Create Dockerfile

Dockerfile

@@ -0,0 +1,51 @@
+# Builds GPU docker image of PyTorch
+# Uses multi-staged approach to reduce size
+# Stage 1
+# Use base conda image to reduce time
+FROM continuumio/miniconda3:latest AS compile-image
+# Specify py version
+ENV PYTHON_VERSION=3.8
+# Install apt libs - copied from https://github.com/huggingface/accelerate/blob/main/docker/accelerate-gpu/Dockerfile
+RUN apt-get update && \
+    apt-get install -y curl git wget software-properties-common git-lfs && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists*
+
+# Install audio-related libraries 
+RUN apt-get update && \
+    apt install -y ffmpeg
+
+RUN apt install -y libsndfile1-dev
+RUN git lfs install
+
+# Create our conda env - copied from https://github.com/huggingface/accelerate/blob/main/docker/accelerate-gpu/Dockerfile
+RUN conda create --name peft python=${PYTHON_VERSION} ipython jupyter pip
+RUN python3 -m pip install --no-cache-dir --upgrade pip
+
+# Below is copied from https://github.com/huggingface/accelerate/blob/main/docker/accelerate-gpu/Dockerfile
+# We don't install pytorch here yet since CUDA isn't available
+# instead we use the direct torch wheel
+ENV PATH /opt/conda/envs/peft/bin:$PATH
+# Activate our bash shell
+RUN chsh -s /bin/bash
+SHELL ["/bin/bash", "-c"]
+# Activate the conda env and install transformers + accelerate from source
+RUN source activate peft && \
+    python3 -m pip install --no-cache-dir \
+    librosa \
+    "soundfile>=0.12.1" \
+    scipy \
+    git+https://github.com/huggingface/transformers \
+    git+https://github.com/huggingface/accelerate \
+    peft[test]@git+https://github.com/huggingface/peft
+
+# Install apt libs
+RUN apt-get update && \
+    apt-get install -y curl git wget && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists*
+
+RUN echo "source activate peft" >> ~/.profile
+
+# Activate the virtualenv
+CMD ["/bin/bash"]