CosyVoice：开源强大的 AI 语音合成工具

from modelscope import snapshot_download
snapshot_download('iic/CosyVoice - 300M', local_dir='pretrained_models/CosyVoice - 300M')
snapshot_download('iic/CosyVoice - 300M - SFT', local_dir='pretrained_models/CosyVoice - 300M - SFT')
snapshot_download('iic/CosyVoice - 300M - Instruct', local_dir='pretrained_models/CosyVoice - 300M - Instruct')
snapshot_download('iic/CosyVoice - ttsfrd', local_dir='pretrained_models/CosyVoice - ttsfrd')

mkdir -p pretrained_models
git clone https://www.modelscope.cn/iic/CosyVoice - 300M.git pretrained_models/CosyVoice - 300M
git clone https://www.modelscope.cn/iic/CosyVoice - 300M - SFT.git pretrained_models/CosyVoice - 300M - SFT
git clone https://www.modelscope.cn/iic/CosyVoice - 300M - Instruct.git pretrained_models/CosyVoice - 300M - Instruct
git clone https://www.modelscope.cn/iic/CosyVoice - ttsfrd.git pretrained_models/CosyVoice - ttsfrd

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

from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torchaudio

cosyvoice = CosyVoice('pretrained_models/CosyVoice - 300M - SFT')
# sft usage
print(cosyvoice.list_avaliable_spks())
# change stream=True for chunk stream inference
for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
    torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], 22050)

cosyvoice = CosyVoice('pretrained_models/CosyVoice - 300M')
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
    torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], 22050)
# cross_lingual usage
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
    torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], 22050)

cosyvoice = CosyVoice('pretrained_models/CosyVoice - 300M - Instruct')
# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
    torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], 22050)

cd runtime/python
docker build -t cosyvoice:v1.0.

docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice - 300M && sleep infinity"
cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>

docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice - 300M && sleep infinity"
cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>