Views
No views yet
1git clone https://github.com/ASLP-lab/WenetSpeech-Chuan.git
2cd WenetSpeech-Chuan/CosyVoice2-Chuan1conda create -n cosyvoice python=3.10
2conda activate cosyvoice
3# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.
4conda install -y -c conda-forge pynini==2.1.5
5pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
61from huggingface_hub import snapshot_download
2snapshot_download('ASLP-lab/Cosyvoice2-Chuan', local_dir='pretrained_models/Cosyvoice2-Chuan')
3
41import sys
2sys.path.append('third_party/Matcha-TTS')
3from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
4from cosyvoice.utils.file_utils import load_wav
5import torchaudio
6import opencc
7
8cosyvoice_base = CosyVoice2(
9 'pretrained_models/Cosyvoice2-Chuan',
10 load_jit=False, load_trt=False, load_vllm=False, fp16=False
11)
12
13
14prompt_speech_16k = load_wav('asset/sg_017_090.wav', 16000)
15
16text = '我跟你说，四川火锅必须吃牛油锅底，而且必须蘸油碟，你知道了吗？'
17
18for i, j in enumerate(cosyvoice_base.inference_instruct2(text, '用四川话说这句话', prompt_speech_16k, stream=False)):
19 torchaudio.save('base_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
20
21
22
23## Contact
24If you are interested in leaving a message to our research team, feel free to email ziyu_zhang@mail.nwpu.edu.cn.