From 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 19:50:07 +0800
Subject: [PATCH] update
---
funasr/runtime/python/onnxruntime/README.md | 29 ++++++++++++++++-------------
1 files changed, 16 insertions(+), 13 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/README.md b/funasr/runtime/python/onnxruntime/README.md
index b8da082..e19e3a2 100644
--- a/funasr/runtime/python/onnxruntime/README.md
+++ b/funasr/runtime/python/onnxruntime/README.md
@@ -21,11 +21,21 @@
```
-2. Install the `funasr_onnx`.
+2. Install the `funasr_onnx`
+
+install from pip
```shell
-pip install funasr_onnx -i https://pypi.Python.org/simple
+pip install --upgrade funasr_onnx -i https://pypi.Python.org/simple
```
+or install from source code
+
+```shell
+git clone https://github.com/alibaba/FunASR.git && cd FunASR
+cd funasr/runtime/python/onnxruntime
+python setup.py build
+python setup.py install
+```
3. Run the demo.
- Model_dir: the model path, which contains `model.onnx`, `config.yaml`, `am.mvn`.
@@ -44,17 +54,10 @@
print(result)
```
-## Speed
+## Performance benchmark
-Environment锛欼ntel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz
-
-Test [wav, 5.53s, 100 times avg.](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav)
-
-| Backend | RTF |
-|:-------:|:-----------------:|
-| Pytorch | 0.110 |
-| Onnx | 0.038 |
-
+Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_onnx.md)
## Acknowledge
-1. We acknowledge [SWHL](https://github.com/RapidAI/RapidASR) for contributing the onnxruntime(python api).
+1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
+2. We acknowledge [SWHL](https://github.com/RapidAI/RapidASR) for contributing the onnxruntime (for paraformer model).
--
Gitblit v1.9.1