Commit Graph

823 Commits

Author SHA1 Message Date
Fangjun Kuang
bc08160820 Export Pyannote speaker segmentation models to onnx (#1382) 2024-09-29 14:23:56 +08:00
Fangjun Kuang
11f0cb7e1c Support Parakeet models from NeMo (#1381) 2024-09-27 17:12:00 +08:00
Fangjun Kuang
12d04ce8ed Fix running MeloTTS models on GPU. (#1379)
We need to use opset 18 to export the model to onnx.
2024-09-26 16:51:43 +08:00
Flutter Painter
69c8e7b9d0 Update online_model.dart (#1375)
fix typo on french joiner file
2024-09-25 06:40:22 +08:00
Fangjun Kuang
d8809b520e Fix CI errors introduced by supporting loading keywords from buffers (#1366) 2024-09-20 19:04:21 +08:00
lxiao336
06b61ccad8 Allow more online models to load tokens file from the memory (#1352)
Co-authored-by: xiao <shawl336@6163.com>
2024-09-20 16:38:41 +08:00
Fangjun Kuang
73c90ec871 Fix swift example for generating subtitles. (#1362)
We need to invoke vad.flush() at the end.
2024-09-20 11:44:25 +08:00
Fangjun Kuang
647b63ea44 Release v1.10.27 (#1359) 2024-09-19 10:49:29 +08:00
Fangjun Kuang
576a3aa90d Add non-streaming ONNX models for Russian ASR (#1358) 2024-09-18 13:43:49 +08:00
Fangjun Kuang
7e642325f3 Fix building Flutter TTS examples for Linux (#1356) 2024-09-18 12:04:02 +08:00
Fangjun Kuang
cddac52780 Support passing utf-8 strings from JavaScript to C++. (#1355)
We first convert utf-16 strings to Uint8Array and then we
pass the array to C++.
2024-09-18 11:03:42 +08:00
lllwan
bf06b268d0 Fix sherpa_onnx.go (#1353) 2024-09-17 13:39:56 +08:00
Fangjun Kuang
9dade25d3e Release v1.10.26 (#1350) 2024-09-14 14:37:42 +08:00
Fangjun Kuang
e7ffcbd677 Add APIs about max speech duration in VAD for various programming languages (#1349) 2024-09-14 12:30:13 +08:00
Fangjun Kuang
1423ddb1f0 Support specifying max speech duration for VAD. (#1348) 2024-09-14 10:57:46 +08:00
Fangjun Kuang
5d761712db Support lang/emotion/event results from SenseVoice in Swift API. (#1346) 2024-09-13 19:43:46 +08:00
Fangjun Kuang
6bf9310cb4 Add links to projects using sherpa-onnx. (#1345) 2024-09-13 19:17:08 +08:00
Fangjun Kuang
211786e798 Release v1.10.25 (#1344) 2024-09-13 14:58:38 +08:00
Fangjun Kuang
544857b097 Fix building (#1343) 2024-09-13 13:33:52 +08:00
lxiao336
65cfa7548a re-pull-request allow tokens and hotwords be loaded from buffered string driectly (#1339)
Co-authored-by: xiao <shawl336@163.com>
2024-09-13 09:58:17 +08:00
Fangjun Kuang
6b6e7635ed Fix computing features for CED audio tagging models. (#1341)
See also
https://github.com/RicherMans/CED/blob/main/onnx_inference_with_kaldi.py
2024-09-12 19:38:18 +08:00
Askars
fa20ae1552 Preserve previous result as context for next segment (#1335)
Co-authored-by: vsd-vector <askars.salimbajevs@tilde.lv>
2024-09-11 10:44:13 +08:00
Fangjun Kuang
ba7f1a7439 Fix building (#1331) 2024-09-09 10:29:31 +08:00
Lim Yao Chong
3bffc24d64 Add Python binding for online punctuation models (#1312) 2024-09-09 10:26:53 +08:00
Fangjun Kuang
857cb5075c Fix typos (#1330) 2024-09-09 10:22:42 +08:00
Fangjun Kuang
363b8e4c1e Fix vad.Flush(). (#1329)
Fixes #1314
2024-09-08 17:52:53 +08:00
Fangjun Kuang
1977c8d04d fix wasm app for streaming paraformer (#1328) 2024-09-08 17:49:19 +08:00
Fangjun Kuang
ae2bc17168 Build websocket related binaries for embedded systems. (#1327) 2024-09-08 17:16:58 +08:00
Michael Twohey
b409b0a958 Fixed the C api calls and created the TTS project file (#1324)
Co-authored-by: Michael Twohey <mtwohey@americanambulance.com>
2024-09-07 23:25:02 +08:00
SilverSulfide
888f74bf3c Re-implement LM rescore for online transducer (#1231)
Co-authored-by: Martins Kronis <martins.kuznecovs@tilde.lv>
2024-09-06 10:01:25 +08:00
RGdevz
1f29e4a1a9 throw error instead exit (#1323) 2024-09-06 09:59:21 +08:00
Fangjun Kuang
e66d4c414a Fix releasing dart packages. (#1317) 2024-09-04 12:12:13 +08:00
Fangjun Kuang
cc462316db Release v1.10.24 (#1309) 2024-08-30 17:27:08 +08:00
Fangjun Kuang
d60a4d418e Provide prebuilt .jar files for different java versions. (#1307) 2024-08-30 14:16:31 +08:00
Fangjun Kuang
3687c9f60a Reduce onnxruntime log output. (#1306)
Change the logging level from WARNING to ERROR.
2024-08-30 12:50:34 +08:00
Fangjun Kuang
6b8877f185 Downgrade flutter sdk versions. (#1305) 2024-08-30 11:47:27 +08:00
Fangjun Kuang
c38634dfcf two-pass Android APK for SenseVoice (#1302) 2024-08-29 12:08:49 +08:00
Fangjun Kuang
0ccd3a4c3f remove extra files from linux/macos/windows jni libs (#1301) 2024-08-29 10:45:38 +08:00
Fangjun Kuang
9064430c3e Fix releasing wasm app for vad+asr (#1300) 2024-08-29 08:47:38 +08:00
Fangjun Kuang
ca30d83915 Avoid SherpaOnnxSpeakerEmbeddingManagerFreeBestMatches freeing null. (#1296)
Fixes #1295
2024-08-28 10:42:36 +08:00
Fangjun Kuang
22c6f81393 Fix VAD+ASR example for Dart API. (#1294)
There is no need to invoke vad.isDetected().
2024-08-27 22:15:50 +08:00
Fangjun Kuang
a2a70900d6 ADD VAD+ASR example for dart with CircularBuffer. (#1293) 2024-08-27 19:29:34 +08:00
Fangjun Kuang
6ec57327ce add vad+sense voice example for C API (#1291) 2024-08-27 16:11:24 +08:00
Emmanuel Schmidbauer
a8556e31ba add Tokens []string, Timestamps []float32, Lang string, Emotion string, Event string (#1277) 2024-08-27 06:35:59 +08:00
Fangjun Kuang
17c8237ee4 Fix releasing npm package and fix building Android VAD+ASR example (#1288) 2024-08-26 10:18:48 +08:00
Hán Trung Kiên
452555b218 update generate-asset-list.py (#1287) 2024-08-25 08:57:16 +08:00
Fangjun Kuang
5ed8e31868 Add VAD and keyword spotting for the Node package with WebAssembly (#1286) 2024-08-24 23:05:54 +08:00
Fangjun Kuang
537e163dd0 WebAssembly example for VAD + Non-streaming ASR (#1284) 2024-08-24 13:24:52 +08:00
Fangjun Kuang
1ef8a7a202 Add WebAssembly for VAD (#1281) 2024-08-23 17:08:37 +08:00
Fangjun Kuang
fb09f8fae3 Set batch size to 1 for more streaming ASR models (#1280) 2024-08-23 11:06:55 +08:00