Dockerize (#22)

* created Dockerfile and docker-compose.yml

* Update docker-compose.yml

* added docker instructions to readme

.dockerignore

+tmp
+cache
+Dockerfile
+docker-compose.yml
+.dockerignore
+.gitignore

.gitignore

 __pycache__
-tmp
\ No newline at end of file
+tmp
+cache
\ No newline at end of file

Dockerfile

+FROM pytorch/pytorch:2.4.0-cuda12.1-cudnn9-devel
+
+ENV PYTHONUNBUFFERED 1
+
+WORKDIR /usr/src/app
+
+# Install packages
+RUN apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .

README.md

@@ -12,6 +12,7 @@
   - [Modularity](#modularity)
 * [Setup](#setup)
 * [Usage](#usage)
+  - [Docker Server approach](#docker-server)
   - [Server/Client approach](#serverclient-approach)
   - [Local approach](#local-approach)
 * [Command-line usage](#command-line-usage)
@@ -56,6 +57,15 @@ The pipeline can be run in two ways:
 - **Server/Client approach**: Models run on a server, and audio input/output are streamed from a client.
 - **Local approach**: Uses the same client/server method but with the loopback address.
 
+### Docker Server
+
+#### Install the NVIDIA Container Toolkit
+
+https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
+
+#### Start the docker container
+```docker compose up```
+
 ### Server/Client Approach
 
 To run the pipeline on the server:

docker-compose.yml

+---
+version: "3.8"
+services:
+
+  pipeline:
+    build:
+      context: .
+    command: 
+      - python3 
+      - s2s_pipeline.py 
+      - --recv_host 
+      - 0.0.0.0 
+      - --send_host 
+      - 0.0.0.0 
+      - --lm_model_name 
+      - microsoft/Phi-3-mini-4k-instruct 
+      - --init_chat_role 
+      - system
+      - --init_chat_prompt
+      - "You are a helpful assistant"
+      - --stt_compile_mode 
+      - reduce-overhead 
+      - --tts_compile_mode 
+      - default
+    expose:
+      - 12345/tcp
+      - 12346/tcp
+    ports:
+      - 12345:12345/tcp
+      - 12346:12346/tcp
+    volumes:
+      - ./cache/:/root/.cache/
+      - ./s2s_pipeline.py:/usr/src/app/s2s_pipeline.py
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ['0']
+              capabilities: [gpu]

requirements.txt

-nltk==3.8.1
+nltk==3.9.1
 parler_tts @ git+https://github.com/huggingface/parler-tts.git
 torch==2.4.0
 sounddevice==0.5.0