TED very often has a transcript on their page, but it involves some clicking and then some copy-pasting, and the text result is often broken mid-clause after about 10-15 characters.
I'm wondering if there's any useful userscripts, userstyles, or other methods that handle this. (I think TED often sues people who try to make transcripts easily available on a separate site. I may be mistaken, and TED, please don't sue me, it's just a general feeling.)
The same request would apply to YouTube and/or other popular video sites, but I run into this issue most often with TED.
My thanks in advance to anyone who can help me on this!
I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great. You could probably use a local asr model if you want to save money, I just don't bother because it's so cheap already.
That only makes sense for videos that don't have official (not auto-generated) transcripts of course. If there are official transcripts that are good you can just get them directly with yt-dlp.
https://news.ycombinator.com/item?id=44381640
[TedTalk] Extracting URL: [1]
[TedTalk] luvvie_ajayi_jones_how_to_be_a_professional_troublemaker: Downloading webpage
ERROR: the JSON object must be str, bytes or bytearray, not NoneType
exit 1
[1] - full URL is: https://www.ted.com/talks/luvvie_ajayi_jones_how_to_be_a_pro...