setup.sh

#!/usr/bin/env bash

apt-get update && \
  apt-get install -y --no-install-recommends \
    libgomp1 \
    openjdk-21-jre-headless \
    wget \
    unzip \
    libgoogle-perftools-dev \
    libsparsehash-dev \
    git \
    cmake \
    build-essential

# download and compile fast align
git clone https://github.com/clab/fast_align.git fast_align_src
cd fast_align_src
mkdir build && cd build
cmake -DCMAKE_POLICY_VERSION_MINIMUM=3.5 ..
make
cd ../..

cp fast_align_src/build/fast_align .
cp fast_align_src/build/atools .
rm -rf fast_align_src

# download fastalign config files
pip install gdown
gdown https://drive.google.com/uc\?id\=1OS-qbYLAgLJ2n4cpk9usNdTcNARjNaSr -O fast_align_config.zip
unzip -o fast_align_config.zip
rm -rf fast_align_config.zip

# download okapi tikal
wget https://okapiframework.org/binaries/main/1.47.0/okapi-apps_gtk2-linux-x86_64_1.47.0.zip
unzip -o okapi-apps_gtk2-linux-x86_64_1.47.0.zip -d okapi-apps_gtk2-linux-x86_64_1.47.0

pip install -r requirements.txt
python -m spacy download xx_ent_wiki_sm