diff --git a/docs/source/install.md b/docs/source/install.md
index ac48d88ba8258e3ccb2c9392f7d93669914be8e3..4291b87afa231164f9df30e7811be95ed129d30e 100644
--- a/docs/source/install.md
+++ b/docs/source/install.md
@@ -5,8 +5,8 @@ There are 3 ways to use `PaddleSpeech`. According to the degree of difficulty, t
| Way | Function | Support|
|:---- |:----------------------------------------------------------- |:----|
| Easy | (1) Use command-line functions of PaddleSpeech.
(2) Experience PaddleSpeech on Ai Studio. | Linux, Mac(not support M1 chip),Windows ( For more information about installation, see [#1195](https://github.com/PaddlePaddle/PaddleSpeech/discussions/1195)) |
-| Medium | Support major functions ,such as using the` ready-made `examples and using PaddleSpeech to train your model. | Linux |
-| Hard | Support full function of Paddlespeech, including using join ctc decoder with kaldi, training n-gram language model, Montreal-Forced-Aligner, and so on. And you are more able to be a developer! | Ubuntu |
+| Medium | Support major functions ,such as using the` ready-made `examples and using PaddleSpeech to train your model. | Linux, Mac(not support M1 chip, not support training models),Windows (not support training models) |
+| Hard | Support full function of Paddlespeech, including using join ctc decoder with kaldi([asr2](../../examples/librispeech/asr2 )), training n-gram language model, Montreal-Forced-Aligner, and so on. And you are more able to be a developer! | Ubuntu |
## Prerequisites
- Python >= 3.7
@@ -65,7 +65,7 @@ pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple
> If you fail to install paddlespeech-ctcdecoders, it doesn't matter.
-## Medium: Get the Major Functions (Support Linux)
+## Medium: Get the Major Functions (Support Linux, mac and windows not support training)
If you want to get the major function of `paddlespeech`, you need to do following steps:
### Git clone PaddleSpeech
You need to `git clone` this repository at first.
@@ -75,7 +75,7 @@ cd PaddleSpeech
```
### Install Conda
-Conda is a management system of the environment. You can go to [minicoda](https://docs.conda.io/en/latest/miniconda.html) to select a version (py>=3.7) and install it by yourself or you can use the following command:
+Conda is a management system of the environment. You can go to [minicoda](https://docs.conda.io/en/latest/miniconda.html) to select a version (py>=3.7). For windows, you can follow the installing guide step by step and for linux and mac, you can use the following commands:
```bash
# download the miniconda
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -P tools/
diff --git a/docs/source/install_cn.md b/docs/source/install_cn.md
index 52eb5dadac443a6826ef1f696c624dcc956cbf3d..9294a2bcdfa15ee29462989fa18fbe93df66b870 100644
--- a/docs/source/install_cn.md
+++ b/docs/source/install_cn.md
@@ -4,8 +4,8 @@
| 方式 | 功能 | 支持系统 |
| :--- | :----------------------------------------------------------- | :------------------ |
| 简单 | (1) 使用 PaddleSpeech 的命令行功能.
(2) 在 Aistudio上体验 PaddleSpeech. | Linux, Mac(不支持M1芯片),Windows (安装详情查看[#1195](https://github.com/PaddlePaddle/PaddleSpeech/discussions/1195)) |
-| 中等 | 支持 PaddleSpeech 主要功能,比如使用已有 examples 中的模型和使用 PaddleSpeech 来训练自己的模型. | Linux |
-| 困难 | 支持 PaddleSpeech 的各项功能,包含结合kaldi使用 join ctc decoder 方式解码,训练语言模型,使用强制对齐等。并且你更能成为一名开发者! | Ubuntu |
+| 中等 | 支持 PaddleSpeech 主要功能,比如使用已有 examples 中的模型和使用 PaddleSpeech 来训练自己的模型. | Linux, Mac(不支持M1芯片,不支持训练), Windows(不支持训练) |
+| 困难 | 支持 PaddleSpeech 的各项功能,包含结合 kaldi 使用 join ctc decoder 方式解码 ([asr2](../../examples/librispeech/asr2 )),训练语言模型,使用强制对齐等。并且你更能成为一名开发者! | Ubuntu |
## 先决条件
- Python >= 3.7
- 最新版本的 PaddlePaddle (请看 [安装向导](https://www.paddlepaddle.org.cn/documentation/docs/en/beginners_guide/index_en.html))
@@ -62,7 +62,7 @@ pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple
> 如果出现 paddlespeech-ctcdecoders 无法安装的问题,无须担心,这不影响使用。
-## 中等: 获取主要功能(支持 Linux)
+## 中等: 获取主要功能(支持 Linux, Mac 和 Windows 不支持训练)
如果你想要使用 `paddlespeech` 的主要功能。你需要完成以下几个步骤
### Git clone PaddleSpeech
你需要先 git clone 本仓库
@@ -71,7 +71,7 @@ git clone https://github.com/PaddlePaddle/PaddleSpeech.git
cd PaddleSpeech
```
### 安装 Conda
-Conda 是一个包管理的环境。你可以前往 [minicoda](https://docs.conda.io/en/latest/miniconda.html) 去下载并安装 conda(请下载 py>=3.7 的版本)。你可以尝试自己安装,或者使用以下的命令:
+Conda 是一个包管理的环境。你可以前往 [minicoda](https://docs.conda.io/en/latest/miniconda.html) 去下载并安装 conda(请下载 py>=3.7 的版本)。windows 系统可以使用 conda 的向导安装,linux 和 mac 可以使用以下的命令:
```bash
# 下载 miniconda
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -P tools/
@@ -118,7 +118,7 @@ python3 -m pip install paddlepaddle-gpu==2.2.0 -i https://mirror.baidu.com/pypi/
### 安装 PaddleSpeech
最后安装 `paddlespeech`,这样你就可以使用 `paddlespeech` 中已有的 examples:
```bash
-# 部分用户系统由于默认源的问题,安装中会出现kaldiio安转出错的问题,建议首先安装pytest-runner:
+# 部分用户系统由于默认源的问题,安装中会出现 kaldiio 安转出错的问题,建议首先安装pytest-runner:
pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple
# 请确保目前处于PaddleSpeech项目的根目录
pip install . -i https://pypi.tuna.tsinghua.edu.cn/simple