From f02ebbe8f1497c9fdbf4be5554b967f196165b79 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期日, 29 一月 2023 10:31:08 +0800
Subject: [PATCH] readme

---
 README.md |   12 ++++--------
 1 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 6bf1278..92ae6ed 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@
 - FunASR supplies a easy-to-use pipeline to finetune pretrained models from [ModelScope](https://www.modelscope.cn/models?page=1&tasks=auto-speech-recognition)
 - Compared to [Espnet](https://github.com/espnet/espnet) framework, the training speed of large-scale datasets in FunASR is much faster owning to the optimized dataloader.
 
-## Installation(Training and Developing)
+## Installation
 
 - Install Conda:
 ``` sh
@@ -40,6 +40,7 @@
 ```
 For more versions, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)
 
+- Install ModelScope:
 
 If you are in the area of China, you could set the source to speed the downloading.
 
@@ -47,7 +48,6 @@
 pip config set global.index-url https://mirror.sjtu.edu.cn/pypi/web/simple
 ```
 
-- Install ModelScope:
 ``` sh
 pip install "modelscope[audio]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
 ```
@@ -61,18 +61,14 @@
 pip install --editable ./
 ```
 
-## Pretrained Model Zoo
-
-We have trained many academic and industrial models, [model hub](docs/modelscope_models.md)
-
 ## Contact
 
 If you have any questions about FunASR, please contact us by
 
 - email: [funasr@list.alibaba-inc.com](funasr@list.alibaba-inc.com)
 
-- Dingding group:
-<div align="left"><img src="docs/images/dingding.jpg" width="250"/>!<img src="docs/images/wechat.png" width="222"/></div>
+- Dingding group and Wechat group:
+<div align="left"><img src="docs/images/dingding.jpg" width="250"/> <img src="docs/images/wechat.png" width="222"/></div>
 
 
 ## Acknowledge

--
Gitblit v1.9.1