This Docker image generates subtitles for audio files in different languages using OpenAI's Whisper model.
- Build the Docker Image
docker build -t subgen .- Run the Docker Container
docker run -it -v <path/to/audio/folder>:/app subgenThis mounts the folder containing your audio files to the /app directory inside the Docker container. Once inside, you can use ls to list all files and folders.
- Activate the Virtual Environment - Inside the Docker container, activate the Python virtual environment by running
source /opt/venv/bin/activate- -enerate Subtitles - Use the Whisper model to generate subtitles. For example:
whisper sample.wav --language Hindi --task translate- Output - After the process completes, subtitle files like .srt and .vtt will be available in your mounted folder. Check your local directory for these files.
This project uses the Whisper AI model developed by OpenAI.
Pull requests are always welcom :)