Fangjun Kuang
9efe69720d
Support VITS VCTK models ( #367 )
...
* Support VITS VCTK models
* Release v1.8.1
2023-10-16 17:22:30 +08:00
Fangjun Kuang
655e0fa836
add python API and examples for TTS ( #364 )
2023-10-14 14:21:53 +08:00
Peng He
4771c9275c
Add lm decode for the Python API. ( #353 )
...
* Add lm decode for the Python API.
* fix style.
* Fix LogAdd,
Shouldn't double lm_log_prob when merge same prefix path
* sort the import alphabetically
2023-10-13 11:15:16 +08:00
Fangjun Kuang
407602445d
Add CTC HLG decoding using OpenFst ( #349 )
2023-10-08 11:32:39 +08:00
Fangjun Kuang
33a5765169
Print a more user-friendly error message when using --hotwords-file. ( #344 )
2023-09-26 11:04:20 +08:00
Fangjun Kuang
c471423125
Add Silero VAD ( #313 )
2023-09-17 14:54:38 +08:00
Wei Kang
47184f9db7
Refactor hotwords，support loading hotwords from file ( #296 )
2023-09-14 19:33:17 +08:00
Fangjun Kuang
f709c95c5f
Support multilingual whisper models ( #274 )
2023-08-16 00:28:52 +08:00
Fangjun Kuang
6038e2aa62
Support streaming paraformer ( #263 )
2023-08-14 10:32:14 +08:00
Fangjun Kuang
a4bff28e21
Support TDNN models from the yesno recipe from icefall ( #262 )
2023-08-12 19:50:22 +08:00
Fangjun Kuang
b094868fb8
Add non-streaming websocket server for python ( #259 )
2023-08-11 15:56:24 +08:00
Fangjun Kuang
79c2ce5dd4
Refactor online recognizer ( #250 )
...
* Refactor online recognizer.
Make it easier to support other streaming models.
Note that it is a breaking change for the Python API.
`sherpa_onnx.OnlineRecognizer()` used before should be
replaced by `sherpa_onnx.OnlineRecognizer.from_transducer()`.
2023-08-09 20:27:31 +08:00
Fangjun Kuang
45b9d4ab37
Support whisper models ( #238 )
2023-08-07 12:34:18 +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
f3206c49dc
Reduce model initialization time for offline speech recognition ( #213 )
2023-07-14 18:07:27 +08:00
Fangjun Kuang
bebc1f1398
Use static libraries for MFC examples ( #210 )
2023-07-13 14:52:43 +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
33bf8dc1f4
Support specifying providers in Python API ( #198 )
2023-07-06 10:14:01 +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
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
5e2dc5ceea
add streaming-server with web client ( #164 )
...
* add streaming-server with web client
* small fixes
2023-05-30 22:46:52 +08:00
Fangjun Kuang
cea718e3d8
Support CoreML for macOS ( #151 )
2023-05-12 15:57:44 +08:00
PF Luo
8c6a6768d5
Add lm rescore to online-modified-beam-search ( #133 )
2023-05-05 21:23:54 +08:00
Fangjun Kuang
86017f9833
Add RNN LM rescore for offline ASR with modified_beam_search ( #125 )
2023-04-23 17:15:18 +08:00
Fangjun Kuang
80060c276d
Begin to support CTC models ( #119 )
...
Please see https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-ctc/nemo/index.html for a list of pre-trained CTC models from NeMo.
2023-04-07 23:11:34 +08:00
KajiMaCN
7f7e3680c3
Modify the rule attribute data type of OnlineRecognizer ( #113 )
2023-04-04 15:42:56 +08:00
Fangjun Kuang
5d3c8edbc9
add python tests ( #111 )
2023-04-02 23:05:30 +08:00
manyeyes
3f7e0c23ac
adding a python api for offline decode ( #110 )
2023-04-02 13:17:43 +08:00
Fangjun Kuang
5572246253
Add non-streaming ASR ( #92 )
2023-03-26 08:53:42 +08:00
Fangjun Kuang
c230cf0a97
Fix building wheels for Windows ( #81 )
2023-03-05 10:00:18 +08:00
Fangjun Kuang
9d8fddef01
Support resampling ( #77 )
2023-03-03 16:42:33 +08:00
Fangjun Kuang
7f72c13d9a
Code refactoring ( #74 )
...
* Don't reset model state and feature extractor on endpointing
* support passing decoding_method from commandline
* Add modified_beam_search to Python API
* fix C API example
* Fix style issues
2023-03-03 12:10:59 +08:00
Fangjun Kuang
e4b79ad34b
Add Python websocket client ( #63 )
2023-02-24 22:46:30 +08:00
Fangjun Kuang
9064b3f016
Support Android ( #59 )
2023-02-24 13:57:03 +08:00
Fangjun Kuang
124384369a
Add endpointing ( #54 )
2023-02-22 15:35:55 +08:00
Fangjun Kuang
ea09d5fbc5
Add Python API ( #31 )
2023-02-19 19:36:03 +08:00
