Commit Graph

  • 3d3edabb5f Add Go API for Moonshine models (#1479) Fangjun Kuang 2024-10-27 09:39:09 +08:00
  • 052b8645ba Add Go API examples for adding punctuations to text. (#1478) Fangjun Kuang 2024-10-27 09:04:05 +08:00
  • 4a4659aa4f Add Swift API for Moonshine models. (#1477) Fangjun Kuang 2024-10-27 08:19:01 +08:00
  • 2ca2985d04 Add C and C++ API for Moonshine models (#1476) Fangjun Kuang 2024-10-26 23:24:46 +08:00
  • bd4b223920 Add Kotlin and Java API for Moonshine models (#1474) Fangjun Kuang 2024-10-26 22:30:29 +08:00
  • 669f5ef441 Add C++ runtime and Python APIs for Moonshine models (#1473) Fangjun Kuang 2024-10-26 14:34:07 +08:00
  • 0f2732e4e8 Publish pre-built JNI libs for Linux aarch64 (#1472) Fangjun Kuang 2024-10-26 09:59:18 +08:00
  • b06b460851 Begin to support https://github.com/usefulsensors/moonshine (#1470) Fangjun Kuang 2024-10-26 09:51:16 +08:00
  • 3d6344ead3 Fix building node-addon for Windows x86. (#1469) Fangjun Kuang 2024-10-25 18:49:33 +08:00
  • d5a2f52413 Release v1.10.29 (#1468) Fangjun Kuang 2024-10-25 15:50:42 +08:00
  • 707cf792c5 Add GigaAM NeMo transducer model for Russian ASR (#1467) Fangjun Kuang 2024-10-25 15:20:13 +08:00
  • b41f6d2c94 Support GigaAM CTC models for Russian ASR (#1464) Fangjun Kuang 2024-10-25 10:55:16 +08:00
  • 2b40079faf Add speaker identification with VAD and non-streaming ASR using ALSA (#1463) Peakyxh 2024-10-24 22:04:51 +08:00
  • a5295aad10 Handle NaN embeddings in speaker diarization. (#1461) Fangjun Kuang 2024-10-24 14:03:09 +08:00
  • b3e05f6dc4 Fix style issues (#1458) Fangjun Kuang 2024-10-24 11:15:08 +08:00
  • ceb69ebd94 Add C++ API for non-streaming ASR (#1456) Fangjun Kuang 2024-10-23 16:40:12 +08:00
  • effd5ef2be Add C++ API for streaming ASR. (#1455) Fangjun Kuang 2024-10-23 12:07:43 +08:00
  • 3edd8d7cf6 add java android demo (#1454) JameWade 2024-10-23 11:38:26 +08:00
  • bcaa91ed36 update java for hotword jar (#1444) YeyuchenBa 2024-10-18 18:07:51 +08:00
  • 1af8ad89e6 Add Java API example for hotwords. (#1442) Fangjun Kuang 2024-10-18 16:35:31 +08:00
  • e0586f1876 add more models for speaker diarization (#1440) Fangjun Kuang 2024-10-17 20:03:09 +08:00
  • 4783c8f590 fix "log10" compile error by import CMATH lib (#1438) Zazzle516 2024-10-17 14:50:04 +08:00
  • 620597f501 Support https://huggingface.co/Revai/reverb-diarization-v1 (#1437) Fangjun Kuang 2024-10-17 11:58:14 +08:00
  • 471cbd83c6 updated onnxruntime-linux-aarch64.cmake so that libonnxruntime.so can be found for specific aarch64 cross-compilation environments (#1436) lxiao336 2024-10-16 22:42:42 +08:00
  • 593b96758b Add Go API for offline punctuation models (#1434) Fangjun Kuang 2024-10-16 17:16:47 +08:00
  • 77dd5f73fc Update README.md (#1431) semxum 2024-10-14 18:25:27 +08:00
  • df4150dc5d Upload speaker embedding models to huggingface (#1428) Fangjun Kuang 2024-10-14 16:20:00 +08:00
  • 99f320b893 Release v1.10.28 (#1424) Fangjun Kuang 2024-10-13 15:27:38 +08:00
  • 5a22f74b2b Android demo for speaker diarization (#1423) Fangjun Kuang 2024-10-13 14:02:57 +08:00
  • 94b26ff07c Android JNI support for speaker diarization (#1421) Fangjun Kuang 2024-10-12 13:03:48 +08:00
  • 5e273c5be4 Pascal API for speaker diarization (#1420) Fangjun Kuang 2024-10-12 12:28:38 +08:00
  • 1ed803adc1 Dart API for speaker diarization (#1418) Fangjun Kuang 2024-10-11 21:17:41 +08:00
  • 1851ff6337 Java API for speaker diarization (#1416) Fangjun Kuang 2024-10-11 16:51:40 +08:00
  • 2d412b1190 Kotlin API for speaker diarization (#1415) Fangjun Kuang 2024-10-11 14:41:53 +08:00
  • eefc172095 JavaScript API with WebAssembly for speaker diarization (#1414) Fangjun Kuang 2024-10-11 11:40:10 +08:00
  • f1b311ee4f Handle audio files less than 10s long for speaker diarization. (#1412) Fangjun Kuang 2024-10-11 10:27:16 +08:00
  • 1d061df355 WebAssembly exmaple for speaker diarization (#1411) Fangjun Kuang 2024-10-10 22:14:45 +08:00
  • 67349b52f2 JavaScript API (node-addon) for speaker diarization (#1408) Fangjun Kuang 2024-10-10 15:51:31 +08:00
  • a45e5dba99 C# API for speaker diarization (#1407) Fangjun Kuang 2024-10-10 14:29:05 +08:00
  • bd50e79590 Update readme to include more external projects using sherpa-onnx (#1405) Fangjun Kuang 2024-10-10 10:27:14 +08:00
  • 1571344509 Swift API for speaker diarization (#1404) Fangjun Kuang 2024-10-09 23:25:39 +08:00
  • df681e9807 Go API for speaker diarization (#1403) Fangjun Kuang 2024-10-09 20:10:44 +08:00
  • 97654122fa docs(nodejs-addon-examples): add guide for pnpm user (#1401) Yongzeng Liu 2024-10-09 18:12:41 +08:00
  • d468527f62 C API for speaker diarization (#1402) Fangjun Kuang 2024-10-09 17:10:03 +08:00
  • 8535b1d3bb Python API for speaker diarization. (#1400) Fangjun Kuang 2024-10-09 14:13:26 +08:00
  • 59407edcad C++ API for speaker diarization (#1396) Fangjun Kuang 2024-10-09 12:01:20 +08:00
  • 70165cb42d Speaker diarization example with onnxruntime Python API (#1395) Fangjun Kuang 2024-10-06 16:37:29 +08:00
  • 5f50cbf65a context_state is not set correctly when previous context is passed after reset (#1393) Askars 2024-10-03 11:42:09 +03:00
  • 66feecb2b5 support whisper turbo (#1390) Fangjun Kuang 2024-10-02 18:13:34 +08:00
  • b965f14cf0 Add Python API for clustering (#1385) Fangjun Kuang 2024-09-30 11:33:15 +08:00
  • 70568c2df7 Support Agglomerative clustering. (#1384) Fangjun Kuang 2024-09-29 23:44:29 +08:00
  • bc08160820 Export Pyannote speaker segmentation models to onnx (#1382) Fangjun Kuang 2024-09-29 14:23:56 +08:00
  • 11f0cb7e1c Support Parakeet models from NeMo (#1381) Fangjun Kuang 2024-09-27 17:12:00 +08:00
  • 12d04ce8ed Fix running MeloTTS models on GPU. (#1379) Fangjun Kuang 2024-09-26 16:51:43 +08:00
  • 69c8e7b9d0 Update online_model.dart (#1375) Flutter Painter 2024-09-25 00:40:22 +02:00
  • d8809b520e Fix CI errors introduced by supporting loading keywords from buffers (#1366) Fangjun Kuang 2024-09-20 19:04:21 +08:00
  • 06b61ccad8 Allow more online models to load tokens file from the memory (#1352) lxiao336 2024-09-20 16:38:41 +08:00
  • 73c90ec871 Fix swift example for generating subtitles. (#1362) Fangjun Kuang 2024-09-20 11:44:25 +08:00
  • 647b63ea44 Release v1.10.27 (#1359) Fangjun Kuang 2024-09-19 10:49:29 +08:00
  • 576a3aa90d Add non-streaming ONNX models for Russian ASR (#1358) Fangjun Kuang 2024-09-18 13:43:49 +08:00
  • 7e642325f3 Fix building Flutter TTS examples for Linux (#1356) Fangjun Kuang 2024-09-18 12:04:02 +08:00
  • cddac52780 Support passing utf-8 strings from JavaScript to C++. (#1355) Fangjun Kuang 2024-09-18 11:03:42 +08:00
  • bf06b268d0 Fix sherpa_onnx.go (#1353) lllwan 2024-09-17 13:39:56 +08:00
  • 9dade25d3e Release v1.10.26 (#1350) Fangjun Kuang 2024-09-14 14:37:42 +08:00
  • e7ffcbd677 Add APIs about max speech duration in VAD for various programming languages (#1349) Fangjun Kuang 2024-09-14 12:30:13 +08:00
  • 1423ddb1f0 Support specifying max speech duration for VAD. (#1348) Fangjun Kuang 2024-09-14 10:57:46 +08:00
  • 5d761712db Support lang/emotion/event results from SenseVoice in Swift API. (#1346) Fangjun Kuang 2024-09-13 19:43:46 +08:00
  • 6bf9310cb4 Add links to projects using sherpa-onnx. (#1345) Fangjun Kuang 2024-09-13 19:17:08 +08:00
  • 211786e798 Release v1.10.25 (#1344) Fangjun Kuang 2024-09-13 14:58:38 +08:00
  • 544857b097 Fix building (#1343) Fangjun Kuang 2024-09-13 13:33:52 +08:00
  • 65cfa7548a re-pull-request allow tokens and hotwords be loaded from buffered string driectly (#1339) lxiao336 2024-09-13 09:58:17 +08:00
  • 6b6e7635ed Fix computing features for CED audio tagging models. (#1341) Fangjun Kuang 2024-09-12 19:38:18 +08:00
  • fa20ae1552 Preserve previous result as context for next segment (#1335) Askars 2024-09-11 05:44:13 +03:00
  • ba7f1a7439 Fix building (#1331) Fangjun Kuang 2024-09-09 10:29:31 +08:00
  • 3bffc24d64 Add Python binding for online punctuation models (#1312) Lim Yao Chong 2024-09-09 10:26:53 +08:00
  • 857cb5075c Fix typos (#1330) Fangjun Kuang 2024-09-09 10:22:42 +08:00
  • 363b8e4c1e Fix vad.Flush(). (#1329) Fangjun Kuang 2024-09-08 17:52:53 +08:00
  • 1977c8d04d fix wasm app for streaming paraformer (#1328) Fangjun Kuang 2024-09-08 17:49:19 +08:00
  • ae2bc17168 Build websocket related binaries for embedded systems. (#1327) Fangjun Kuang 2024-09-08 17:16:58 +08:00
  • b409b0a958 Fixed the C api calls and created the TTS project file (#1324) Michael Twohey 2024-09-07 08:25:02 -07:00
  • 888f74bf3c Re-implement LM rescore for online transducer (#1231) SilverSulfide 2024-09-06 05:01:25 +03:00
  • 1f29e4a1a9 throw error instead exit (#1323) RGdevz 2024-09-06 04:59:21 +03:00
  • e66d4c414a Fix releasing dart packages. (#1317) Fangjun Kuang 2024-09-04 12:12:13 +08:00
  • cc462316db Release v1.10.24 (#1309) Fangjun Kuang 2024-08-30 17:27:08 +08:00
  • d60a4d418e Provide prebuilt .jar files for different java versions. (#1307) Fangjun Kuang 2024-08-30 14:16:31 +08:00
  • 3687c9f60a Reduce onnxruntime log output. (#1306) Fangjun Kuang 2024-08-30 12:50:34 +08:00
  • 6b8877f185 Downgrade flutter sdk versions. (#1305) Fangjun Kuang 2024-08-30 11:47:27 +08:00
  • c38634dfcf two-pass Android APK for SenseVoice (#1302) Fangjun Kuang 2024-08-29 12:08:49 +08:00
  • 0ccd3a4c3f remove extra files from linux/macos/windows jni libs (#1301) Fangjun Kuang 2024-08-29 10:45:38 +08:00
  • 9064430c3e Fix releasing wasm app for vad+asr (#1300) Fangjun Kuang 2024-08-29 08:47:38 +08:00
  • ca30d83915 Avoid SherpaOnnxSpeakerEmbeddingManagerFreeBestMatches freeing null. (#1296) Fangjun Kuang 2024-08-28 10:42:36 +08:00
  • 22c6f81393 Fix VAD+ASR example for Dart API. (#1294) Fangjun Kuang 2024-08-27 22:15:50 +08:00
  • a2a70900d6 ADD VAD+ASR example for dart with CircularBuffer. (#1293) Fangjun Kuang 2024-08-27 19:29:34 +08:00
  • 6ec57327ce add vad+sense voice example for C API (#1291) Fangjun Kuang 2024-08-27 16:11:24 +08:00
  • a8556e31ba add Tokens []string, Timestamps []float32, Lang string, Emotion string, Event string (#1277) Emmanuel Schmidbauer 2024-08-26 18:35:59 -04:00
  • 17c8237ee4 Fix releasing npm package and fix building Android VAD+ASR example (#1288) Fangjun Kuang 2024-08-26 10:18:48 +08:00
  • 452555b218 update generate-asset-list.py (#1287) Hán Trung Kiên 2024-08-25 07:57:16 +07:00
  • 5ed8e31868 Add VAD and keyword spotting for the Node package with WebAssembly (#1286) Fangjun Kuang 2024-08-24 23:05:54 +08:00
  • 537e163dd0 WebAssembly example for VAD + Non-streaming ASR (#1284) Fangjun Kuang 2024-08-24 13:24:52 +08:00
  • 1ef8a7a202 Add WebAssembly for VAD (#1281) Fangjun Kuang 2024-08-23 17:08:37 +08:00