experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove unneeded assets and only copy kenlm bins

Browse Source
This commit is contained in:
Josh Meyer 2021-07-15 09:53:04 -04:00
parent 8c65cbf064
commit 52ecb5dbe2
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
Dockerfile.train
View File

@ -1,6 +1,6 @@
# This is a Dockerfile useful for training models with Coqui STT.
# You can train "acoustic" models with audio + Tensorflow, and
# you can train "language" models with text + KenLM.
# You can train "acoustic models" with audio + Tensorflow, and
# you can create "scorers" with text + KenLM.
FROM ubuntu:20.04 AS kenlm-build
ENV DEBIAN_FRONTEND=noninteractive
@ -10,7 +10,8 @@ RUN apt-get update && \
build-essential cmake libboost-system-dev \
libboost-thread-dev libboost-program-options-dev \
libboost-test-dev libeigen3-dev zlib1g-dev \
libbz2-dev liblzma-dev
libbz2-dev liblzma-dev && \
rm -rf /var/lib/apt/lists/*
# Build KenLM to generate new scorers
WORKDIR /code
@ -33,10 +34,12 @@ RUN apt-get update && apt-get install -y --no-install-recommends wget unzip xz-u
# Tool to convert output graph for inference
RUN wget --no-check-certificate https://github.com/coqui-ai/STT/releases/download/v0.9.3/convert_graphdef_memmapped_format.linux.amd64.zip -O temp.zip && \
unzip temp.zip
unzip temp.zip && \
rm temp.zip
RUN wget --no-check-certificate https://github.com/coqui-ai/STT/releases/download/v0.9.3/native_client.tf.Linux.tar.xz -O temp.tar.xz && \
tar -xf temp.tar.xz
tar -xf temp.tar.xz && \
rm temp.tar.xz
FROM nvcr.io/nvidia/tensorflow:21.05-tf1-py3
@ -76,7 +79,8 @@ COPY setup.py /code/setup.py
COPY VERSION /code/VERSION
COPY training /code/training
# Copy files from previous build stages
COPY --from=kenlm-build /code/kenlm /code/kenlm
RUN mkdir -p /code/kenlm/build/
COPY --from=kenlm-build /code/kenlm/build/bin /code/kenlm/build/bin
COPY --from=wget-binaries /convert_graphdef_memmapped_format /code/convert_graphdef_memmapped_format
COPY --from=wget-binaries /generate_scorer_package /code/generate_scorer_package