improve build on docker images

.github/workflows/dockerhub.yml

@@ -9,65 +9,62 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-        
+        uses: docker/setup-qemu-action@v2
+
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-
-      - name: checkout repo
-        uses: actions/checkout@v2
-
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v1
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
         with:
           username: ${{ secrets.DOCKER_USER_NAME }}
           password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v3
-        with:
-          images: baxtree/subaligner:latest
-
+
       - name: Extract the tag
         id: tag
         run: echo ::set-output name=TAG::${GITHUB_REF/refs\/tags\/v/}
 
       - name: Build and push the latest image
         id: docker_build_latest
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         with:
           context: ./docker
           file: "./docker/Dockerfile-Ubuntu20"
           build-args: |
             "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
+          platforms: linux/amd64,linux/arm64
           allow: network.host
           github-token: ${{ github.token }}
           tags: baxtree/subaligner:latest
           push: true
 
       - name: Build and push the Ubuntu 20 image
         id: docker_build_u20
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         with:
           context: ./docker
           file: "./docker/Dockerfile-Ubuntu20"
           build-args: |
             "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
+          platforms: linux/amd64,linux/arm64
           allow: network.host
           github-token: ${{ github.token }}
           tags: baxtree/subaligner:${{ steps.tag.outputs.TAG }}.u20
           push: true
 
       - name: Build and push the Ubuntu 22 image
         id: docker_build_u22
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v4
         with:
           context: ./docker
           file: "./docker/Dockerfile-Ubuntu22"
           build-args: |
             "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
+          platforms: linux/amd64,linux/arm64
           allow: network.host
           github-token: ${{ github.token }}
           tags: baxtree/subaligner:${{ steps.tag.outputs.TAG }}.u22
@@ -81,6 +78,7 @@ jobs:
           file: "./docker/Dockerfile-Fedora34"
           build-args: |
             "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
+          platforms: linux/amd64,linux/arm64
           allow: network.host
           github-token: ${{ github.token }}
           tags: baxtree/subaligner:${{ steps.tag.outputs.TAG }}.fed34
@@ -94,23 +92,8 @@ jobs:
           file: "./docker/Dockerfile-ArchLinux"
           build-args: |
             "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
+          platforms: linux/amd64
           allow: network.host
           github-token: ${{ github.token }}
           tags: baxtree/subaligner:${{ steps.tag.outputs.TAG }}.arch
           push: true
-
-      - name: Build and push the CentOS 7 image
-        id: docker_build_el7
-        uses: docker/build-push-action@v2
-        with:
-          context: ./docker
-          file: "./docker/Dockerfile-CentOS7"
-          build-args: |
-            "RELEASE_VERSION=${{ steps.tag.outputs.TAG }}"
-          allow: network.host
-          github-token: ${{ github.token }}
-          tags: baxtree/subaligner:${{ steps.tag.outputs.TAG }}.el7
-          push: true
-
-      - name: Image digest
-        run: echo ${{ steps.docker_build.outputs.digest }}

Pipfile

@@ -33,14 +33,13 @@ chardet = "~=3.0.4"
 click = "==5.1"
 cloudpickle = "==0.5.3"
 cycler = "==0.10.0"
-dask = ">=2021.10.0,<2022.1.0"
 decorator = "==4.3.0"
 distributed = "==1.13.0"
 filelock = "<4.0.0"
 google-pasta = "~=0.2"
 graphviz = "==0.8.3"
 HeapDict = "==1.0.0"
-h5py = "<=3.6.0"
+h5py = "<4.0.0"
 html5lib = "==1.0b9"
 hyperopt = "==0.2.4"
 idna = "==2.8"

README.md

@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="./figures/subaligner.png" alt="subaligner" width="300" />
+  <img src="https://raw.githubusercontent.com/baxtree/subaligner/master/figures/subaligner.png" alt="subaligner" width="300" />
 </div>
 
 [![Build Status](https://github.com/baxtree/subaligner/actions/workflows/ci-pipeline.yml/badge.svg?branch=master)](https://github.com/baxtree/subaligner/actions/workflows/ci-pipeline.yml?query=branch%3Amaster) ![Codecov](https://img.shields.io/codecov/c/github/baxtree/subaligner)

docker/Dockerfile-ArchLinux

@@ -15,8 +15,6 @@ RUN ["/bin/bash", "-c", "pacman --noconfirm -Syu &&\
     /usr/sbin/pyenv install 3.8.12 &&\
     /usr/sbin/pyenv local 3.8.12 &&\
     ln -s /root/.pyenv/versions/3.8.12/bin/python /usr/bin/python &&\
-    python -m venv venv &&\
-    source venv/bin/activate &&\
     python -m pip install --upgrade pip &&\
     python -m pip install wheel &&\
     python -m pip install \"subaligner==${RELEASE_VERSION}\" &&\

docker/Dockerfile-CentOS7

@@ -1,25 +1,30 @@
 # Subaligner CentOS 7 Docker Image
-From centos:7
+From centos:8
 
 ARG RELEASE_VERSION
 
 ENV RELEASE_VERSION=${RELEASE_VERSION}
 
-RUN ["/bin/bash", "-c", "yum install -y epel-release &&\
-    yum update -y &&\
-    yum groupinstall -y \"Development Tools\" &&\
-    rpm -Uvh http://li.nux.ro/download/nux/dextop/el7/x86_64/nux-dextop-release-0-5.el7.nux.noarch.rpm &&\
-    yum install -y openssl-devel bzip2-devel libffi-devel xz-devel &&\
-    yum install -y wget &&\
-    yum install -y ffmpeg &&\
-    yum install -y espeak espeak-devel &&\
-    yum install -y libsndfile-devel &&\
-    yum install -y gcc &&\
-    wget https://www.python.org/ftp/python/3.8.12/Python-3.8.12.tgz &&\
-    tar xvf Python-3.8.12.tgz &&\
-    cd Python-3.8.12 &&\
-    ./configure --enable-optimizations &&\
-    make altinstall &&\
-    python3.8 -m pip install --upgrade pip &&\
-    python3.8 -m pip install \"subaligner==${RELEASE_VERSION}\" &&\
-    python3.8 -m pip install \"subaligner[harmony]==${RELEASE_VERSION}\""]
+RUN cd /etc/yum.repos.d/
+RUN sed -i 's/mirrorlist/#mirrorlist/g' /etc/yum.repos.d/CentOS-*
+RUN sed -i 's|#baseurl=http://mirror.centos.org|baseurl=http://vault.centos.org|g' /etc/yum.repos.d/CentOS-*
+
+RUN ["/bin/bash", "-c", "dnf install -y epel-release dnf-utils &&\
+    dnf upgrade -y openssl-libs bind-export-libs &&\
+    dnf config-manager --set-enabled powertools &&\
+    dnf install -y https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm &&\
+    dnf install -y ffmpeg &&\
+    dnf install -y espeak-ng &&\
+    ln -s /usr/lib64/libespeak-ng.so.1 /usr/lib64/libespeak.so &&\
+    dnf install -y libsndfile-devel &&\
+    dnf install -y python3 &&\
+    dnf install -y gcc &&\
+    dnf install -y python3-wheel &&\
+    dnf install -y python3-devel &&\
+    dnf install -y python3-pip &&\
+    dnf makecache &&\
+    dnf upgrade python3-pip &&\
+    python3 -m pip install --upgrade pip &&\
+    python3 -m pip install --upgrade setuptools wheel &&\
+    python3 -m pip install \"subaligner==${RELEASE_VERSION}\" &&\
+    python3 -m pip install \"subaligner[llm]==${RELEASE_VERSION}\""]

docker/Dockerfile-Debian11

@@ -17,8 +17,6 @@ RUN ["/bin/bash", "-c", "apt -y update &&\
     apt -y install python3-tk &&\
     apt -y install python3-pip &&\
     apt -y install python3-venv &&\
-    python3 -m venv .venv &&\
-    source .venv/bin/activate &&\
     python3 -m pip install --upgrade pip &&\
     python3 -m pip install \"subaligner==${RELEASE_VERSION}\" &&\
     python3 -m pip install \"subaligner[harmony]==${RELEASE_VERSION}\""]

docker/Dockerfile-Ubuntu20

@@ -11,6 +11,7 @@ RUN ["/bin/bash", "-c", "apt-get -y update &&\
     apt-get -y install ffmpeg &&\
     apt-get -y install espeak libespeak1 libespeak-dev espeak-data &&\
     apt-get -y install libsndfile-dev &&\
+    apt-get -y install libhdf5-dev &&\
     apt-get -y install python3-dev &&\
     apt-get -y install python3-tk &&\
     apt-get -y install python3-pip &&\

docker/Dockerfile-Ubuntu22

@@ -11,9 +11,11 @@ RUN ["/bin/bash", "-c", "apt-get -y update &&\
     apt-get -y install ffmpeg &&\
     apt-get -y install espeak libespeak1 libespeak-dev espeak-data &&\
     apt-get -y install libsndfile-dev &&\
+    apt-get -y install libhdf5-dev &&\
     apt-get -y install python3-dev &&\
     apt-get -y install python3-tk &&\
     apt-get -y install python3-pip &&\
     python3 -m pip install --upgrade pip &&\
+    python3 -m pip install --upgrade setuptools wheel &&\
     python3 -m pip install \"subaligner==${RELEASE_VERSION}\" &&\
     python3 -m pip install \"subaligner[harmony]==${RELEASE_VERSION}\""]

docker/docker-compose.yml

@@ -7,12 +7,6 @@ services:
       dockerfile: Dockerfile-CentOS7
     image: baxtree/subaligner:${SUBALIGNER_VERSION}.el7
 
-  subaligner-ubuntu18:
-    build:
-      context: ./
-      dockerfile: Dockerfile-Ubuntu18
-    image: baxtree/subaligner:${SUBALIGNER_VERSION}.u18
-
   subaligner-ubuntu20:
     build:
       context: ./

requirements-arm64.txt

@@ -8,15 +8,14 @@ chardet==3.0.4
 click==5.1
 cloudpickle~=1.6.0
 cycler==0.10.0
-dask>=2021.10.0,<2022.1.0
 decorator==4.3.0
 distributed==1.13.0
 filelock<4.0.0
 google-auth-oauthlib==0.4.2
 google-pasta~=0.2
 graphviz==0.8.3
 HeapDict==1.0.0
-h5py<=4.0.0
+h5py<4.0.0
 html5lib==1.0b9
 hyperopt==0.2.4
 idna==2.8

requirements.txt

@@ -8,14 +8,13 @@ chardet~=3.0.4
 click==5.1
 cloudpickle~=1.6.0
 cycler==0.10.0
-dask>=2021.10.0,<2022.1.0
 decorator==4.3.0
 distributed==1.13.0
 filelock<4.0.0
 google-pasta~=0.2
 graphviz==0.8.3
 HeapDict==1.0.0
-h5py<=3.6.0
+h5py<4.0.0
 html5lib==1.0b9
 hyperopt==0.2.4
 idna==2.8

setup.py

@@ -13,7 +13,7 @@
 with open("README.md") as readme_file:
     readme = readme_file.read()
 
-if machine() == "arm64":
+if sys.platform == "darwin" and machine() == "arm64":
     with open("requirements-arm64.txt") as requirements_file:
         requirements = requirements_file.read().splitlines()[::-1]
 else:
@@ -50,10 +50,6 @@ def get_tag(self):
         python = f"py{sys.version_info.major}{sys.version_info.minor}"
         if sys.platform == "darwin" and architecture == "arm64":
             os_arch = "macosx_11_0_arm64"
-        elif sys.platform == "win32":
-            os_arch = "win32" if architecture == "32bit" else "win_amd64"
-        # elif sys.platform == "linux":
-        #     os_arch = f"manylinux_2_17_{architecture}"
         else:
             os_arch = "any"
         return python, "none", os_arch

site/source/conf.py

@@ -87,7 +87,7 @@
     "sklearn",
     "tensorflow",
     "pysubs2",
-    "cchardet",
+    "chardet",
     "captionstransformer",
     "bs4",
     "transformers",