git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
# If you failed to clone submodule due to network failures, please run following command until success
cd CosyVoice
git submodule update --init --recursive

# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.
pip install pynini==2.1.5
pip install -r requirements.txt

# If you encounter sox compatibility issues
# ubuntu
sudo apt-get install sox libsox-dev

mkdir -p pretrained_models
huggingface-cli download model-scope/CosyVoice-300M --local-dir pretrained_models/CosyVoice-300M --token=$hf_token
huggingface-cli download model-scope/CosyVoice-300M-SFT --local-dir pretrained_models/CosyVoice-300M-SFT --token=$hf_token
huggingface-cli download FunAudioLLM/CosyVoice-ttsfrd --local-dir pretrained_models/CosyVoice-ttsfrd --token=$hf_token

ls pretrained_models

cd pretrained_models/CosyVoice-ttsfrd/
unzip resource.zip -d .
pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl

export PYTHONPATH=third_party/Matcha-TTS