OpenAI Whisper Docker Image (GPU Accelerated)

This Docker image provides a convenient environment for running OpenAI Whisper, a powerful automatic speech recognition (ASR) system. It is based on the latest Ubuntu image and includes the necessary dependencies for running Whisper seamlessly.

Prerequisites

Before you can use this Docker image, you need to have Docker installed on your system.

Installing Docker

Follow the instructions on the official Docker website to install Docker for your operating system.

Usage

To build the Docker image, use the following command:

docker build -t openai-whisper .

Running OpenAI Whisper

To run OpenAI Whisper with the Docker image, you can use the following example command:

docker run --gpus all -it -v ${PWD}/models:/root/.cache/whisper -v ${PWD}/audio-files:/app openai-whisper whisper audio-file.mp3 --device cuda --model large-v3 --language Italian --output_dir /app --output_format txt

This command utilizes GPU acceleration (--gpus all), mounts the local directories for Whisper models and audio files, and specifies the input audio file, output directory, language, and other relevant parameters.

If you do not have a GPU or want to run without GPU acceleration, you can omit the --gpus all flag from the command. For example:

docker run --gpus all -it -v ${PWD}/models:/root/.cache/whisper -v ${PWD}/audio-files:/app openai-whisper whisper audio-file.mp3 --model large-v3 --language Italian --output_dir /app --output_format txt

Additional Commands

You can also check the GPU information using the following command:

docker run --gpus all -it openai-whisper nvidia-smi

References

• OpenAI Whisper GitHub Repository

• NVIDIA Container Toolkit Installation Guide

• Docker Official Website

Feel free to explore and adapt this Docker image based on your specific use case and requirements. For more details on OpenAI Whisper and its usage, refer to the official documentation.