Splitting SRT Subtitles into Chunks for Embedding
Splits SRT subtitles into thematic chunks for embedding. A component technology for a bigger project.
About the project
For one bigger project I needed to cut SRT subtitle transcripts into meaningful thematic chunks that embeddings for vector search are then made from. A local GPT drives the splitting.
The tool has two parts: a Python CLI that processes the subtitles and a Next.js chunk viewer to visualize the results. Unassuming on its own, but a key piece of the puzzle.
What you get
- A basis for vector search in content.
- A local GPT drives the chunking.
- A piece of a bigger project.
How it works (under the hood)
- A Python CLI, srt-segmenter, for processing.
- Splitting into topics via a local GPT (Ollama).
- A Next.js chunk viewer to check the results.
Built with
Want to build like this too?
I teach building apps without programming in the AI First course.
More from Tool
Shoutbase: Testimonials Manager
An internal tool for managing testimonials: a queue of who to ask, a collection of what we've gathered, and an overview of where we use them.
Toucan: A Shared Second Brain for the Team
A shared cloud knowledge base that the team and its AI agents draw from, a "second brain" connected to my local context1.
Running a Project's Marketing Through Claude Code
A marketing team as a set of Claude Code skills: a director, department managers, and specialists that run a project alongside me.