说明文档
CosyVoice
👉🏻 CosyVoice 演示 👈🏻
[CosyVoice 论文][CosyVoice 工作室][CosyVoice 代码]
关于 SenseVoice,请访问 SenseVoice 仓库 和 SenseVoice 空间。
安装
克隆并安装
- 克隆仓库
git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
# 如果由于网络问题导致克隆子模块失败,请运行以下命令直到成功
cd CosyVoice
git submodule update --init --recursive
- 安装 Conda:请参阅 https://docs.conda.io/en/latest/miniconda.html
- 创建 Conda 环境:
conda create -n cosyvoice python=3.8
conda activate cosyvoice
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
# 如果遇到 sox 兼容性问题
# ubuntu
sudo apt-get install sox libsox-dev
# centos
sudo yum install sox sox-devel
模型下载
我们强烈建议您下载我们预训练的 CosyVoice-300M、CosyVoice-300M-SFT、CosyVoice-300M-Instruct 模型和 speech_kantts_ttsfrd 资源。
如果您是该领域的专家,并且只想从头开始训练自己的 CosyVoice 模型,可以跳过此步骤。
# SDK模型下载
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/speech_kantts_ttsfrd', local_dir='pretrained_models/speech_kantts_ttsfrd')
# git模型下载,请确保已安装git lfs
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/speech_kantts_ttsfrd.git pretrained_models/speech_kantts_ttsfrd
解压 ttsfrd 资源并安装 ttsfrd 包
cd pretrained_models/speech_kantts_ttsfrd/
unzip resource.zip -d .
pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl
基本用法
对于零样本/跨语言推理,请使用 CosyVoice-300M 模型。
对于 SFT 推理,请使用 CosyVoice-300M-SFT 模型。
对于指令推理,请使用 CosyVoice-300M-Instruct 模型。
首先,将 third_party/AcademiCodec 和 third_party/Matcha-TTS 添加到您的 PYTHONPATH 中。
export PYTHONPATH=third_party/AcademiCodec:third_party/Matcha-TTS
from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torchaudio
cosyvoice = CosyVoice('speech_tts/CosyVoice-300M-SFT')
# sft 用法
print(cosyvoice.list_avaliable_spks())
output = 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')
torchaudio.save('sft.wav', output['tts_speech'], 22050)
cosyvoice = CosyVoice('speech_tts/CosyVoice-300M')
# zero_shot 用法
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
output = 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)
torchaudio.save('zero_shot.wav', output['tts_speech'], 22050)
# cross_lingual 用法
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
output = 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)
torchaudio.save('cross_lingual.wav', output['tts_speech'], 22050)
cosyvoice = CosyVoice('speech_tts/CosyVoice-300M-Instruct')
# instruct 用法
output = 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.')
torchaudio.save('instruct.wav', output['tts_speech'], 22050)
启动网页演示
您可以使用我们的网页演示页面快速熟悉 CosyVoice。 我们在网页演示中支持 sft/zero_shot/cross_lingual/instruct 推理。
详情请参阅演示网站。
# 将 speech_tts/CosyVoice-300M-SFT 更改为 sft 推理,或将 speech_tts/CosyVoice-300M-Instruct 更改为 instruct 推理
python3 webui.py --port 50000 --model_dir speech_tts/CosyVoice-300M
高级用法
对于高级用户,我们在 examples/libritts/cosyvoice/run.sh 中提供了训练和推理脚本。
您可以按照此教程熟悉 CosyVoice。
构建部署
可选地,如果您想使用 grpc 进行服务部署, 可以运行以下步骤。否则,您可以忽略此步骤。
cd runtime/python
docker build -t cosyvoice:v1.0 .
# 如果要使用 instruct 推理,请将 speech_tts/CosyVoice-300M 更改为 speech_tts/CosyVoice-300M-Instruct
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c \"cd /opt/CosyVoice/CosyVoice/runtime/python && python3 server.py --port 50000 --max_conc 4 --model_dir speech_tts/CosyVoice-300M && sleep infinity\"
python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
讨论与交流
您可以直接在 Github Issues 上讨论。
您也可以扫描二维码加入我们的官方钉钉交流群。
<img src="./asset/dingding.png" width="250px">
致谢
- 我们借鉴了大量来自 FunASR 的代码。
- 我们借鉴了大量来自 FunCodec 的代码。
- 我们借鉴了大量来自 Matcha-TTS 的代码。
- 我们借鉴了大量来自 AcademiCodec 的代码。
- 我们借鉴了大量来自 WeNet 的代码。
免责声明
以上内容仅供学术用途,旨在展示技术能力。部分示例来源于互联网。如有任何内容侵犯您的权利,请联系我们请求删除。
model-scope/CosyVoice-300M-SFT
作者 model-scope
创建时间: 2024-07-07 02:10:07+00:00
更新时间: 2024-07-05 17:41:02+00:00
在 Hugging Face 上查看