Yabin Li
|
a0048dc766
|
8k (#1174) (#1175)
* Adaptive 8K
* fix FfmpegLoad 8k
Co-authored-by: cdevelop <cdevelop@qq.com>
|
2023-12-13 09:50:58 +08:00 |
|
雾聪
|
3c83d64c84
|
fst: support eng hotword
|
2023-12-12 11:11:02 +08:00 |
|
雾聪
|
d674c29323
|
add timestamp smooth
|
2023-12-11 15:51:38 +08:00 |
|
雾聪
|
e9fdbe3f5a
|
set openfst HAVE_BIN/HAVE_SCRIPT off for win32
|
2023-11-29 11:33:06 +08:00 |
|
雾聪
|
eed40f4f08
|
fix bug of LfrCmvn
|
2023-11-26 15:19:44 +08:00 |
|
Yabin Li
|
0c68c942fe
|
fix LfrCmvn for paraformer (#1097)
|
2023-11-16 16:17:37 +08:00 |
|
雾聪
|
ffd085581a
|
update docs
|
2023-11-16 13:58:33 +08:00 |
|
Yabin Li
|
11589f8abb
|
modify cmakelist & glog for wins (#1094)
* modify glog
* update cmakelist
|
2023-11-16 09:35:17 +08:00 |
|
cdevelop
|
eff2570faf
|
解决windwos 加载lm模型失败 (#1093)
* fix vc compatibility
* fix windwos load lm model failed
|
2023-11-15 19:46:00 +08:00 |
|
雾聪
|
9dcd514dc7
|
modify openfst CMakeLists
|
2023-11-15 14:13:32 +08:00 |
|
Yabin Li
|
da5438ff68
|
Update CMakeLists.txt
|
2023-11-15 10:40:17 +08:00 |
|
雾聪
|
fe3944d1ce
|
rename glog head files for ios
|
2023-11-15 10:13:42 +08:00 |
|
雾聪
|
6d6c6e3c79
|
update docs; update run_server.sh; fix initlm
|
2023-11-14 19:22:17 +08:00 |
|
雾聪
|
981b5356a5
|
fix CMakeLists for windows
|
2023-11-14 10:39:36 +08:00 |
|
雾聪
|
c0bfc7c6fe
|
update docs
|
2023-11-13 19:56:43 +08:00 |
|
雾聪
|
923689bb07
|
update docs
|
2023-11-13 17:43:08 +08:00 |
|
Yabin Li
|
e9799f5f1f
|
Update readme.md
|
2023-11-13 16:51:56 +08:00 |
|
Yabin Li
|
feb72814c9
|
Update readme.md
|
2023-11-13 16:49:43 +08:00 |
|
雾聪
|
bf35a4a4e7
|
add glog/*.h for ios
|
2023-11-13 16:40:58 +08:00 |
|
cdevelop
|
be7ddfc4cd
|
runtime windows build (#1082)
* onnxruntime windows build
* runtime websocket windows build
* Upgrade glog
|
2023-11-13 16:15:05 +08:00 |
|
雾聪
|
dfe78d1877
|
modify paraformer-online funcs
|
2023-11-09 13:28:11 +08:00 |
|
雾聪
|
00a0f54b6b
|
update func FunTpassInferBuffer
|
2023-11-09 13:02:53 +08:00 |
|
雾聪
|
b0c1082792
|
update tokenizer.h
|
2023-11-09 11:05:51 +08:00 |
|
雾聪
|
9954fae387
|
tokenizer.cpp
|
2023-11-09 11:04:21 +08:00 |
|
雾聪
|
71f95f256b
|
update funasr-onnx-2pass.cpp
|
2023-11-09 10:56:22 +08:00 |
|
Yabin Li
|
702ec03ad8
|
Dev new (#1065)
* add hotword for deploy_tools
* Support wfst decoder and contextual biasing (#1039)
* Support wfst decoder and contextual biasing
* Turn on fstbin compilation
---------
Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com>
* mv funasr/runtime runtime
* Fix crash caused by OOV in hotwords list
* funasr infer
* funasr infer
* funasr infer
* funasr infer
* funasr infer
* fix some bugs about fst hotword; support wfst for websocket server and clients; mv runtime out of funasr; modify relative docs
* del onnxruntime/include/gflags
* update tensor.h
* update run_server.sh
* update deploy tools
* update deploy tools
* update websocket-server
* update funasr-wss-server
* Remove self loop propagation
* Update websocket_protocol_zh.md
* Update websocket_protocol_zh.md
* update hotword protocol
* author zhaomingwork: change hotwords for h5 and java
* update hotword protocol
* catch exception for json_fst_hws
* update hotword on message
* update onnx benchmark for ngram&hotword
* update docs
* update funasr-wss-serve
* add NONE for LM_DIR
* update docs
* update run_server.sh
* add whats-new
* modify whats-new
* update whats-new
* update whats-new
* Support decoder option for beam searching
* update benchmark_onnx_cpp
* Support decoder option for websocket
* fix bug of CompileHotwordEmbedding
* update html client
* update docs
---------
Co-authored-by: gongbo.gb <35997837+aibulamusi@users.noreply.github.com>
Co-authored-by: gongbo.gb <gongbo.gb@alibaba-inc.com>
Co-authored-by: 游雁 <zhifu.gzf@alibaba-inc.com>
|
2023-11-07 18:34:29 +08:00 |
|