Dockerfile.build

# Please refer to the USING documentation, "Dockerfile for building from source"

# Need devel version cause we need /usr/include/cudnn.h
FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04

# >> START Install base software

# Get basic packages
RUN apt-get update && apt-get install -y --no-install-recommends \
        apt-utils \
        bash-completion \
        build-essential \
        ca-certificates \
        cmake \
        curl \
        g++ \
        gcc \
        git \
        libbz2-dev \
        libboost-all-dev \
        libgsm1-dev \
        libopusfile0 \
        libltdl-dev \
        liblzma-dev \
        libmagic-dev \
        libpng-dev \
        libsox-fmt-mp3 \
        libsox-dev \
        locales \
        openjdk-8-jdk \
        pkg-config \
        python3 \
        python3-dev \
        python3-pip \
        python3-wheel \
        python3-numpy \
        sox \
        unzip \
        wget \
        zlib1g-dev

RUN update-alternatives --install /usr/bin/pip pip /usr/bin/pip3 1
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3 1

# Install Bazel
RUN curl -LO "https://github.com/bazelbuild/bazelisk/releases/download/v1.10.1/bazelisk-linux-amd64" && \
    mv bazelisk-linux-amd64 /usr/bin/bazel && \
    chmod +x /usr/bin/bazel

# Try and free some space
RUN rm -rf /var/lib/apt/lists/*

# << END Install base software

# >> START Configure Tensorflow Build

# GPU Environment Setup
ENV TF_NEED_ROCM 0
ENV TF_NEED_OPENCL_SYCL 0
ENV TF_NEED_OPENCL 0
ENV TF_NEED_CUDA 1
ENV TF_CUDA_PATHS "/usr,/usr/local/cuda-10.1,/usr/lib/x86_64-linux-gnu/"
ENV TF_CUDA_VERSION 10.1
ENV TF_CUDNN_VERSION 7.6
ENV TF_CUDA_COMPUTE_CAPABILITIES 6.0
ENV TF_NCCL_VERSION 2.8

# Common Environment Setup
ENV TF_BUILD_CONTAINER_TYPE GPU
ENV TF_BUILD_OPTIONS OPT
ENV TF_BUILD_DISABLE_GCP 1
ENV TF_BUILD_ENABLE_XLA 0
ENV TF_BUILD_PYTHON_VERSION PYTHON3
ENV TF_BUILD_IS_OPT OPT
ENV TF_BUILD_IS_PIP PIP

# Other Parameters
ENV CC_OPT_FLAGS -mavx -mavx2 -msse4.1 -msse4.2 -mfma
ENV TF_NEED_GCP 0
ENV TF_NEED_HDFS 0
ENV TF_NEED_JEMALLOC 1
ENV TF_NEED_OPENCL 0
ENV TF_CUDA_CLANG 0
ENV TF_NEED_MKL 0
ENV TF_ENABLE_XLA 0
ENV TF_NEED_AWS 0
ENV TF_NEED_KAFKA 0
ENV TF_NEED_NGRAPH 0
ENV TF_DOWNLOAD_CLANG 0
ENV TF_NEED_TENSORRT 0
ENV TF_NEED_GDR 0
ENV TF_NEED_VERBS 0
ENV TF_NEED_OPENCL_SYCL 0

ENV PYTHON_BIN_PATH /usr/bin/python3.6
ENV PYTHON_LIB_PATH /usr/local/lib/python3.6/dist-packages

# << END Configure Tensorflow Build

# >> START Configure Bazel

# Running bazel inside a `docker build` command causes trouble, cf:
#   https://github.com/bazelbuild/bazel/issues/134
# The easiest solution is to set up a bazelrc file forcing --batch.
RUN echo "startup --batch" >>/etc/bazel.bazelrc
# Similarly, we need to workaround sandboxing issues:
#   https://github.com/bazelbuild/bazel/issues/418
RUN echo "build --spawn_strategy=standalone --genrule_strategy=standalone" \
    >>/etc/bazel.bazelrc

# << END Configure Bazel

WORKDIR /
COPY . /STT/

# >> START Build and bind

WORKDIR /STT/tensorflow

# Fix for not found script https://github.com/tensorflow/tensorflow/issues/471
RUN ./configure

# Using CPU optimizations:
# -mtune=generic -march=x86-64 -msse -msse2 -msse3 -msse4.1 -msse4.2 -mavx.
# Adding --config=cuda flag to build using CUDA.

# passing LD_LIBRARY_PATH is required cause Bazel doesn't pickup it from environment

# Build STT

RUN bazel build \
	--verbose_failures \
	--workspace_status_command="bash native_client/bazel_workspace_status_cmd.sh" \
	-c opt \
	--copt=-mtune=generic \
	--copt=-march=x86-64 \
	--copt=-msse \
	--copt=-msse2 \
	--copt=-msse3 \
	--copt=-msse4.1 \
	--copt=-msse4.2 \
	--copt=-mavx \
	--config=noaws \
	--config=nogcp \
	--config=nohdfs \
	--config=nonccl \
	//native_client:libstt.so

# Copy built libs to /STT/native_client
RUN cp bazel-bin/native_client/libstt.so bazel-bin/native_client/libkenlm.so /STT/native_client/

# Build client.cc and install Python client and decoder bindings
ENV TFDIR /STT/tensorflow

RUN nproc

WORKDIR /STT/native_client
RUN make NUM_PROCESSES=$(nproc) stt

WORKDIR /STT
RUN cd native_client/python && make NUM_PROCESSES=$(nproc) bindings
RUN pip3 install --upgrade pip
RUN pip3 install -U pip setuptools wheel
RUN pip3 install --upgrade native_client/python/dist/*.whl

RUN cd native_client/ctcdecode && make NUM_PROCESSES=$(nproc) bindings
RUN pip3 install --upgrade native_client/ctcdecode/dist/*.whl

# << END Build and bind

# Allow Python printing utf-8
ENV PYTHONIOENCODING UTF-8

# Build KenLM in /STT/native_client/kenlm folder
WORKDIR /STT/native_client
RUN rm -rf kenlm && \
	git clone https://github.com/kpu/kenlm && \
	cd kenlm && \
	git checkout 87e85e66c99ceff1fab2500a7c60c01da7315eec && \
	mkdir -p build && \
	cd build && \
	cmake .. && \
	make -j $(nproc)

# Done
WORKDIR /STT