OSUM

What is OSUM ?

OSUM is a transcription tool developed by the ASLP laboratory at Northwestern Polytechnical University. It is designed to transcribe audio from podcasts into readable text. This tool provides users with an efficient way to convert spoken content into a written format, making it easier to analyze, share, or reference later. OSUM emphasizes accuracy and usability, catering to both researchers and general users who need reliable transcription services.

Features

• Audio-to-Text Conversion: Accurately transcribes podcast audio files into text. • Customizable Options: Offers flexibility in transcription settings to meet specific needs. • Text Export: Allows users to export transcribed text for further use. • User-Friendly Interface: Provides an intuitive interface for easy navigation and use. • Support for Multiple Formats: Compatible with various audio file formats.

How to use OSUM ?

1. Visit the OSUM demo page on the ASLP laboratory's website.
2. Upload your podcast audio file to the platform.
3. Adjust any customization options as needed (e.g., transcription accuracy, speaker identification).
4. Click the "Start Transcription" button to begin the process.
5. Once completed, review the transcribed text and use the export feature to save or share it.

Frequently Asked Questions

What formats does OSUM support for audio files?
OSUM supports common audio formats such as MP3, WAV, and OGG. For a full list of supported formats, refer to the tool's documentation.

Can I edit the transcribed text directly on the platform?
Yes, OSUM allows users to edit the transcribed text within the interface before exporting it.

How do I access OSUM?
OSUM is available as a web-based tool through the ASLP laboratory's official website. Simply navigate to the demo page and follow the instructions to start using it.