DeepSpeech/Dockerfile.train.tmpl
2020-06-15 14:13:22 +02:00

45 lines
1.2 KiB
Cheetah

# Please refer to the TRAINING documentation, "Basic Dockerfile for training"
FROM tensorflow/tensorflow:1.15.2-gpu-py3
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
WORKDIR /
RUN git lfs install
RUN git clone $DEEPSPEECH_REPO
WORKDIR /DeepSpeech
RUN git checkout $DEEPSPEECH_SHA
# Setup a virtualenv otherwise we mess with the system and this is BAD.
RUN python3 -m venv venv/
ENV VIRTUAL_ENV=/DeepSpeech/venv
ENV PATH=$VIRTUAL_ENV/bin:$PATH
# Build CTC decoder first, to avoid clashes on incompatible versions upgrades
RUN cd native_client/ctcdecode && make NUM_PROCESSES=$(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
RUN DS_NODECODER=y pip3 install --upgrade --force-reinstall -e .
RUN ./bin/run-ldc93s1.sh