EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Commit Graph

  • bbd7c7fc18 Add Android demo for speaker recognition (#536) Fangjun Kuang 2024-01-23 16:50:52 +08:00
  • 626775e5e2 Change model url from modelscope to github (#538) Wei Kang 2024-01-23 10:15:58 +08:00
  • b6c020901a decoder for open vocabulary keyword spotting (#505) Wei Kang 2024-01-20 22:52:41 +08:00
  • bf1dd3daf6 Refactor the UI of Android TTS engine (#533) Fangjun Kuang 2024-01-17 12:12:50 +08:00
  • 59e28518b4 Add Python API examples for speaker recognition with VAD and ASR. (#532) Fangjun Kuang 2024-01-15 21:40:30 +08:00
  • 7e0ae677c8 Add a Persian and a Slovenian model from Piper for Android TTS. (#531) Fangjun Kuang 2024-01-15 15:00:15 +08:00
  • f4e3f45664 Fix setting speaker ID for Android TTS Engine. (#530) Fangjun Kuang 2024-01-15 11:46:57 +08:00
  • 229853b77e Android TTS APKs for Persian (#529) Fangjun Kuang 2024-01-14 21:44:46 +08:00
  • 2024e96639 Add C++ runtime for speaker verification models from NeMo (#527) Fangjun Kuang 2024-01-13 21:42:09 +08:00
  • 68a525a024 Export speaker verification models from NeMo to ONNX (#526) Fangjun Kuang 2024-01-13 19:49:45 +08:00
  • afc81ec122 Add C++ runtime for models from 3d-speaker (#523) Fangjun Kuang 2024-01-11 19:10:30 +08:00
  • ec728ff7f6 Fix publishing nuget packages. (#525) Fangjun Kuang 2024-01-11 18:54:23 +08:00
  • 07e2b9a36d Support exporting models to onnx from 3D-Speaker (#522) Fangjun Kuang 2024-01-10 21:09:45 +08:00
  • 55266918c8 Add runtime support for wespeaker models (#516) Fangjun Kuang 2024-01-09 22:06:08 +08:00
  • 902b21894b Use NDK 22.1 for android build (#518) Fangjun Kuang 2024-01-05 20:34:01 +08:00
  • 0be71a31f5 Use high_freq -400 in computing fbank features. (#515) Fangjun Kuang 2024-01-04 12:39:06 +08:00
  • 547a22f7d9 Fix #510 (#513) Fangjun Kuang 2024-01-04 12:32:19 +08:00
  • e215d0c39a Fix Byte BPE string results for Python. (#512) Fangjun Kuang 2024-01-03 16:03:24 +08:00
  • d01142173a Add missing field for two-pass APK. (#511) Fangjun Kuang 2024-01-03 12:51:54 +08:00
  • 581eceb4d5 Build text-to-speech engine APKs (#509) Fangjun Kuang 2024-01-01 12:44:20 +08:00
  • d7e10bb3f8 Replace Android system TTS engine (#508) Fangjun Kuang 2023-12-31 23:02:35 +08:00
  • e475e750ac Support streaming zipformer CTC (#496) Fangjun Kuang 2023-12-22 13:46:33 +08:00
  • 7634f5f034 Release Python GIL in C++ class constructor (#493) Fangjun Kuang 2023-12-20 15:54:32 +08:00
  • ef8d112aaa Fix whisper test script for the latest onnxruntime. (#494) Fangjun Kuang 2023-12-20 11:12:12 +08:00
  • 03ff9db56e Keep multiple threads from calling into espeak-ng at the same time (#489) Fangjun Kuang 2023-12-15 17:44:33 +08:00
  • ad72e7afc3 Print informative error messages for sherpa-onnx-alsa on errors. (#486) Fangjun Kuang 2023-12-15 11:10:39 +08:00
  • 33c03f78b2 Fix CI (#485) Fangjun Kuang 2023-12-15 10:25:03 +08:00
  • 9ff6185b7c fix building linux x86 wheels (#484) Fangjun Kuang 2023-12-14 21:37:40 +08:00
  • b18812ceff Play generated audio using alsa for TTS (#482) Fangjun Kuang 2023-12-13 22:28:03 +08:00
  • 9829d7c4d3 Add two GLaDOS TTS models (#481) Fangjun Kuang 2023-12-13 15:40:07 +08:00
  • 80d0192325 Fix android tts audio buffer size and fix CI. (#478) Fangjun Kuang 2023-12-10 18:25:50 +08:00
  • 0f053d8040 Support playing as it is generating for Android (#477) Fangjun Kuang 2023-12-09 16:36:38 +08:00
  • cae0231f93 Fix releasing go packages (#476) Fangjun Kuang 2023-12-09 00:07:52 +08:00
  • aef74c5125 convert wespeaker models to sherpa-onnx (#475) Fangjun Kuang 2023-12-08 19:32:29 +08:00
  • 0e23f82691 Give an informative log for whisper on exceptions. (#473) Fangjun Kuang 2023-12-08 14:33:59 +08:00
  • 868c339e5e Support distil-small.en whisper (#472) Fangjun Kuang 2023-12-08 11:59:20 +08:00
  • 3ae984f148 Remove the 30-second constraint from whisper. (#471) Fangjun Kuang 2023-12-07 17:47:08 +08:00
  • a7d69359c9 Release v1.9.0 (#470) Fangjun Kuang 2023-12-06 19:46:50 +08:00
  • d34161413d Support Ukrainian VITS models from coqui-ai/TTS (#469) Fangjun Kuang 2023-12-06 19:37:11 +08:00
  • 23cf92daf7 Use espeak-ng for coqui-ai/TTS VITS English models. (#466) Fangjun Kuang 2023-12-06 11:00:38 +08:00
  • 3b90e85ef2 Fix building for .Net (#463) Fangjun Kuang 2023-12-04 19:27:55 +08:00
  • 73afa0248b Support playing generated audio as it is generating for MFC. (#462) Fangjun Kuang 2023-12-04 14:23:38 +08:00
  • 86b4be5260 Break text into sentences for tts. (#460) Fangjun Kuang 2023-12-03 11:50:25 +08:00
  • 99ff6a834c Play generated audio as it is generating. (#457) Fangjun Kuang 2023-12-02 15:35:11 +08:00
  • 539b27e575 Fix CI (#456) Fangjun Kuang 2023-12-01 11:00:16 +08:00
  • 62dc3c3e46 Use piper-phonemize to convert text to token IDs (#453) Fangjun Kuang 2023-11-30 23:57:43 +08:00
  • db41778e99 Support piper-phonemize (#452) Fangjun Kuang 2023-11-28 19:12:58 +08:00
  • 87a47d7db4 Release GIL to support multithreading in websocket servers. (#451) Fangjun Kuang 2023-11-27 13:44:03 +08:00
  • 8dc08a9b97 Fix nodejs on Windows (#450) Fangjun Kuang 2023-11-25 21:23:15 +08:00
  • 66cad9fa93 Fix reading tokens.txt on Windows (#448) Fangjun Kuang 2023-11-25 14:22:26 +08:00
  • 8444d54c4e Update to onnxruntime 1.16.3 (#446) Fangjun Kuang 2023-11-24 14:39:03 +08:00
  • 2a91524dbf Lock before push_back the deque for thread safety (#445) HieDean 2023-11-24 10:23:25 +08:00
  • 94ef6929bb Text-to-speech for iOS (#443) Fangjun Kuang 2023-11-23 21:38:32 +08:00
  • 2f22e6ed63 Add Swift API for TTS (#439) Fangjun Kuang 2023-11-22 16:04:26 +08:00
  • fe977b8e8e support nodejs (#438) Fangjun Kuang 2023-11-21 23:20:08 +08:00
  • 38ad05bdf8 Refactor building wheels (#436) Fangjun Kuang 2023-11-20 12:33:06 +08:00
  • e6a2d0da3b Replace Clone() with View() (#432) HieDean 2023-11-20 09:20:50 +08:00
  • ac00edab5b Build MFC examples for Windows x86 (Win32) (#434) Fangjun Kuang 2023-11-18 16:13:09 +08:00
  • 1a6a41eb2c Judge before UseCachedDecoderOut (#431) HieDean 2023-11-17 12:07:47 +08:00
  • eeda1e190e Build building for iOS (#430) Fangjun Kuang 2023-11-16 21:14:25 +08:00
  • 049fb9f451 Add Python APIs for WeNet CTC models (#428) Fangjun Kuang 2023-11-16 14:20:41 +08:00
  • fac4f6bc7c Support streaming conformer CTC models from wenet (#427) Fangjun Kuang 2023-11-16 10:35:23 +08:00
  • b83b3e3cd1 Support non-streaming WeNet CTC models. (#426) Fangjun Kuang 2023-11-15 14:23:20 +08:00
  • d34640e3a3 Add scripts to export ASR models from wenet to ONNX (#425) Fangjun Kuang 2023-11-15 11:41:15 +08:00
  • 097d641869 Resize circular buffer on overflow (#422) Fangjun Kuang 2023-11-13 12:07:51 +08:00
  • 9884cf71e7 Update onnxruntime to v1.16.2 (#421) Fangjun Kuang 2023-11-12 11:29:33 +08:00
  • 68f0e59688 Add a C++ example to show streaming VAD + non-streaming ASR. (#420) Fangjun Kuang 2023-11-11 22:54:27 +08:00
  • 3c1ea990b1 Build Android APKs for VITS models from Coqui-ai/TTS (#419) Fangjun Kuang 2023-11-11 13:27:15 +08:00
  • 47947ffae9 Fix punctuations in tts (#417) Fangjun Kuang 2023-11-10 17:09:48 +08:00
  • 61341b7187 Support VITS TTS models from coqui-ai/TTS (#416) Fangjun Kuang 2023-11-10 16:24:11 +08:00
  • ab0e830bee Release v1.8.8 (#414) Fangjun Kuang 2023-11-07 15:58:23 +08:00
  • 10d6dba187 add --tts-rule-fsts argument at offline-tts.py (#413) longshiming 2023-11-07 14:18:18 +08:00
  • a65cdc3d76 Support distil-whisper (#411) Fangjun Kuang 2023-11-06 22:33:39 +08:00
  • 86baf43c6b support reading rule FST for Android TTS (#410) Fangjun Kuang 2023-11-06 10:38:40 +08:00
  • 723e5265bb Support Chinese polyphones in TTS (#409) Fangjun Kuang 2023-11-05 13:06:00 +08:00
  • 606cb26a62 Catch exception from whisper (#408) Fangjun Kuang 2023-11-05 11:10:24 +08:00
  • d1a450bf82 Support text normalization via rule FST (#407) Fangjun Kuang 2023-11-05 08:59:03 +08:00
  • cca744e34e Update to onnxruntime v1.16.1 (#406) Fangjun Kuang 2023-11-01 16:23:31 +08:00
  • 27db015c8e Use a single static lib file for onnxruntime on Windows (#404) Fangjun Kuang 2023-10-31 21:50:56 +08:00
  • b80b7e5144 Support linking onnxruntime statically for macOS (#403) Fangjun Kuang 2023-10-31 20:24:43 +08:00
  • fabbc70633 Support static linking onnxruntime for 64-bit ARM (#402) Fangjun Kuang 2023-10-31 16:51:04 +08:00
  • 2f2d3bbd82 Support static linking onnxruntime lib for 32-bit arm (#401) Fangjun Kuang 2023-10-31 11:19:01 +08:00
  • 1544a577e0 Upload TTS APKs to huggingface (#400) Fangjun Kuang 2023-10-29 18:30:43 +08:00
  • 4115f97bf0 Add C# TTS API (#399) 木子李 2023-10-28 23:10:24 +08:00
  • 157628b257 Support French in TTS (#397) Fangjun Kuang 2023-10-28 22:22:00 +08:00
  • 64ab1ea9f8 Support Spanish in TTS (#396) Fangjun Kuang 2023-10-28 11:09:34 +08:00
  • 69e985f701 Support German umlauts in splitting UTF8 strings. (#395) Fangjun Kuang 2023-10-27 16:11:38 +08:00
  • fbf4c903e1 Support German TTS (#394) Fangjun Kuang 2023-10-27 11:12:45 +08:00
  • 93ef4ee4bc Release v1.8.6 (#391) Fangjun Kuang 2023-10-26 14:53:09 +08:00
  • 44512858d6 Support vits models from piper (#390) Fangjun Kuang 2023-10-26 14:10:24 +08:00
  • a8fed2a9ce Fix splitting words containing ', e.g., I've (#389) Fangjun Kuang 2023-10-26 13:07:30 +08:00
  • fcde4c4944 include cstdint (debian, gcc-13.2) (#388) Peter Ross 2023-10-26 11:10:48 +11:00
  • 29a5d06691 Fix utf8 spliting for English (#386) Fangjun Kuang 2023-10-25 14:55:27 +08:00
  • 6e5efa48c5 Fix splitting utf8 string into words (#385) Fangjun Kuang 2023-10-25 11:49:27 +08:00
  • 1249710e1d support specifying speed for tts Python APIs (#384) Fangjun Kuang 2023-10-24 21:38:58 +08:00
  • 789a8be73b Add Android TTS demo (#383) Fangjun Kuang 2023-10-24 21:31:28 +08:00
  • e7432cd042 Fix jni test (#382) Fangjun Kuang 2023-10-23 15:27:18 +08:00
  • 0fdb2044e1 Add jni interface and kotlin API examples for TTS. (#381) Fangjun Kuang 2023-10-23 12:31:54 +08:00
  • b582f6c115 support specifying output filename (#380) Fangjun Kuang 2023-10-21 14:43:11 +08:00
  • 1937717705 Add MFC TTS example on Windows (#378) Fangjun Kuang 2023-10-21 00:13:07 +08:00