From 44366d4ede92f68c86f751ad68252c28162b362b Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 14 四月 2023 23:18:59 +0800
Subject: [PATCH] readme
---
funasr/runtime/python/libtorch/README.md | 11 ++++++-----
1 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/funasr/runtime/python/libtorch/README.md b/funasr/runtime/python/libtorch/README.md
index 0e837b1..1150b37 100644
--- a/funasr/runtime/python/libtorch/README.md
+++ b/funasr/runtime/python/libtorch/README.md
@@ -2,8 +2,6 @@
[FunASR](https://github.com/alibaba-damo-academy/FunASR) hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model released on ModelScope, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun锛�
-### Introduction
-- Model comes from [speech_paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary).
### Steps:
1. Export the model.
@@ -31,9 +29,8 @@
```shell
git clone https://github.com/alibaba/FunASR.git && cd FunASR
- cd funasr/runtime/python/funasr_torch
- python setup.py build
- python setup.py install
+ cd funasr/runtime/python/libtorch
+ pip install -e ./
```
3. Run the demo.
@@ -53,6 +50,10 @@
print(result)
```
+## Performance benchmark
+
+Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md)
+
## Speed
Environment锛欼ntel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz
--
Gitblit v1.9.1