Create captions for videos using AI.

This small project uses OpenAI's whisper AI to generate captions for videos.

• FFmpeg
• Python

• Clone the repo
• Install python from here if you have not already installed it.
• You can install FFmpeg from here or use your package manager to install it.
• Install the requirements by running py setup.py inside of the project directory.

• If you have not already, run the setup.py file to install the required packages.

python setup.py

• Then run the main.py with your own arguments.

python main.py -v <video path> -m <whisper model name> -p (-p is optional)

• Example

python main.py -v video.mp4 -m tiny.en -p

• Arguments

  • -v or --video - The path to the video file.
  • -m or --model - The name of the model to use. (The list of models can be found below)
  • -p or --preview - If you want to preview the generated video.

• Models

For English-only applications, the .en models tend to perform better, especially for the tiny.en and base.en models. These models are provided by OpenAI. More Info

It may take some time to run for the first time since the AI model needs to be downloaded.

The output of the program will be in the output folder. There will be a video called output.mp4 inside of the folder. There will also be a transcript file called captions.vtt and an audio file called audio.mp3.

Make an Issue to report a bug or request a feature.

@GodModed

• 0.3
  • Using ffmpeg instead of moviepy
  • Increased speed by so much
• 0.2
  • Added the ability to preview the generated video.
  • Added better argument parsing.
• 0.1.1
  • Fixed video getting cut off
• 0.1.0
  • Initial Release

This project is licensed under the GNU General Public License v3.0 License.

• Nicholas Renotte
• OpenAI Whisper