install funasr and modelscope on mac m1 chip

游雁

2023-04-23 31d5c2c125412c02db82d69f9faa7169f189fe3a

 docs/installation.md

@@ -1,35 +1,74 @@
# Installation
FunASR is easy to install, which is mainly based on python packages.
<p align="left">
    <a href=""><img src="https://img.shields.io/badge/OS-Linux%2C%20Win%2C%20Mac-brightgreen.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/Python->=3.7,<=3.10-aff.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/Pytorch-%3E%3D1.11-blue"></a>
</p>

- Clone the repo
``` sh
git clone https://github.com/alibaba/FunASR.git
```
## Installation

- Install Conda
``` sh
### Install Conda (Optional):

#### Linux
```sh
wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
sh Miniconda3-latest-Linux-x86_64.sh
source ~/.bashrc
conda create -n funasr python=3.7
conda activate funasr
```
#### Mac
```sh
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
# For M1 chip
# wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
sh Miniconda3-latest-MacOSX*
source ~/.zashrc
conda create -n funasr python=3.8
conda activate funasr
```
#### Windows
Ref to [docs](https://docs.conda.io/en/latest/miniconda.html#windows-installers)

- Install Pytorch (version >= 1.7.0):
### Install Pytorch (version >= 1.11.0):

| cuda  | |
|:-----:| --- |
|  9.2  | conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=9.2 -c pytorch |
| 10.2  | conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=10.2 -c pytorch |
| 11.1  | conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch |

For more versions, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)

- Install ModelScope
``` sh
pip install "modelscope[audio]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
```sh
pip install torch torchaudio
```

- Install other packages
For more details about torch, please see [https://pytorch.org/get-started/locally](https://pytorch.org/get-started/locally)

### Install funasr

#### Install from pip

```shell
pip install -U funasr
# For the users in China, you could install with the command:
# pip install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
```

#### Or install from source code

``` sh
pip install --editable ./
```
git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip install -e ./
# For the users in China, you could install with the command:
# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple
```

### Install modelscope (Optional)
If you want to use the pretrained models in ModelScope, you should install the modelscope:

```shell
pip install -U modelscope
# For the users in China, you could install with the command:
# pip install -U modelscope -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
```

### FQA
- For installation on MAC M1 chip, the following error may happen:
- - _cffi_backend.cpython-38-darwin.so' (mach-o file, but is an incompatible architecture (have (x86_64), need (arm64e)))
    ```shell
    pip uninstall cffi pycparser
    ARCHFLAGS="-arch arm64" pip install cffi pycparser --compile --no-cache-dir
    ```