Commit Graph

350 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
Fangjun Kuang
e639c70d78 Support linking onnxruntime statically for Android (#1619) 2024-12-14 09:53:44 +08:00
Fangjun Kuang
4dc4f1a708 Provide sherpa-onnx.aar for Android (#1615) 2024-12-12 16:59:00 +08:00
Fangjun Kuang
dc3287f3a8 Add HarmonyOS support for text-to-speech. (#1584) 2024-12-01 21:43:34 +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
315d8e2a47 Publish sherpa_onnx.har for HarmonyOS (#1572) 2024-11-28 17:30:16 +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
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
f97daed408 Fixes #1512 (#1522) 2024-11-08 21:07:36 +08:00
Fangjun Kuang
4eeb336f59 Export the English TTS model from MeloTTS (#1509) 2024-11-04 07:54:19 +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
9ab89c33bc Support building GPU-capable sherpa-onnx on Linux aarch64. (#1500)
Thanks to @Peakyxh for providing pre-built onnxruntime libraries 
with CUDA support for Linux aarch64.

Tested on Jetson nano b01
2024-11-01 11:16:28 +08:00
Fangjun Kuang
a3c89aa0d8 Add two-pass ASR Android APKs for Moonshine models. (#1499) 2024-10-31 17:54:16 +08:00
Fangjun Kuang
356da3b54c Publish pre-built macos xcframework (#1490) 2024-10-29 12:26:26 +08:00
Fangjun Kuang
9eb493f6bf Publish pre-built wheels for Python 3.13 (#1485) 2024-10-28 10:37:50 +08:00
Fangjun Kuang
cdd8e1bbcb Add Pascal API for Moonshine models (#1482) 2024-10-27 12:21:16 +08:00
Fangjun Kuang
3d3edabb5f Add Go API for Moonshine models (#1479) 2024-10-27 09:39:09 +08:00
Fangjun Kuang
052b8645ba Add Go API examples for adding punctuations to text. (#1478) 2024-10-27 09:04:05 +08:00
Fangjun Kuang
2ca2985d04 Add C and C++ API for Moonshine models (#1476) 2024-10-26 23:24:46 +08:00
Fangjun Kuang
bd4b223920 Add Kotlin and Java API for Moonshine models (#1474) 2024-10-26 22:30:29 +08:00
Fangjun Kuang
669f5ef441 Add C++ runtime and Python APIs for Moonshine models (#1473) 2024-10-26 14:34:07 +08:00
Fangjun Kuang
0f2732e4e8 Publish pre-built JNI libs for Linux aarch64 (#1472) 2024-10-26 09:59:18 +08:00
Fangjun Kuang
b06b460851 Begin to support https://github.com/usefulsensors/moonshine (#1470) 2024-10-26 09:51:16 +08:00
Fangjun Kuang
707cf792c5 Add GigaAM NeMo transducer model for Russian ASR (#1467) 2024-10-25 15:20:13 +08:00
Fangjun Kuang
b41f6d2c94 Support GigaAM CTC models for Russian ASR (#1464)
See also https://github.com/salute-developers/GigaAM
2024-10-25 10:55:16 +08:00
Fangjun Kuang
ceb69ebd94 Add C++ API for non-streaming ASR (#1456) 2024-10-23 16:40:12 +08:00
Fangjun Kuang
effd5ef2be Add C++ API for streaming ASR. (#1455)
It is a wrapper around the C API.
2024-10-23 12:07:43 +08:00
Fangjun Kuang
620597f501 Support https://huggingface.co/Revai/reverb-diarization-v1 (#1437) 2024-10-17 11:58:14 +08:00
Fangjun Kuang
df4150dc5d Upload speaker embedding models to huggingface (#1428)
See also
https://huggingface.co/spaces/k2-fsa/speaker-diarization
2024-10-14 16:20:00 +08:00
Fangjun Kuang
5a22f74b2b Android demo for speaker diarization (#1423) 2024-10-13 14:02:57 +08:00
Fangjun Kuang
5e273c5be4 Pascal API for speaker diarization (#1420) 2024-10-12 12:28:38 +08:00
Fangjun Kuang
1ed803adc1 Dart API for speaker diarization (#1418) 2024-10-11 21:17:41 +08:00
Fangjun Kuang
1851ff6337 Java API for speaker diarization (#1416) 2024-10-11 16:51:40 +08:00
Fangjun Kuang
eefc172095 JavaScript API with WebAssembly for speaker diarization (#1414)
#1408 uses [node-addon-api](https://github.com/nodejs/node-addon-api) to call C API from JavaScript, whereas this pull request uses WebAssembly to call C API from JavaScript.
2024-10-11 11:40:10 +08:00
Fangjun Kuang
1d061df355 WebAssembly exmaple for speaker diarization (#1411) 2024-10-10 22:14:45 +08:00
Fangjun Kuang
a45e5dba99 C# API for speaker diarization (#1407) 2024-10-10 14:29:05 +08:00
Fangjun Kuang
df681e9807 Go API for speaker diarization (#1403) 2024-10-09 20:10:44 +08:00
Fangjun Kuang
8535b1d3bb Python API for speaker diarization. (#1400) 2024-10-09 14:13:26 +08:00
Fangjun Kuang
59407edcad C++ API for speaker diarization (#1396) 2024-10-09 12:01:20 +08:00
Fangjun Kuang
70165cb42d Speaker diarization example with onnxruntime Python API (#1395) 2024-10-06 16:37:29 +08:00
Fangjun Kuang
66feecb2b5 support whisper turbo (#1390) 2024-10-02 18:13:34 +08:00
Fangjun Kuang
b965f14cf0 Add Python API for clustering (#1385) 2024-09-30 11:33:15 +08:00
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
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
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