I’m not impressed by the subtitles themselves (they’re just ok) but rather by how accessible it is. Like it being an option rather than it being a “tool for creators” or limited to premium or something
Or maybe youtube has added so much dogshit features recently (like ai overviews, automatically adding info cards for anyone mentioned, and highlighting seemingly random words in comments to search it outside of context) that it makes me appreciate these things more lol
I’ve been messing with more recent open-source AI Subtitling models via Subtitle Editor which has a nice GUI for it. Quality is much better these days, at least for English. It still makes mistakes, but the mistakes are on the level of “I misheard what they said and had little context for the conversation” or “the speaker has an accent which makes it hard to understand what they’re saying” mistakes, which is way better than most YouTube Auto Transriptions I’ve seen.
If youtube transcriptions is anything to go by this won’t be great. But I’m optimistic
Youtube transcriptions are suprisingly abysmal considering what technology google already has at hand.
I find them pretty good for English spoken by native speakers. For anything else it’s horrible.
As long as they are talking about normal things and not playing D&D 😃
I actually disagree.
I’m consistently impressed whenever I have auto-subtitles turned on on Youtube.
I’m not impressed by the subtitles themselves (they’re just ok) but rather by how accessible it is. Like it being an option rather than it being a “tool for creators” or limited to premium or something
Or maybe youtube has added so much dogshit features recently (like ai overviews, automatically adding info cards for anyone mentioned, and highlighting seemingly random words in comments to search it outside of context) that it makes me appreciate these things more lol
I’ve been messing with more recent open-source AI Subtitling models via Subtitle Editor which has a nice GUI for it. Quality is much better these days, at least for English. It still makes mistakes, but the mistakes are on the level of “I misheard what they said and had little context for the conversation” or “the speaker has an accent which makes it hard to understand what they’re saying” mistakes, which is way better than most YouTube Auto Transriptions I’ve seen.