From bf243f54de39504236609aa55222ac36d68f4ef4 Mon Sep 17 00:00:00 2001
From: shockrah <alejandros714@protonmail.com>
Date: Sun, 6 Dec 2020 22:31:51 -0800
Subject: [PATCH] new docker for new project

---
 chipsy-training/Dockerfile | 68 ++++++++++++++++++++++++++++++++++++++
 chipsy-training/readme     |  6 ++++
 2 files changed, 74 insertions(+)
 create mode 100644 chipsy-training/Dockerfile
 create mode 100644 chipsy-training/readme

diff --git a/chipsy-training/Dockerfile b/chipsy-training/Dockerfile
new file mode 100644
index 0000000..c8b077d
--- /dev/null
+++ b/chipsy-training/Dockerfile
@@ -0,0 +1,68 @@
+# Please refer to the TRAINING documentation, "Basic Dockerfile for training"
+
+FROM tensorflow/tensorflow:1.15.4-gpu-py3
+ENV DEBIAN_FRONTEND=noninteractive
+
+ENV DEEPSPEECH_REPO=https://github.com/mozilla/DeepSpeech.git
+ENV DEEPSPEECH_SHA=origin/master
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        apt-utils \
+        bash-completion \
+        build-essential \
+        cmake \
+        curl \
+        git \
+        libboost-all-dev \
+        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
+
+# Try and free some space
+RUN rm -rf /var/lib/apt/lists/*
+
+WORKDIR /
+RUN git clone $DEEPSPEECH_REPO DeepSpeech
+
+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==20.2.2 wheel==0.34.2 setuptools==49.6.0
+
+# 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 -e .
+
+# Tool to convert output graph for inference
+RUN python3 util/taskcluster.py --source tensorflow --branch r1.15 \
+        --artifact convert_graphdef_memmapped_format  --target .
+
+# Build KenLM to generate new scorers
+WORKDIR /DeepSpeech/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)
+WORKDIR /DeepSpeech
+
+RUN ./bin/run-ldc93s1.sh
diff --git a/chipsy-training/readme b/chipsy-training/readme
new file mode 100644
index 0000000..114ba85
--- /dev/null
+++ b/chipsy-training/readme
@@ -0,0 +1,6 @@
+Chipsy Training environment
+===========================
+
+The setup for Chipsy(voice assistant thing) to train in.
+Courtesy of Mozilla :^)
+