Whisper + Python Automation Pipeline - Independent Project
3 MVP iterations | Audio-to-text pipeline automated | GitHub + YouTube demos
Automated speech-to-text pipeline built with Whisper + Python
Created a low-code, open-source pipeline to automate audio transcription and metadata indexing.
Combined Bash + Python scripts to convert media files into timestamped text with searchable keyword logs stored in SQLite.
Published the MVP on GitHub and demos on YouTube.
OpenAI Whisper automation pipeline at a glance
-
![]()
OpenAI Whisper integration
OpenAI Whisper CLI configured for on-demand audio to text transcription.
-
![]()
Metadata & logging
Bash scripts enabled
- Filename cleanup
- DB record duplicate checking
- Logging
-
![]()
Python automation
Python script end-to-end pipeline management
- SQLite DB setup
- Keyword metadata definition
- Transcription word length calculation
- File management.
-
![]()
Community showcase
Published GitHub repo + TyouTube demos and pipeline walkthrough for community sharing.
Demo
Video short extracted from the longer episode featured on https://youtube.com/@techandtangents channel.