在网站中写小说想要删除如何做,营销网站建设制作设计,用流媒体做的电台网站,做网站需要多少钱卖片可以吗国内Ubuntu环境Docker部署CosyVoice 本文旨在记录在 国内 CosyVoice项目在 Ubuntu 环境下如何使用 dockermin-conda进行一键部署。 源项目地址#xff1a; https://github.com/FunAudioLLM/CosyVoice
如果想要使用 dockerpython 进行部署#xff0c;可以参考我另一篇博客中的…国内Ubuntu环境Docker部署CosyVoice 本文旨在记录在 国内 CosyVoice项目在 Ubuntu 环境下如何使用 dockermin-conda进行一键部署。 源项目地址 https://github.com/FunAudioLLM/CosyVoice
如果想要使用 dockerpython 进行部署可以参考我另一篇博客中的dockerfile进行修改。 https://blog.csdn.net/qq_36991535/article/details/144872382?spm1001.2014.3001.5502
你只需要将在 git clone 的项目根目录下创建 docker 文件夹然后将本文的文件放到docker文件夹内; model_download.py 放到项目根目录下最后进入docker文件夹使用docker compose -f compose.yaml up 命令即可一键部署。
文件一览
Dockerfilecompose.yamlrequirements.txtstart.shmodel_download.py
效果端口8888
Dockerfile
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04ARG VENV_NAMEcosyvoice
ENV VENV$VENV_NAME
ENV LANGC.UTF-8 LC_ALLC.UTF-8ENV DEBIAN_FRONTENnoninteractive
ENV PYTHONUNBUFFERED1
SHELL [/bin/bash, --login, -c]RUN apt-get update -y --fix-missing
RUN apt-get install -y git build-essential curl wget ffmpeg unzip git git-lfs sox libsox-dev \apt-get clean \git lfs install#
# conda install and conda forge channel as default
# ------------------------------------------------------------------
# Install miniforge
RUN wget --quiet https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh -O ~/miniforge.sh \/bin/bash ~/miniforge.sh -b -p /opt/conda \rm ~/miniforge.sh \ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh \echo source /opt/conda/etc/profile.d/conda.sh /opt/nvidia/entrypoint.d/100.conda.sh \echo source /opt/conda/etc/profile.d/conda.sh ~/.bashrc \echo conda activate ${VENV} /opt/nvidia/entrypoint.d/110.conda_default_env.sh \echo conda activate ${VENV} $HOME/.bashrcENV PATH /opt/conda/bin:$PATHRUN conda config --add channels conda-forge \conda config --set channel_priority strict
# ------------------------------------------------------------------
# ~conda
# RUN conda create -y -n ${VENV} python3.8
ENV CONDA_DEFAULT_ENV${VENV}
ENV PATH /opt/conda/bin:/opt/conda/envs/${VENV}/bin:$PATHWORKDIR /workspace
COPY ./requirements.txt ./ENV PYTHONPATH${PYTHONPATH}:/workspace/CosyVoice:/workspace/CosyVoice/third_party/Matcha-TTS# RUN git clone --recursive https://github.com/FunAudioLLM/CosyVoice.gitRUN conda activate ${VENV} conda install -y -c conda-forge pynini2.1.5
# RUN conda activate ${VENV} cd CosyVoice pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-hostmirrors.aliyun.com
RUN conda activate ${VENV} pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-hostmirrors.aliyun.comWORKDIR /workspace/CosyVoice
compose.yaml
services:cosyvoice:container_name: cosyvoiceimage: cosyvoice:1.0restart: alwaysports:- 8888:8888environment:- TZAsia/Tokyo- NVIDIA_VISIBLE_DEVICESallvolumes:- ../../CosyVoice:/workspace/CosyVoice# command: tail -f /dev/nullcommand: sh -c docker/start.shdeploy:resources:reservations:devices:- driver: nvidiacapabilities: [gpu]requirements.txt
# --extra-index-url https://download.pytorch.org/whl/cu121
--extra-index-url https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/wheel/cu121/
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/ # https://github.com/microsoft/onnxruntime/issues/21684
conformer0.3.2
deepspeed0.14.2; sys_platform linux
diffusers0.27.2
gdown5.1.0
gradio4.32.2
grpcio1.57.0
grpcio-tools1.57.0
huggingface-hub0.25.2
hydra-core1.3.2
HyperPyYAML1.2.2
inflect7.3.1
librosa0.10.2
lightning2.2.4
matplotlib3.7.5
modelscope1.15.0
networkx3.1
omegaconf2.3.0
onnx1.16.0
onnxruntime-gpu1.18.0; sys_platform linux
onnxruntime1.18.0; sys_platform darwin or sys_platform windows
openai-whisper20231117
protobuf4.25
pydantic2.7.0
rich13.7.1
soundfile0.12.1
tensorboard2.14.0
tensorrt-cu1210.0.1; sys_platform linux
tensorrt-cu12-bindings10.0.1; sys_platform linux
tensorrt-cu12-libs10.0.1; sys_platform linux
torch2.3.1
torchaudio2.3.1
transformers4.40.1
uvicorn0.30.0
wget3.2
fastapi0.111.0
fastapi-cli0.0.4
WeTextProcessing1.0.3
matchastart.sh
#! /bin/bash
python3 model_download.py
python3 webui.py --port 8888 --model_dir pretrained_models/CosyVoice-300Mmodel_download.py
# SDK模型下载
from modelscope import snapshot_download
snapshot_download(iic/CosyVoice2-0.5B, local_dirpretrained_models/CosyVoice2-0.5B)
snapshot_download(iic/CosyVoice-300M, local_dirpretrained_models/CosyVoice-300M)
snapshot_download(iic/CosyVoice-300M-25Hz, local_dirpretrained_models/CosyVoice-300M-25Hz)
snapshot_download(iic/CosyVoice-300M-SFT, local_dirpretrained_models/CosyVoice-300M-SFT)
snapshot_download(iic/CosyVoice-300M-Instruct, local_dirpretrained_models/CosyVoice-300M-Instruct)
snapshot_download(iic/CosyVoice-ttsfrd, local_dirpretrained_models/CosyVoice-ttsfrd)
