diff --git a/docker/Dockerfile_arm64 b/docker/Dockerfile_arm64
new file mode 100644
index 000000000..26b82e997
--- /dev/null
+++ b/docker/Dockerfile_arm64
@@ -0,0 +1,76 @@
+FROM dannadori/voice-changer-internal:20221114_095228 as front
+# FROM debian:bullseye-slim as base
+
+# ARG DEBIAN_FRONTEND=noninteractive
+
+# RUN apt-get update 
+# RUN apt-get install -y python3-pip git
+# RUN apt-get install -y espeak
+# RUN apt-get install -y cmake
+
+# RUN pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
+
+
+# RUN pip install Cython==0.29.32
+# RUN pip install numpy==1.22.4 
+# RUN pip install scipy==1.9.0
+# RUN pip install librosa==0.9.2
+# RUN pip install phonemizer==3.2.1
+# RUN pip install Unidecode==1.3.4
+# RUN pip install resampy==0.4.0
+
+# RUN pip install tqdm==4.64.0
+# RUN pip install retry==0.9.2
+# RUN pip install psutil==5.9.1
+# RUN pip install python-socketio==5.7.1
+# RUN pip install matplotlib==3.5.3
+
+# RUN pip install fastapi==0.85.0
+# RUN pip install python-multipart==0.0.5
+# RUN pip install uvicorn==0.18.3
+# RUN pip install websockets==10.4
+# RUN pip install pyOpenSSL==22.0.0
+
+# RUN pip install pyopenjtalk==0.2.0
+# RUN pip install tensorboard==2.10.0
+
+
+FROM sonoisa/deep-learning-coding:pytorch1.12.0_tensorflow2.9.1
+RUN apt-get update \
+        && apt-get install -y python3-pip espeak gosu libsndfile1-dev\
+        && apt-get clean \
+        && rm -rf /var/lib/apt/lists/*
+
+### Copy local resource
+COPY fine_model/G_180000.pth /MMVC_Trainer/fine_model/G_180000.pth
+COPY fine_model/D_180000.pth /MMVC_Trainer/fine_model/D_180000.pth
+
+### Copy from base
+# COPY --from=base --chmod=777 /usr/local/lib/python3.9/dist-packages /usr/local/lib/python3.9/dist-packages
+
+### Copy from frontend
+##### MMVC Trainer
+COPY --from=front --chmod=777 /MMVC_Trainer /MMVC_Trainer
+RUN chmod 0777 /MMVC_Trainer 
+
+ADD /setup.sh  /MMVC_Trainer/
+ADD /exec.sh  /MMVC_Trainer/
+
+##### Voice changer Internal
+COPY --from=front --chmod=777 /voice-changer-internal/frontend/dist /voice-changer-internal/frontend/dist
+COPY --from=front --chmod=777 /voice-changer-internal/voice-change-service /voice-changer-internal/voice-change-service
+RUN chmod 0777 /voice-changer-internal/voice-change-service 
+
+
+## 歴史的な経緯でsetup.shをMMVC_Trainerに置いているのでそこを起動時のWORKDIRにしている。
+WORKDIR /MMVC_Trainer
+
+# ##### Soft VC
+# COPY --from=front /hubert /hubert
+# COPY --from=front /acoustic-model /acoustic-model
+# COPY --from=front /hifigan /hifigan
+# COPY --from=front /models /models 
+
+
+ENTRYPOINT ["/bin/bash", "setup.sh"]
+CMD [ "-h"]
diff --git a/package.json b/package.json
index 37ad39751..e5ec82988 100644
--- a/package.json
+++ b/package.json
@@ -5,10 +5,12 @@
   "main": "index.js",
   "scripts": {
     "build:docker": "date +%Y%m%d%H%M%S > docker/dummy && DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile docker/ -t voice-changer",
+    "build:docker_arm64": "date +%Y%m%d%H%M%S > docker/dummy && DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile_arm64 docker/ -t voice-changer-arm64",
     "copy:frontend":"docker run -v `pwd`/frontend/dist:/frontend/dist --entrypoint /bin/bash -ti voice-changer -c \"cp -r /voice-changer-internal/frontend/dist/* /frontend/dist\"",
     "copy:backend":"docker run -v `pwd`/demo:/demo --entrypoint /bin/bash -ti voice-changer -c \"cp -r /voice-changer-internal/voice-change-service/* /demo/\"",
     "create:demo":"run-p copy:frontend copy:backend",
     "push:docker": "bash script/001_pushDocker.sh",
+    "push:docker_arm64": "bash script/002_pushDocker_arm64.sh",
     "test": "echo \"Error: no test specified\" && exit 1"
   },
   "repository": {
diff --git a/script/002_pushDocker_arm64.sh b/script/002_pushDocker_arm64.sh
new file mode 100644
index 000000000..f788c61b7
--- /dev/null
+++ b/script/002_pushDocker_arm64.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+data_tag=`date +%Y%m%d_%H%M%S`
+docker login 
+
+docker tag voice-changer dannadori/voice-changer-arm64:$data_tag
+docker push dannadori/voice-changer-arm64:$data_tag