https://github.com/itk-dev/whisper-docker
https://github.com/itk-dev/whisper-docker
Last synced: 7 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/itk-dev/whisper-docker
- Owner: itk-dev
- Created: 2024-10-09T19:56:52.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-07-15T19:42:32.000Z (8 months ago)
- Last Synced: 2025-07-16T22:44:29.305Z (8 months ago)
- Language: Python
- Size: 25.4 KB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
[](https://github.com/psf/black)
# Whisper Docker Setup
This is a Docker setup with a FastAPI proxy that provides basic authentication for the Whisper ASR (Automatic Speech Recognition) service.
## Prerequisites
- Docker and Docker Compose
- Access to the ITKDev Docker commands (`idc`)
## Setup
1. Copy the example environment file and configure it for your needs:
```shell
cp .env.example .env
```
2. Update the API key and other configuration in the `.env` file:
- `API_KEY`: Set a secure API key for authentication
- `ASR_ENGINE`: Choose the ASR engine (default: openai_whisper)
- `ASR_MODEL`: Set the model to use (default: large-v3)
3. Build and start the containers:
```shell
idc build --pull --no-cache
idc up -d
```
## Configuration Options
The following environment variables can be configured in your `.env` file:
- `COMPOSE_PROJECT_NAME`: Project name for Docker Compose (default: whisper)
- `COMPOSE_DOMAIN`: Domain for local development (default: whisper.local.itkdev.dk)
- `API_KEY`: Authentication key for the API
- `WHISPER_ENDPOINT`: Internal endpoint for the Whisper service
- `ASR_ENGINE`: Speech recognition engine to use
- `ASR_MODEL`: Model to use for speech recognition
## API Documentation
The API documentation is available at [/docs](/docs) after starting the services.
## Links
* [Whisper ASR Webservice Documentation](https://ahmetoner.com/whisper-asr-webservice/endpoints/)
* [FastAPI Documentation](https://fastapi.tiangolo.com/)
* [OpenAI Speech to text API](https://platform.openai.com/docs/guides/speech-to-text)