Tools
EasySubber
A Python desktop tool that combines Whisper transcription and FFmpeg audio extraction in a dialog-based subtitle workflow.
Context
Connecting existing transcription and media tools through a small graphical workflow.
What it does
- Video-file selection
- selectable Whisper models and language options
- audio extraction
- segment-based transcription
- user-selected subtitle output path
Engineering focus
The workflow connects file selection, audio preparation, transcription, and timestamped text output. Model and language choices are available through Tkinter dialogs.
My role
Development of the integration workflow represented in my public repository; Whisper is an existing external model.
Let’s talk software.
Want to discuss software development or a possible opportunity? Get in touch by email.
ignabelitzky@gmail.com