Chatterbox Docker Setup

This repository contains a Docker setup for running Chatterbox, a text-to-speech application.

Prerequisites

• Docker installed on your system
• NVIDIA GPU with CUDA support (required for GPU acceleration)
• NVIDIA Container Toolkit installed

Building the Docker Image

To build the Docker image, run the following command from the directory containing the Dockerfile:

docker build -t chatterbox-docker-app .

You can run the command with --network host flag to build your image using the host's network directly, which bypasses virtual networking bugs of "Docker Bridge Network"

Running the Container

To run the container with GPU support, use the following command:

docker run -p 7860:7860 --gpus all -e APP_SCRIPT="gradio_tts_app.py" --name chatterbox chatterbox-docker-app

Customizing the Application Script

You can change the application script to run multilingual model by modifying the APP_SCRIPT environment variable:

docker run -p 7860:7860 --gpus all -e APP_SCRIPT="multilingual_app.py" --name chatterbox chatterbox-docker-app

Accessing the Application

After starting the container, you can access the application at:

http://localhost:7860

Notes

• The container is configured to use all available NVIDIA GPUs
• The application will be accessible from any network interface (0.0.0.0)
• The Hugging Face cache is stored in /app/hf_cache for better model caching