Commit Graph

296 Commits

Author SHA1 Message Date
Fangjun Kuang
cd1fedaa49 Add Dart API for audio tagging (#1181) 2024-07-29 11:15:14 +08:00
Fangjun Kuang
69b6b47d91 Add vad with non-streaming ASR examples for Dart API (#1180) 2024-07-28 23:01:03 +08:00
Fangjun Kuang
d279c8d20e Add more Python examples for SenseVoice (#1179) 2024-07-28 21:54:38 +08:00
Fangjun Kuang
994c3e7c96 Add VAD + Non-streaming ASR example for JavaScript API. (#1170) 2024-07-26 12:42:08 +08:00
Fangjun Kuang
ea1d81bdfe C api example for sense voice (#1165) 2024-07-22 16:54:00 +08:00
Fangjun Kuang
dd300b1de5 Add Java and Kotlin API for sense voice (#1164) 2024-07-22 14:08:40 +08:00
Fangjun Kuang
ac8223bd8a Add Dart API for keyword spotter (#1162) 2024-07-22 10:53:34 +08:00
Fangjun Kuang
ffdb23a8ec Add dart API for SenseVoice (#1159) 2024-07-21 21:48:12 +08:00
Fangjun Kuang
70d14353bb Add WebAssembly for SenseVoice (#1158) 2024-07-21 15:39:55 +08:00
Fangjun Kuang
c3260ef842 Add JavaScript API for SenseVoice (#1157) 2024-07-21 10:14:14 +08:00
Fangjun Kuang
8f4d332aab Add Go API for SenseVoice (#1154) 2024-07-20 23:41:53 +08:00
Fangjun Kuang
e472180f2c Add C# API for SenseVoice models (#1151) 2024-07-20 17:09:23 +08:00
Fangjun Kuang
25f0a10468 Add C++ runtime for SenseVoice models (#1148) 2024-07-18 22:54:18 +08:00
Fangjun Kuang
346f419f39 export sense-voice to onnx (#1144) 2024-07-18 00:18:38 +08:00
Fangjun Kuang
4198d9a166 Provide pre-built wheels with CUDA support. (#1143) 2024-07-17 22:59:13 +08:00
Fangjun Kuang
803c02db0a publish all pre-built wheels to huggingface (#1142)
pypi.org provides only 10GB of free space for open-source projects.

Each new release of sherpa-onnx occupies about 800MB, so we have to delete previous releases otherwise pypi.org refuses to accept new releases due to limited spaces.

To let users install previous versions, we also publish wheels to huggingface and users can find them at

https://k2-fsa.github.io/sherpa/onnx/cpu.html
and
https://k2-fsa.github.io/sherpa/onnx/cpu-cn.html (for users without access to huggingface.co)
2024-07-17 14:41:27 +08:00
Fangjun Kuang
9e448d03bc Provide npm package for 32-bit Windows x86 (#1141) 2024-07-17 12:33:15 +08:00
Fangjun Kuang
960eb7529e Add C++ runtime for MeloTTS (#1138) 2024-07-16 15:55:02 +08:00
Fangjun Kuang
95485411fa Support English for MeloTTS models. (#1134) 2024-07-15 19:49:22 +08:00
Fangjun Kuang
b2c283fa2b Add Swift API for adding punctuations to text. (#1132) 2024-07-15 15:30:40 +08:00
Fangjun Kuang
c35200dccf Revert to onnxruntime 1.17.1 (#1131) 2024-07-15 14:24:08 +08:00
Fangjun Kuang
04c2319c2c Export MeloTTS to ONNX (#1129) 2024-07-15 10:47:19 +08:00
Fangjun Kuang
ab71c3976d Add int8 quantized whisper large models (#1126) 2024-07-13 22:30:06 +08:00
Fangjun Kuang
3951a12f8d Add pre-trained models for the Libriheavy dataset (#1122) 2024-07-13 19:21:13 +08:00
Fangjun Kuang
b5093e27f9 Fix publishing apks to huggingface (#1121)
Save APKs for each release in a separate directory.

Huggingface requires that each directory cannot contain more than 1000 files.

Since we have so many tts models and for each model we need to build APKs of 4 different ABIs,
it is a workaround for the huggingface's constraint by placing them into separate directories for different releases.
2024-07-13 16:14:00 +08:00
Fangjun Kuang
117cd7bb8c Support whisper large/large-v1/large-v2/large-v3 and distil-large-v2 (#1114) 2024-07-12 23:47:39 +08:00
Fangjun Kuang
1c104ea847 Update onnxruntime from v1.18.0 to v1.18.1 (#1107) 2024-07-11 09:35:28 +08:00
Fangjun Kuang
08c758520f Add keyword spotting for C# (#1105) 2024-07-10 21:18:46 +08:00
Fangjun Kuang
dd0ff2ca06 Support onnxruntime 1.18.0 (#906) 2024-07-10 17:05:26 +08:00
Fangjun Kuang
9e446b8501 Fix typos (#1101) 2024-07-09 20:08:47 +08:00
Fangjun Kuang
c2cc9dec58 Add Flush to VAD so that the last segment can be detected. (#1099) 2024-07-09 16:15:56 +08:00
Fangjun Kuang
e832d356c7 Add Flutter text to speech demo (#1087) 2024-07-08 11:23:11 +08:00
Fangjun Kuang
1fe12c5107 Support the platform iOS for Flutter (#1079) 2024-07-06 19:43:37 +08:00
Fangjun Kuang
a25075101c Build sherpa-onnx as a single shared library (#1078)
When `-D BUILD_SHARED_LIBS=ON` is passed to `cmake`, it builds a single shared library.

Specifically, 

- For C APIs, it builds `libsherpa-onnx-c-api.so`
- For Python APIs, it builds `_sherpa_onnx.cpython-xx-xx.so`
- For Kotlin and Java APIs, it builds `libsherpa-onnx-jni.so`

There is no `libsherpa-onnx-core.so` any longer.

Note it affects only shared libraries.
2024-07-06 16:41:54 +08:00
Fangjun Kuang
f5e9a162d1 Publish flutter packages for Android (#1074) 2024-07-04 20:07:07 +08:00
Fangjun Kuang
b502116068 Refactor flutter to support Android (#1072) 2024-07-04 10:49:09 +08:00
Fangjun Kuang
125bb9ff99 replace macos-11 with macos-13 for GitHub actions (#1066)
Tests using macos-11 wait a long time before they can start, so we replace macos-11 with macos-13.
2024-07-01 12:37:56 +08:00
Fangjun Kuang
598c12c4e5 Fix CI tests (#1061) 2024-06-27 18:05:18 +08:00
Fangjun Kuang
2f8c489698 Publish pre-built jni libs for windows and osx (#1056) 2024-06-25 11:59:04 +08:00
Fangjun Kuang
5cce159cf3 Fix passing C# string to C++ (#1055) 2024-06-25 10:52:59 +08:00
Fangjun Kuang
a3bac19c54 fix a bug for wenet streaming model. (#1054)
* fix a bug for wenet streaming model.

The chunk shift was wrong.
See
https://github.com/wenet-e2e/wenet/blob/main/runtime/core/decoder/asr_model.cc#L15
and
https://github.com/wenet-e2e/wenet/blob/main/runtime/core/decoder/asr_model.cc#L28
2024-06-24 21:52:54 +08:00
Fangjun Kuang
e7a45108ac Remove unused files from .Net examples (#1051) 2024-06-24 10:25:14 +08:00
东风破
00de2bd00b Refactor .Net example project (#1049)
Co-authored-by: 东风破 <birdfishs@163.com>
2024-06-24 10:10:13 +08:00
Fangjun Kuang
6b7ced2317 Fix the alsa-lib version to v1.2.12 (#1048) 2024-06-23 20:20:38 +08:00
Fangjun Kuang
169c9bf627 Flutter demo for real-time speech recognition (#1042) 2024-06-23 13:29:13 +08:00
Fangjun Kuang
a11c859971 Support clang-tidy (#1034) 2024-06-19 20:51:57 +08:00
Fangjun Kuang
ab21131f7f Swift API for keyword spotting. (#1027) 2024-06-18 16:51:30 +08:00
Fangjun Kuang
0be7f28853 build pre-compiled libs for jni (linux x64) (#1026) 2024-06-18 16:50:04 +08:00
Fangjun Kuang
6789c909d2 Inverse text normalization API of streaming ASR for various programming languages (#1022) 2024-06-18 13:42:17 +08:00
Fangjun Kuang
349d957da2 Add inverse text normalization for online ASR (#1020) 2024-06-17 18:39:23 +08:00