Commit Graph

938 Commits

Author SHA1 Message Date
Fangjun Kuang
70ee779410 Support using onnxruntime 1.16.0 with CUDA 11.4 on Jetson Orin NX (Linux arm64 GPU). (#1630)
* Support using onnxruntime 1.16.0 with CUDA 11.4 on Jetson Orin NX.

The pre-built onnxruntime libs are provided by the community
using the following command:

```bash
./build.sh --build_shared_lib --config Release --update \
  --build --parallel --use_cuda \
  --cuda_home /usr/local/cuda \
  --cudnn_home /usr/lib/aarch64-linux-gnu 2>&1 | tee my-log.txt
```

See also https://github.com/microsoft/onnxruntime/discussions/11226

---

Info about the board:

```
Model: NVIDIA Orin NX T801-16GB - Jetpack 5.1.4 [L4T 35.6.0]
```

```
nvidia@nvidia-desktop:~/Downloads$ head -n 1 /etc/nv_tegra_release
# R35 (release), REVISION: 6.0, GCID: 37391689, BOARD: t186ref, EABI: aarch64, DATE: Wed Aug 28 09:12:27 UTC 2024

nvidia@nvidia-desktop:~/Downloads$ uname -r
5.10.216-tegra

nvidia@nvidia-desktop:~/Downloads$ lsb_release -i -r
Distributor ID:	Ubuntu
Release:	20.04

nvidia@nvidia-desktop:~/Downloads$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:43:33_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

nvidia@nvidia-desktop:~/Downloads$ dpkg -l libcudnn8
Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name           Version              Architecture Description
+++-==============-====================-============-=================================
ii  libcudnn8      8.6.0.166-1+cuda11.4 arm64        cuDNN runtime libraries

nvidia@nvidia-desktop:~/Downloads$ dpkg -l tensorrt
Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name           Version            Architecture Description
+++-==============-==================-============-=================================
ii  tensorrt       8.5.2.2-1+cuda11.4 arm64        Meta package for TensorRT
```
2024-12-19 18:19:53 +08:00
sawich
5cc60de5c9 Rename maxNumStences to maxNumSentences (#1625) 2024-12-16 22:37:59 +08:00
Fangjun Kuang
ed8d8e41f9 Update readme to include Open-LLM-VTuber (#1622) 2024-12-16 10:47:07 +08:00
Fangjun Kuang
e639c70d78 Support linking onnxruntime statically for Android (#1619) 2024-12-14 09:53:44 +08:00
Fangjun Kuang
efb505f578 Update AAR version in Android Java demo (#1618) 2024-12-12 20:51:57 +08:00
Fangjun Kuang
e54c1f4533 Release v1.10.35 (#1617) 2024-12-12 20:07:47 +08:00
windy
0f4b1f41e2 🔧 build(portaudio-go): Fixed version 1.0.3 (#1614)
Co-authored-by: windy <deretame123@gmail.com>
2024-12-12 19:39:43 +08:00
Fangjun Kuang
be87f866f3 Use aar in Android Java demo. (#1616) 2024-12-12 18:26:54 +08:00
Fangjun Kuang
4dc4f1a708 Provide sherpa-onnx.aar for Android (#1615) 2024-12-12 16:59:00 +08:00
Fangjun Kuang
9d4659fd29 Add missing changes about speaker identfication demo for HarmonyOS (#1612) 2024-12-11 12:01:13 +08:00
Fangjun Kuang
e011e849d4 Release v1.10.34 (#1611) 2024-12-10 20:29:33 +08:00
Fangjun Kuang
914cbad6a3 Add speaker diarization demo for HarmonyOS (#1610) 2024-12-10 20:11:44 +08:00
Fangjun Kuang
1bae4085ca Add speaker diarization API for HarmonyOS. (#1609) 2024-12-10 16:03:03 +08:00
Fangjun Kuang
14944d8c81 Add speaker identification demo for HarmonyOS (#1608) 2024-12-10 14:50:13 +08:00
Fangjun Kuang
314545f938 Add speaker identification APIs for HarmonyOS (#1607)
* Add speaker embedding extractor API for HarmonyOS

* Add ArkTS API for speaker identification
2024-12-09 19:23:18 +08:00
Fangjun Kuang
a743a4400f Add on-device real-time ASR demo for HarmonyOS (#1606) 2024-12-09 16:40:15 +08:00
Fangjun Kuang
91a43cccff Update doc links for HarmonyOS (#1601) 2024-12-06 17:38:40 +08:00
Fangjun Kuang
84821b1f99 Fix building node-addon package (#1598) 2024-12-06 10:11:18 +08:00
Fangjun Kuang
9352ccf7d5 Release v1.10.33 (#1591) 2024-12-04 14:51:46 +08:00
Fangjun Kuang
74a8735f7a Add on-device tex-to-speech (TTS) demo for HarmonyOS (#1590) 2024-12-04 14:27:12 +08:00
goddamnVincent
47a2dd4cf8 'update20241203' (#1589)
add '--modeling-unit' and "--bpe-vocab" to /sherpa-onnx/python-api-examples/streaming_server.py make it specifiable.
2024-12-04 09:22:24 +08:00
JiayuXu
0d6bf52844 fix: support both old and new websockets request headers format (#1588)
Co-authored-by: xujiayu <xujiayu@kaihong.com>
2024-12-03 17:22:12 +08:00
Fangjun Kuang
dc3287f3a8 Add HarmonyOS support for text-to-speech. (#1584) 2024-12-01 21:43:34 +08:00
Fangjun Kuang
a3d6e1acc7 Fix getting microphone permission for HarmonyOS VAD+ASR example (#1582) 2024-11-30 16:24:22 +08:00
Fangjun Kuang
c9d3b6cd8c Add microphone demo about VAD+ASR for HarmonyOS (#1581) 2024-11-30 15:23:45 +08:00
Fangjun Kuang
299f2392e2 Add CI to build HAPs for HarmonyOS (#1578) 2024-11-29 21:13:01 +08:00
Fangjun Kuang
be159f943e Fix publishing har packages for HarmonyOS (#1576) 2024-11-29 12:20:12 +08:00
Fangjun Kuang
f3f8961462 Add VAD+ASR demo for HarmonyOS (#1573) 2024-11-28 22:59:56 +08:00
Fangjun Kuang
315d8e2a47 Publish sherpa_onnx.har for HarmonyOS (#1572) 2024-11-28 17:30:16 +08:00
Fangjun Kuang
109fb799ca fix building for Android (#1568) 2024-11-27 10:36:16 +08:00
Fangjun Kuang
2101227269 Add streaming ASR support for HarmonyOS. (#1565) 2024-11-26 18:36:56 +08:00
Fangjun Kuang
298b6b6fda Add non-streaming ASR support for HarmonyOS. (#1564) 2024-11-26 16:38:35 +08:00
Fangjun Kuang
a4b79f077c Fix flutter ios (#1563) 2024-11-26 13:45:15 +08:00
Fangjun Kuang
31d6206fde HarmonyOS support for VAD. (#1561) 2024-11-24 16:29:24 +08:00
Fangjun Kuang
e424cc9e0d Support cross-compiling for HarmonyOS (#1553) 2024-11-20 10:06:49 +08:00
Fangjun Kuang
9a48012648 Use xcframework for Flutter iOS plugin. (#1547) 2024-11-16 16:42:02 +08:00
Anders Xiao
e993c08538 fix windows build (#1546) 2024-11-16 11:57:10 +08:00
Fangjun Kuang
b28b0c81b1 Support static build for windows arm64. (#1539) 2024-11-15 16:06:17 +08:00
Fangjun Kuang
c34ab35591 Add Android APK for streaming Paraformer ASR (#1538) 2024-11-14 20:57:35 +08:00
Fangjun Kuang
8436ba834c Add WebAssembly example for VAD + Moonshine models. (#1535) 2024-11-13 21:06:50 +08:00
Aero
3f777b3fe3 Add isolate_tts demo (#1529) 2024-11-13 00:04:57 +08:00
Fangjun Kuang
a16c9aff8b Add Lazarus example for Moonshine models. (#1532) 2024-11-13 00:04:16 +08:00
VEP
4fab3f2e2f Revert: [#1521] No need to reset sample-buffer (#1524)
Co-authored-by: VEP <517138883@qq.com>
2024-11-08 21:28:04 +08:00
Fangjun Kuang
f97daed408 Fixes #1512 (#1522) 2024-11-08 21:07:36 +08:00
VEP
f94cca71cf Fix: Reset sample-buffer after processing (#1521)
Co-authored-by: VEP <517138883@qq.com>
2024-11-08 19:04:34 +08:00
張小凡
86b1856c20 Reduce vad-sense-voice example code. (#1510) 2024-11-05 20:34:12 +08:00
Fangjun Kuang
4eeb336f59 Export the English TTS model from MeloTTS (#1509) 2024-11-04 07:54:19 +08:00
Fangjun Kuang
6ee8c99c5d Fix building (#1508) 2024-11-03 19:47:04 +08:00
Fangjun Kuang
f0cced1f37 Publish pre-built wheels with CUDA support for Linux aarch64. (#1507) 2024-11-03 19:15:11 +08:00
Fangjun Kuang
c5205f08bf Add an example for computing RTF about streaming ASR. (#1501) 2024-11-01 11:40:13 +08:00