TL;DR We're building a caption evaluation harness that scores a WebVTT file on four axes...
TL;DR
We're building a caption evaluation harness that scores a WebVTT file on four axes instead of one:
word error rate under a fixed normalizer, missed entity rate on domain terms, median cue timing
offset, and reading rate in characters per second. Python 3.12, jiwer, whisper_normalizer,
webvtt-py. Run it on every model or vendor change.
Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily…
Every "add captions to your short" tool works the same way: you upload your clip to their servers,...
TL;DR — I built Captionly, a subtitle generator that runs Whisper inside the browser...
A subtitle line-wrap width guard measured text in uppercase to get a conservative pixel budget, but the renderer draws mixed…
I spent the last few days building a multimodal video RAG platform. With a lot of help from Claude...
Word Error Rate lies in both directions on text-to-speech. A 390-sample blind study: 55% of the uncertain clips were the…
