Installation

Install Conda (Optional):

Linux

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=3.8
conda activate funasr

Mac

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

Install Pytorch (version >= 1.11.0):

pip3 install torch torchaudio

If there exists CUDAs in your environments, you should install the pytorch with the version matching the CUDA. The matching list could be found in docs.

Install funasr

Install from pip

pip3 install -U funasr
# For the users in China, you could install with the command:
# pip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple

Or install from source code

git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip3 install -e ./
# For the users in China, you could install with the command:
# pip3 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:

pip3 install -U modelscope
# For the users in China, you could install with the command:
# pip3 install -U modelscope -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)))
```
pip uninstall cffi pycparser
ARCHFLAGS="-arch arm64" pip install cffi pycparser --compile --no-cache-dir
```