Commit Graph

113 Commits

Author SHA1 Message Date
Fangjun Kuang
44efff4e47 Fix CI tests for Python and JNI. (#554) 2024-01-27 13:01:54 +08:00
Wei Kang
2ff1049079 change modelscope link to github for build-kws-apki (#540) 2024-01-24 16:40:14 +08:00
Fangjun Kuang
bbd7c7fc18 Add Android demo for speaker recognition (#536)
See pre-built Android APKs at 
https://k2-fsa.github.io/sherpa/onnx/speaker-identification/apk.html
2024-01-23 16:50:52 +08:00
Wei Kang
b6c020901a decoder for open vocabulary keyword spotting (#505)
* various fixes to ContextGraph to support open vocabulary keywords decoder

* Add keyword spotter runtime

* Add binary

* First version works

* Minor fixes

* update text2token

* default values

* Add jni for kws

* add kws android project

* Minor fixes

* Remove unused interface

* Minor fixes

* Add workflow

* handle extra info in texts

* Minor fixes

* Add more comments

* Fix ci

* fix cpp style

* Add input box in android demo so that users can specify their keywords

* Fix cpp style

* Fix comments

* Minor fixes

* Minor fixes

* minor fixes

* Minor fixes

* Minor fixes

* Add CI

* Fix code style

* cpplint

* Fix comments

* Fix error
2024-01-20 22:52:41 +08:00
Fangjun Kuang
68a525a024 Export speaker verification models from NeMo to ONNX (#526) 2024-01-13 19:49:45 +08:00
Fangjun Kuang
afc81ec122 Add C++ runtime for models from 3d-speaker (#523) 2024-01-11 19:10:30 +08:00
Fangjun Kuang
ec728ff7f6 Fix publishing nuget packages. (#525) 2024-01-11 18:54:23 +08:00
Fangjun Kuang
07e2b9a36d Support exporting models to onnx from 3D-Speaker (#522) 2024-01-10 21:09:45 +08:00
Fangjun Kuang
581eceb4d5 Build text-to-speech engine APKs (#509) 2024-01-01 12:44:20 +08:00
Fangjun Kuang
e475e750ac Support streaming zipformer CTC (#496)
* Support streaming zipformer CTC

* test online zipformer2 CTC

* Update doc of sherpa-onnx.cc

* Add Python APIs for streaming zipformer2 ctc

* Add Python API examples for streaming zipformer2 ctc

* Swift API for streaming zipformer2 CTC

* NodeJS API for streaming zipformer2 CTC

* Kotlin API for streaming zipformer2 CTC

* Golang API for streaming zipformer2 CTC

* C# API for streaming zipformer2 CTC

* Release v1.9.6
2023-12-22 13:46:33 +08:00
Fangjun Kuang
ef8d112aaa Fix whisper test script for the latest onnxruntime. (#494) 2023-12-20 11:12:12 +08:00
Fangjun Kuang
33c03f78b2 Fix CI (#485) 2023-12-15 10:25:03 +08:00
Fangjun Kuang
9ff6185b7c fix building linux x86 wheels (#484) 2023-12-14 21:37:40 +08:00
Fangjun Kuang
80d0192325 Fix android tts audio buffer size and fix CI. (#478) 2023-12-10 18:25:50 +08:00
Fangjun Kuang
cae0231f93 Fix releasing go packages (#476) 2023-12-09 00:07:52 +08:00
Fangjun Kuang
aef74c5125 convert wespeaker models to sherpa-onnx (#475) 2023-12-08 19:32:29 +08:00
Fangjun Kuang
868c339e5e Support distil-small.en whisper (#472) 2023-12-08 11:59:20 +08:00
Fangjun Kuang
3ae984f148 Remove the 30-second constraint from whisper. (#471) 2023-12-07 17:47:08 +08:00
Fangjun Kuang
3b90e85ef2 Fix building for .Net (#463) 2023-12-04 19:27:55 +08:00
Fangjun Kuang
62dc3c3e46 Use piper-phonemize to convert text to token IDs (#453) 2023-11-30 23:57:43 +08:00
Fangjun Kuang
db41778e99 Support piper-phonemize (#452) 2023-11-28 19:12:58 +08:00
Fangjun Kuang
8dc08a9b97 Fix nodejs on Windows (#450) 2023-11-25 21:23:15 +08:00
Fangjun Kuang
2f22e6ed63 Add Swift API for TTS (#439) 2023-11-22 16:04:26 +08:00
Fangjun Kuang
fe977b8e8e support nodejs (#438) 2023-11-21 23:20:08 +08:00
Fangjun Kuang
38ad05bdf8 Refactor building wheels (#436) 2023-11-20 12:33:06 +08:00
Fangjun Kuang
ac00edab5b Build MFC examples for Windows x86 (Win32) (#434)
Also, strip binaries on Linux before uploading.
2023-11-18 16:13:09 +08:00
Fangjun Kuang
049fb9f451 Add Python APIs for WeNet CTC models (#428) 2023-11-16 14:20:41 +08:00
Fangjun Kuang
fac4f6bc7c Support streaming conformer CTC models from wenet (#427) 2023-11-16 10:35:23 +08:00
Fangjun Kuang
b83b3e3cd1 Support non-streaming WeNet CTC models. (#426) 2023-11-15 14:23:20 +08:00
Fangjun Kuang
d34640e3a3 Add scripts to export ASR models from wenet to ONNX (#425)
See
https://user-images.githubusercontent.com/5284924/282995968-f6d39118-8008-4ce7-9d7c-d1d6387ac183.png
2023-11-15 11:41:15 +08:00
Fangjun Kuang
a65cdc3d76 Support distil-whisper (#411) 2023-11-06 22:33:39 +08:00
Fangjun Kuang
86baf43c6b support reading rule FST for Android TTS (#410) 2023-11-06 10:38:40 +08:00
Fangjun Kuang
b80b7e5144 Support linking onnxruntime statically for macOS (#403) 2023-10-31 20:24:43 +08:00
Fangjun Kuang
fabbc70633 Support static linking onnxruntime for 64-bit ARM (#402) 2023-10-31 16:51:04 +08:00
Fangjun Kuang
2f2d3bbd82 Support static linking onnxruntime lib for 32-bit arm (#401) 2023-10-31 11:19:01 +08:00
Fangjun Kuang
1544a577e0 Upload TTS APKs to huggingface (#400) 2023-10-29 18:30:43 +08:00
Fangjun Kuang
789a8be73b Add Android TTS demo (#383) 2023-10-24 21:31:28 +08:00
Fangjun Kuang
e7432cd042 Fix jni test (#382) 2023-10-23 15:27:18 +08:00
Fangjun Kuang
a69d0a950e Add Go API for TTS (#377) 2023-10-20 15:57:52 +08:00
Fangjun Kuang
2a932aca86 Add ccache to CI (#375) 2023-10-20 11:17:37 +08:00
Fangjun Kuang
fe0c8bfc51 Test go inside sherpa-onnx (#374)
Previously, we only test the go api examples with pre-built packages. 
This PR tests go API examples against the latest source code of sherpa-onnx.
2023-10-20 10:43:30 +08:00
Fangjun Kuang
ea7c45b60c Add C API for offline TTS. (#373) 2023-10-19 17:38:23 +08:00
Fangjun Kuang
58ab7e77f2 Fix CI test for Go. (#372) 2023-10-19 12:11:12 +08:00
Fangjun Kuang
eead16e27f Fix CI for pip install (#371) 2023-10-19 10:43:14 +08:00
Fangjun Kuang
1ee79e3ff5 Support Chinese vits models (#368) 2023-10-18 10:19:10 +08:00
Fangjun Kuang
0df0a735d7 Fix building wheels for windows (#365) 2023-10-14 23:14:45 +08:00
Fangjun Kuang
655e0fa836 add python API and examples for TTS (#364) 2023-10-14 14:21:53 +08:00
Fangjun Kuang
32da5ecf02 Add script to convert vits models (#355) 2023-10-12 11:59:19 +08:00
Fangjun Kuang
407602445d Add CTC HLG decoding using OpenFst (#349) 2023-10-08 11:32:39 +08:00
Fangjun Kuang
f91c49a7ba Provide pre-built wheels for 32-bit arm (e.g., 32-bit Raspberry Pi) (#338) 2023-09-25 09:33:43 +08:00