Fangjun Kuang
6982b86c66
Support extra languages in multi-lang kokoro tts ( #2303 )
2025-06-20 11:22:52 +08:00
Fangjun Kuang
a6095f5f64
Fix building for Pascal ( #2305 )
2025-06-20 11:10:07 +08:00
Fangjun Kuang
59d118c256
Refactor kokoro export ( #2302 )
...
- generate samples for https://k2-fsa.github.io/sherpa/onnx/tts/all/
- provide int8 model for kokoro v0.19 kokoro-int8-en-v0_19.tar.bz2
2025-06-18 20:30:10 +08:00
Fangjun Kuang
3878170991
Fixes #2172 ( #2301 )
...
Handle the case when the input audio contains no speeches.
2025-06-18 16:48:48 +08:00
Fangjun Kuang
2913cce77c
Add scripts for exporting Piper TTS models to sherpa-onnx ( #2299 )
2025-06-17 14:23:39 +08:00
GlocKieHuan
a135324c8c
Fix isspace on windows in debug build ( #2042 )
2025-06-09 10:27:16 +08:00
Fangjun Kuang
d57e4f84de
Add Python API for source separation ( #2283 )
2025-06-05 20:44:26 +08:00
Fangjun Kuang
1fabc6c79a
Fix rknn for multi-threads ( #2274 )
2025-06-03 20:28:57 +08:00
Fangjun Kuang
2b2788332e
Add C++ support for UVR models ( #2269 )
2025-06-01 17:22:08 +08:00
mtdxc
e0ca224b76
fixed mfc build error ( #2267 )
...
Co-authored-by: cqm <cqm@97kid.com >
2025-05-31 23:32:35 +08:00
mtdxc
613e8084c2
move portaudio common record code to microphone ( #2264 )
...
Co-authored-by: cqm <cqm@97kid.com >
2025-05-31 21:48:41 +08:00
Fangjun Kuang
8e6826521e
Update kaldi-native-fbank. ( #2259 )
...
Now it supports FFT of an even number, not necessarily a power of 2.
2025-05-29 10:34:22 +08:00
Fangjun Kuang
16a3449945
Build APK with replace.fst ( #2254 )
2025-05-28 12:19:29 +08:00
Skepller
640ceb5513
JAVA-API: Manual Library Loading Support for Restricted Environments ( #2253 )
...
* feat: Added LibraryLoader that allows loading to be skipped
* feat: Changed static call to new LibraryLoader
* feat: Makefile adjustment
2025-05-28 06:13:39 +08:00
yegyu
2107afdbd4
Add include headers for __ANDROID_API__,__OHOS__ ( #2251 )
2025-05-27 14:44:06 +08:00
Fangjun Kuang
716ba8317b
Add C++ runtime for spleeter about source separation ( #2242 )
2025-05-23 22:30:57 +08:00
Fangjun Kuang
ff6f3b17ac
Use jlong explicitly in jni. ( #2229 )
2025-05-20 15:29:47 +08:00
Fangjun Kuang
d8bb20710d
Add script to build APK for simulated-streaming-asr. ( #2220 )
2025-05-15 15:40:22 +08:00
esavin
aeb311db50
Expose dither for JNI ( #2215 )
2025-05-14 23:38:25 +08:00
Fangjun Kuang
2e9e0b4e9e
Add Android demo for real-time ASR with non-streaming ASR models. ( #2214 )
2025-05-14 19:10:44 +08:00
Fangjun Kuang
0dfafed7d0
Support homophone replacer in Android asr demo. ( #2210 )
2025-05-14 10:58:35 +08:00
Fangjun Kuang
9a0e16f092
Support sending is_eof for online websocket server. ( #2204 )
...
is_final=true means an endpoint is detected.
is_eof=true means all received samples have been processed
by the server.
2025-05-13 14:49:22 +08:00
Fangjun Kuang
028b8f2718
Add C++ example for streaming ASR with SenseVoice. ( #2199 )
2025-05-11 00:23:32 +08:00
Fangjun Kuang
53518efd2f
Add real-time speech recognition example for SenseVoice. ( #2197 )
2025-05-10 00:50:40 +08:00
Fangjun Kuang
4a833a7547
Fix displaying streaming speech recognition results for Python. ( #2196 )
2025-05-09 21:48:49 +08:00
Fangjun Kuang
a6834f6556
Show verbose logs in homophone replacer ( #2194 )
2025-05-09 10:48:30 +08:00
Fangjun Kuang
562a5f7d9b
Fix building wheels for macOS ( #2192 )
2025-05-08 19:15:33 +08:00
Fangjun Kuang
f9c99032c3
Avoid NaN in feature normalization. ( #2186 )
2025-05-08 11:22:47 +08:00
Fangjun Kuang
f00066db88
Add C++ runtime for parakeet-tdt-0.6b-v2. ( #2181 )
2025-05-06 16:59:01 +08:00
Fangjun Kuang
e537094b07
Add Kotlin and Java API for homophone replacer ( #2166 )
...
* Add Kotlin API for homonphone replacer
* Add Java API for homonphone replacer
2025-04-29 22:55:21 +08:00
Fangjun Kuang
4a7a974a04
More fix for building without tts ( #2162 )
2025-04-29 16:31:31 +08:00
Fangjun Kuang
e51c37eb2f
Add C and CXX API for homophone replacer ( #2156 )
2025-04-27 22:09:13 +08:00
Fangjun Kuang
f64c58342b
Support replacing homonphonic phrases ( #2153 )
2025-04-27 15:31:11 +08:00
Fangjun Kuang
e3280027f9
Support decoding multiple streams in Java API. ( #2149 )
2025-04-25 11:18:57 +08:00
Fangjun Kuang
48ab90aadc
Fix setting OnlineModelConfig in Java API ( #2147 )
2025-04-24 16:25:36 +08:00
Fangjun Kuang
72742d5472
Fix punctuations for kokoro tts 1.1-zh. ( #2146 )
2025-04-24 15:08:47 +08:00
Karel Vesely
6a1efd8ac2
online-transducer: reset the encoder toghter with 2 previous output symbols (non-blank) ( #2129 )
...
* online-transducer: reset the encoder toghter with 2 previous output symbols (non-blank)
- added `reset_encoder` boolean member into the OnlineRecognizerConfig class
- by default the encoder is not reset
* pybind11, adding empty symbols for disabled modules (tts, diarization)
* reset_encoder, add default value (false) [pybind11]
2025-04-24 08:18:11 +08:00
Fangjun Kuang
7cbb1bc433
Upload more onnx ASR models ( #2141 )
2025-04-21 18:57:41 +08:00
Nickolay V. Shmyrev
84ed5d4288
Expose dither in python API ( #2127 )
2025-04-17 16:47:48 +08:00
Karel Vesely
f3d23aa170
cmake build, configurable from env ( #2115 )
...
- make sure the defaults in `cmake/cmake_extension.py` variable
`extra_cmake_args` can be overriden by `cmake_args` from
`SHERPA_ONNX_CMAKE_ARGS` env variable
- fix a bug in `sherpa-onnx/csrc/parse-options.cc` which appears
when using `-DSHERPA_ONNX_ENABLE_CHECK=ON`
- avoid copying binaries when these are disabled
2025-04-16 21:26:54 +08:00
Fangjun Kuang
7a78f2eb7a
Fix building for HarmonyOS ( #2125 )
2025-04-15 18:00:07 +08:00
Fangjun Kuang
e3bce847c0
Support running sherpa-onnx with RK NPU on Android ( #2124 )
2025-04-15 16:42:28 +08:00
Fangjun Kuang
1c3a383002
Fix a typo in the JNI for Android. ( #2108 )
2025-04-09 09:02:41 +08:00
Askars Salimbajevs
664b461d01
Disable strict hotword matching mode for offline transducer ( #1837 )
...
* Disable strict hotword matching mode for offline transducer. Also introduces new variable, so that later this mode can be switched on in the runtime.
* remove strict mode variable
---------
Co-authored-by: Askars Salimbajevs <askars.salimbajevs@tilde.lv >
2025-04-03 22:52:19 +08:00
Fangjun Kuang
8137ac9f0b
Add Pascal API for Dolphin CTC models ( #2096 )
2025-04-03 16:00:22 +08:00
Askars Salimbajevs
18a6ed5ddc
Preserve more context after endpointing in transducer ( #2061 )
2025-04-02 23:33:47 +08:00
Fangjun Kuang
da4aad1189
Add C and CXX API for Dolphin CTC models ( #2088 )
2025-04-02 21:54:20 +08:00
Fangjun Kuang
eee5575836
Add Kotlin and Java API for Dolphin CTC models ( #2086 )
2025-04-02 21:16:14 +08:00
Fangjun Kuang
0de7e1b9f0
Add C++ and Python API for Dolphin CTC models ( #2085 )
2025-04-02 19:09:00 +08:00
Fangjun Kuang
1316719e23
Fix building for android ( #2081 )
2025-04-01 19:36:40 +08:00
