EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
171 Commits 2 Branches 0 Tags
5c9aebd5839cca2ba44384019d393212ece61882
Commit Graph

171 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
zhaomingwork
5c9aebd583 For java ci actions (#231) 2023-08-05 10:32:48 +08:00
Fangjun Kuang
92976b04a0 Update sherpa-onnx-go package version (#233) 2023-08-04 12:33:06 +08:00
frankyoujian
801693a4d4 Support real time hotwords on python (#230) 
* support real time hotwords on python

* fix comments
 2023-08-03 15:50:11 +08:00
Fangjun Kuang
8ab0090909 Fix scripts for releasing go packages (#232) 2023-08-03 10:55:03 +08:00
Fangjun Kuang
c88e672733 Fix building wheels on Windows (#229) 2023-08-01 13:45:02 +08:00
zhaomingwork
5a549615df Java api update for adding modelType in config class (#228) 2023-07-30 17:04:18 +08:00
Jingzhao Ou
daffdab52a Updated hypothesis key generation to be the same as sherpa (#226) 2023-07-28 14:19:49 +08:00
Fangjun Kuang
a12252a01d Fix windows CUDA build CI (#223) 2023-07-25 12:33:23 +08:00
Fangjun Kuang
17a2079cfb Test Windows CUDA support in CI (#222) 2023-07-25 12:20:43 +08:00
Fangjun Kuang
b96837d766 Release v1.5.4 (#221) 2023-07-21 18:05:26 +08:00
Fangjun Kuang
e63d205b3d Add go-api-examples (#219) 2023-07-21 17:56:09 +08:00
Fangjun Kuang
6125d9e063 Refactor onnxruntime.cmake (#220) 2023-07-18 15:44:54 +08:00
Fangjun Kuang
bd74e1c4e5 Fix CI tests (#218) 2023-07-15 19:54:27 +08:00
Fangjun Kuang
5d820b88ef Publish pre-compiled libs for Android. (#217) 2023-07-15 12:25:18 +08:00
Fangjun Kuang
de2673680e Fix model_type for jni, c# and iOS. (#216) 2023-07-14 22:24:38 +08:00
Wilson Wongso
5a6b55c5a7 Reduce model initialization time for online speech recognition (#215) 
* Reduce model initialization time for online speech recognition

* Fixed Styling

---------

Co-authored-by: w11wo <wilsowong961@gmail.com>
 2023-07-14 21:20:10 +08:00
Fangjun Kuang
fe0630fe1f release-v1.5.2 (#214) 2023-07-14 18:18:42 +08:00
Fangjun Kuang
f3206c49dc Reduce model initialization time for offline speech recognition (#213) 2023-07-14 18:07:27 +08:00
Fangjun Kuang
0abd7ce881 Add non-streaming speech recognition examples for MFC (#212) 2023-07-14 17:00:14 +08:00
Fangjun Kuang
bebc1f1398 Use static libraries for MFC examples (#210) 2023-07-13 14:52:43 +08:00
Fangjun Kuang
10f132cfd6 small fixes for MFC examples (#209) 2023-07-12 13:45:35 +08:00
Fangjun Kuang
c818b82e13 Add examples for Visual C++ MFC (#208) 2023-07-12 13:37:28 +08:00
Fangjun Kuang
5cd72ba3aa Fix setting context lists. (#207) 2023-07-12 09:18:56 +08:00
Wilson Wongso
b2364b0374 Implemented tokens and timestamps in Python API (#205) 2023-07-12 09:12:31 +08:00
Fangjun Kuang
0b5fa24134 Upload pre-compiled binaries and libraries on release (#206) 2023-07-10 17:59:08 +08:00
Fangjun Kuang
4eacbed0b2 Update onnxruntime from v1.14.0 to v1.15.1 (#204) 2023-07-09 14:42:19 +08:00
Fangjun Kuang
fa86597f98 Publish pre-compiled xcframework for iOS via GitHub actions (#203) 2023-07-08 13:46:28 +08:00
Fangjun Kuang
ba26783eb0 Support 32-bit ARM Linux (#202) 2023-07-07 17:30:06 +08:00
Jingzhao Ou
27762bb169 fixed broken build when user provides their own onnxruntime library (#201) 2023-07-07 14:26:09 +08:00
Fangjun Kuang
a8599507ca Publish universal wheel for macOS (#200) 2023-07-06 18:05:52 +08:00
Fangjun Kuang
adcb5776d8 Publish pre-compiled wheels for Win32 (#199) 2023-07-06 15:08:52 +08:00
Fangjun Kuang
33bf8dc1f4 Support specifying providers in Python API (#198) 2023-07-06 10:14:01 +08:00
Fangjun Kuang
3a08191a43 Build pre-compiled wheels for aarch64 (Linux) (#197) 2023-07-06 08:40:25 +08:00
Fangjun Kuang
a40697f633 Fix building for GPU support. (#195) 2023-07-05 18:18:31 +08:00
Fangjun Kuang
1f02f7c349 Support recognition from URLs. (#194) 2023-07-04 10:16:11 +08:00
Fangjun Kuang
2c436606bd Support .Netstandard 2.0 (#193) 2023-07-02 22:57:48 +08:00
Fangjun Kuang
0dd2d41f27 Real-time speech recognition from microphone for .Net (#192) 
* 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
 2023-07-01 18:55:41 +08:00
Wei Kang
513dfaa552 Support contextual-biasing for streaming model (#184) 
* Support contextual-biasing for streaming model

* The whole pipeline runs normally

* Fix comments
 2023-06-30 16:46:24 +08:00
Fangjun Kuang
b2e0c4c9c2 Update iOS and Android demos to include the latest streaming zipformer (#189) 2023-06-27 18:11:37 +08:00
James
dab22c4764 Add detection conditions under the x86 platform. (#186) 
When downloading onnxruntime, add detection conditions under the x86 platform.
 2023-06-26 12:05:03 +08:00
danfu
1c3dac9001 support streaming zipformer2 (#185) 
Co-authored-by: danfu <danfu@tencent.com>
 2023-06-26 11:09:43 +08:00
Fangjun Kuang
157b6b801b Fix C# APIs (#183) 
* Fix c# APIs

* reformat
 2023-06-24 00:56:53 +08:00
fx
81579bbddd fix numpy bug (#181) 2023-06-20 20:55:47 +08:00
Fangjun Kuang
d82251cba6 Support the latest offline zipformer model (#180) 2023-06-19 14:09:24 +08:00
Wei Kang
8562711252 Implement context biasing with a Aho Corasick automata (#145) 
* 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
 2023-06-16 14:26:36 +08:00
keanu
1a1b9fd236 RNNLM model support lm_num_thread and lm_provider setting (#173) 
* 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>
 2023-06-12 15:51:27 +08:00
Fangjun Kuang
13b33fcc08 Release v1.4.4 (#172) 2023-06-08 09:41:04 +08:00
keanu
9c017c2ccb rnnlm model inference supports num_threads setting (#169) 
Co-authored-by: cuidongcai1035 <cuidongcai1035@wezhuiyi.com>
 2023-06-07 09:32:27 +08:00
Fangjun Kuang
8fad17c87e Fix iOS build (#167) 2023-06-04 23:03:22 +08:00
Jingzhao Ou
fdd49d0538 add batch processing to sherpa-onnx (#166) 2023-06-04 14:13:55 +08:00