From 097f379c2d1acc0a421ef2652d86132e4e4361fe Mon Sep 17 00:00:00 2001
From: Gareth Davidson <gaz@bitplane.net>
Date: Wed, 13 Sep 2023 00:26:59 +0100
Subject: [PATCH] Add a docker_data dir and improve caching

Rather than relying on things outside the project dir, have a
data dir with all the caches, model files etc, and exclude them from
git and the docker context with the .ignore files.

Also move the install step to last and put it in its own step, so it
doesn't have to rebuild all the slow conda stuff every time there's
a change to a file in the project.
---
 .dockerignore                |  3 +++
 .gitignore                   |  5 ++++-
 Dockerfile                   | 18 +++++++++++++-----
 README.md                    | 10 +---------
 docker_data/data/.gitkeep    |  0
 docker_data/models/.gitkeep  |  0
 docker_data/results/.gitkeep |  0
 docker_data/work/.gitkeep    |  0
 scripts/run_docker.sh        | 15 +++++++++++++++
 9 files changed, 36 insertions(+), 15 deletions(-)
 create mode 100644 .dockerignore
 create mode 100644 docker_data/data/.gitkeep
 create mode 100644 docker_data/models/.gitkeep
 create mode 100644 docker_data/results/.gitkeep
 create mode 100644 docker_data/work/.gitkeep
 create mode 100755 scripts/run_docker.sh

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..6088150
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,3 @@
+docker_data
+build
+*.pyc
diff --git a/.gitignore b/.gitignore
index 7693938..052b2e3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -132,4 +132,7 @@ dmypy.json
 .models/*
 .custom/*
 results/*
-debug_states/*
\ No newline at end of file
+debug_states/*
+
+# Ignore docker data files
+docker_data
diff --git a/Dockerfile b/Dockerfile
index b3e1e5b..1f67ee8 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,7 +1,5 @@
 FROM nvidia/cuda:12.2.0-base-ubuntu22.04
 
-COPY . /app
-
 RUN apt-get update && \
     apt-get install -y --allow-unauthenticated --no-install-recommends \
     wget \
@@ -14,7 +12,6 @@ ENV HOME="/root"
 ENV CONDA_DIR="${HOME}/miniconda"
 ENV PATH="$CONDA_DIR/bin":$PATH
 ENV CONDA_AUTO_UPDATE_CONDA=false
-ENV PIP_DOWNLOAD_CACHE="$HOME/.pip/cache"
 
 RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O /tmp/miniconda3.sh \
     && bash /tmp/miniconda3.sh -b -p "${CONDA_DIR}" -f -u \
@@ -29,5 +26,16 @@ RUN conda create --name tortoise python=3.9 numba inflect \
     && conda activate tortoise \
     && conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia \
     && conda install transformers=4.29.2 \
-    && cd /app \
-    && python setup.py install
+    && conda clean --all \
+    && echo "conda activate tortoise; cd /app" >> "${HOME}/.bashrc"
+
+# Cache the pip deps after all the slow Conda deps
+COPY requirements.txt /app/requirements.txt
+WORKDIR /app
+RUN conda activate tortoise \
+    && pip install -r requirements.txt --no-cache-dir
+
+# and finally copy the source over
+COPY . /app/
+RUN conda activate tortoise \
+    && pip install . --no-cache-dir
diff --git a/README.md b/README.md
index aa8c8cb..eb61cb5 100644
--- a/README.md
+++ b/README.md
@@ -99,15 +99,7 @@ An easy way to hit the ground running and a good jumping off point depending on
 git clone https://github.com/neonbjb/tortoise-tts.git
 cd tortoise-tts
 
-docker build . -t tts
-
-docker run --gpus all \
-    -e TORTOISE_MODELS_DIR=/models \
-    -v /mnt/user/data/tortoise_tts/models:/models \
-    -v /mnt/user/data/tortoise_tts/results:/results \
-    -v /mnt/user/data/.cache/huggingface:/root/.cache/huggingface \
-    -v /root:/work \
-    -it tts
+./scripts/run_docker.sh
 ```
 This gives you an interactive terminal in an environment that's ready to do some tts. Now you can explore the different interfaces that tortoise exposes for tts.
 
diff --git a/docker_data/data/.gitkeep b/docker_data/data/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/docker_data/models/.gitkeep b/docker_data/models/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/docker_data/results/.gitkeep b/docker_data/results/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/docker_data/work/.gitkeep b/docker_data/work/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/scripts/run_docker.sh b/scripts/run_docker.sh
new file mode 100755
index 0000000..0323c6e
--- /dev/null
+++ b/scripts/run_docker.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+set -e
+
+docker build . -t tts
+
+pwd=$(pwd)
+
+docker run --gpus all \
+    -e TORTOISE_MODELS_DIR=/models \
+    -v $pwd/docker_data/models:/models \
+    -v $pwd/docker_data/results:/results \
+    -v $pwd/docker_data/.cache/huggingface:/root/.cache/huggingface \
+    -v $pwd/docker_data/work:/work \
+    -it tts