnx

* Reduce model initialization time for online speech recognition

* Fixed Styling

---------

Co-authored-by: w11wo <wilsowong961@gmail.com>

* Real-time speech recognition from microphone for .Net supporting Linux, macOS, and Windows

* Use PortAudioSharp2.

We will maintain it by ourselves. The project is at
https://github.com/csukuangfj/PortAudioSharp2

* minor fixes

* Support contextual-biasing for streaming model

* The whole pipeline runs normally

* Fix comments

When downloading onnxruntime, add detection conditions under the x86 platform.

Co-authored-by: danfu <danfu@tencent.com>

* Fix c# APIs

* reformat

* Implement context graph

* Modify the interface to support context biasing

* Support context biasing in modified beam search; add python wrapper

* Support context biasing in python api example

* Minor fixes

* Fix context graph

* Minor fixes

* Fix tests

* Fix style

* Fix style

* Fix comments

* Minor fixes

* Add missing header

* Replace std::shared_ptr with std::unique_ptr for effciency

* Build graph in constructor

* Fix comments

* Minor fixes

* Fix docs

* rnnlm model inference supports num_threads setting

* rnnlm params decouple num_thread and provider with Transducer.

* fix python csrc bug which offline-lm-config.cc and online-lm-config.cc arguments problem

* lm_num_threads and lm_provider set default values

---------

Co-authored-by: cuidongcai1035 <cuidongcai1035@wezhuiyi.com>

Co-authored-by: cuidongcai1035 <cuidongcai1035@wezhuiyi.com>

* add streaming-server with web client

* small fixes

* add decode example for mic

* some changes to README.md

* add java websocket srv

* change to readwav to static

* make some changes to code comments

* little change for readme.md

* fix bug about multiple threads

* made little modification

* add protocol in readme, removed static Queue and add lmConfig

---------

Co-authored-by: root <root@localhost.localdomain>