Add Docker support (#2)

- Add Dockerfile (2f226c408aa03149ab91f1410829509e49894bb9)
- Add Docker Compose (821c348f3fb2513806035055e89c9bdc32fa0d4f)
- Update README with running app in Docker instructions (09e7694ff29556e2da6b165ece4dd2eed263ee6f)


Co-authored-by: Jahangir <[email protected]>

Dockerfile

@@ -0,0 +1,28 @@
+FROM --platform=arm64 python:3.10
+
+ARG GRADIO_SERVER_PORT=7860
+ARG GRADIO_SERVER_NAME="0.0.0.0"
+
+ENV PYTHONFAULTHANDLER=1 \
+  PYTHONUNBUFFERED=1 \
+  PYTHONHASHSEED=random \
+  PIP_NO_CACHE_DIR=1 \
+  PIP_DISABLE_PIP_VERSION_CHECK=1 \
+  PIP_DEFAULT_TIMEOUT=100 \
+  GRADIO_SERVER_PORT=${GRADIO_SERVER_PORT} \
+  GRADIO_SERVER_NAME=${GRADIO_SERVER_NAME}
+
+# Install Gradio dependency
+RUN apt-get update && apt-get install -y ffmpeg
+
+WORKDIR /app
+COPY requirements.txt /app
+
+# Strip out GPU packages as we will only use CPU
+RUN sed -i '/nvidia\|triton/d' requirements.txt \
+  && pip install -r requirements.txt
+
+COPY . /app
+
+EXPOSE $GRADIO_SERVER_PORT
+CMD ["python", "/app/app.py"]

README.md

@@ -16,6 +16,32 @@ license: cc-by-nc-4.0
 
 This is an example of using the [MERT-v1-95M](https://huggingface.co/m-a-p/MERT-v1-95M) model as backbone to conduct multiple music understanding tasks with the universal represenation.
 
-The tasks include EMO, GS, MTGInstrument, MTGGenre, MTGTop50, MTGMood, NSynthI, NSynthP, VocalSetS, VocalSetT. 
+The tasks include EMO, GS, MTGInstrument, MTGGenre, MTGTop50, MTGMood, NSynthI, NSynthP, VocalSetS, VocalSetT.
 
-More models can be referred at the [map organization page](https://huggingface.co/m-a-p).
+More models can be referred at the [map organization page](https://huggingface.co/m-a-p).
+
+# Run Local Docker
+
+If you want to run this locally on your MacOS (M1/M2) without having to deal with installing all the dependencies yourself you can use Docker to run the app locally.
+
+### Docker CLI
+
+Using below commands you can build image and run container locally:
+
+```shell
+$ docker build -t isai .
+$ docker run -p 7860:7860 -it isai
+```
+
+The app is now available locally at http://localhost:7860/
+
+### Docker Compose
+
+If there is a desire to tweak or experiment further you can also run the app using Docker Compose.
+
+```shell
+$ docker-compose build
+$ docker-compose up -d
+$ docker-compose exec app bash
+root@cc9b8397a349:/app# python app.py
+```

docker-compose.yml

@@ -0,0 +1,13 @@
+version: '3.5'
+
+services:
+  app:
+    build: .
+    image: isai
+    container_name: isai
+    working_dir: /app
+    command: tail -f /dev/null # Keep container alive
+    ports:
+      - 7860:7860
+    volumes:
+      - .:/app