MASSY (MP3 to Audio Summarization SYstem) is a powerful tool designed to transcribe multiple MP3 audio files in bulk using OpenAI's state-of-the-art Whisper model. While it may seem like a simple bulk transcription tool on the surface, MASSY offers much more under the hood.
- ๐๏ธ Bulk transcription of MP3 files
- ๐ Automatic file splitting for large audio files
- ๐ Dual output formats: SRT (SubRip Subtitle) and plain text
- โฑ๏ธ Precise timestamp information in SRT format
- ๐ Detailed transcription reports
- ๐ฅ๏ธ User-friendly GUI with progress tracking
MASSY serves two primary purposes:
- Human-Readable Transcripts: Generate plain text transcripts for easy reading and analysis.
- Machine-Readable Transcripts: Create SRT files with timestamp information for advanced processing and analysis.
The SRT format allows for a deeper understanding of the audio content, including:
- Precise timing of spoken words
- Detection of silence or pauses
- Improved context for AI-driven analysis
- File Selection: Choose a folder containing MP3 files.
- Transcription: MASSY uses OpenAI's Whisper model to transcribe each audio file.
- File Splitting: Large files (>24MB) are automatically split and merged after transcription.
- Output Generation: Creates SRT and/or plain text files based on user preference.
- Metadata Addition: Adds relevant metadata to each transcript, including:
- File name
- Recording date (extracted from filename)
- Duration
- Transcription date
- Report Generation: Produces a summary report of the transcription process.
- Python 3.7+
- OpenAI API key
- Clone the repository:
git clone https://github.com/yourusername/massy.git
- Install required packages:
pip install -r requirements.txt
- Run the application:
python massy.py
- Enter your OpenAI API key.
- Select the folder containing your MP3 files.
- Choose your preferred output format (SRT, Text, or Both).
- Click "Transcribe" and monitor the progress.
MASSY is designed to be part of a larger AI-driven analysis system. The SRT output, with its precise timing information, is particularly useful for:
- ๐ Semantic search and retrieval
- ๐ Time-based sentiment analysis
- ๐ฃ๏ธ Speaker diarization
- ๐ Contextual understanding in language models
By providing both human-readable and machine-readable formats, MASSY bridges the gap between human interpretation and advanced AI analysis.
We welcome contributions to MASSY! Please see our CONTRIBUTING.md for details on how to get started.
This project is licensed under the MIT License - see the LICENSE.md file for details.
- OpenAI for the Whisper model
- All contributors and users of MASSY
๐ Remember: MASSY is more than just a transcription tool โ it's a bridge between human understanding and machine analysis of audio content!