This project provides a command-line tool for automatically generating and overlaying subtitles onto video files using OpenAI's Whisper model and FFmpeg. It is designed for video creators and editors seeking an efficient way to add accurate subtitles to their content.

How It Works

The tool leverages OpenAI's Whisper, a robust speech-to-text model, to transcribe audio from video files. It then utilizes FFmpeg to burn these generated subtitles directly onto the video frames, creating a single output file with embedded subtitles. Users can select different Whisper model sizes for trade-offs between transcription accuracy and processing speed, and can also opt to translate subtitles into English.

Quick Start & Requirements

• Install via pip: pip install git+https://github.com/m1guelpf/auto-subtitle.git
• Requires Python 3.7+
• Requires FFmpeg installation (available via apt, brew, or choco).
• Usage example: auto_subtitle /path/to/video.mp4 -o subtitled/
• See all options: auto_subtitle --help

Highlighted Details

• Supports multiple Whisper model sizes (tiny, base, small, medium, large) for customizable accuracy and performance.
• Option to translate transcribed audio into English using the --task translate flag.
• Overlays subtitles directly onto video frames using FFmpeg.

Maintenance & Community

No specific community channels or maintenance details are provided in the README.

Licensing & Compatibility

• Licensed under the MIT License.
• Permissive license suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

The README does not specify hardware requirements for different Whisper models, which may impact performance and usability on lower-end systems.