DeepSpeech/Dockerfile.train.tmpl

# Please refer to the TRAINING documentation, "Basic Dockerfile for training"

FROM tensorflow/tensorflow:1.15.2-gpu-py3
ARG DEBIAN_FRONTEND=noninteractive

ENV DEEPSPEECH_REPO=#DEEPSPEECH_REPO#
ENV DEEPSPEECH_SHA=#DEEPSPEECH_SHA#

RUN apt-get update && apt-get install -y --no-install-recommends \
        apt-utils \
        bash-completion \
        build-essential \
        curl \
        git \
        git-lfs \
        libbz2-dev \
        locales \
        python3-venv \
        unzip \
        wget

# We need to remove it because it's breaking deepspeech install later with
# weird errors about setuptools
RUN apt-get purge -y python3-xdg

# Install dependencies for audio augmentation
RUN apt-get install -y --no-install-recommends libopus0 libsndfile1

WORKDIR /
RUN git lfs install
RUN git clone $DEEPSPEECH_REPO

WORKDIR /DeepSpeech
RUN git checkout $DEEPSPEECH_SHA

# Build CTC decoder first, to avoid clashes on incompatible versions upgrades
RUN cd native_client/ctcdecode && make NUM_PROCESSES=$(nproc) bindings
RUN pip3 install --upgrade native_client/ctcdecode/dist/*.whl

# Prepare deps
RUN pip3 install --upgrade pip==20.0.2 wheel==0.34.2 setuptools==46.1.3

# Install DeepSpeech
#  - No need for the decoder since we did it earlier
#  - There is already correct TensorFlow GPU installed on the base image,
#    we don't want to break that
RUN DS_NODECODER=y DS_NOTENSORFLOW=y pip3 install --upgrade --force-reinstall -e .

RUN ./bin/run-ldc93s1.sh