The transcript was tough to read, I got through it, but I don’t think I followed everyone’s points. Tons of typos and also sometimes it would put marginal words in the wrong speaker’s mouth. I think paying someone to go through this and fix typos or having it done by a person originally (I’d guess this is machine-transcribed) would’ve been worth it, I would’ve chipped in $10 for that and I’m sure many others would’ve.
Thanks for the feedback! I wasn’t sure how much effort to put into this producing this transcript (this entire podcast thing is pretty experimental); good to know you were trying to read along.
It was machine transcribed via Descript but then I did put in another ~90min cleaning it up a bit, removing filler words and correcting egregious mistranscriptions. I could have spent another hour or so to really clean it up, and perhaps will do so next time (or find some scaleable way to handle it eg outsource or LLM). I think that put it in an uncanny valley of “almost readable, but quite a bad experience”.
+1 that the transcript is rough. Unfortunately it’s just pretty expensive to create one that’s decent to read—for $1.50/min (so like $95 for this episode) you can get an OK transcript from rev.com within 24 hours, and then if you want to actually eliminate typos, you just have to go over it yourself.
I’d also encourage you to not use the descript feature that cuts out all ums and ahs—it just makes it sound super disjointed (especially when watching the video).
I use filler a lot so thought the um/ah removal was helpful (it actually cut down the recording by something like 10 minutes overall). It’s especially good for making the transcript readable, though perhaps I could just edit the transcript without changing the audio/video.
I think I care about the video being easier to watch more than I care about missing the ums and ahs? But maybe I’m not appreciating how much umming you do.
The transcript was tough to read, I got through it, but I don’t think I followed everyone’s points. Tons of typos and also sometimes it would put marginal words in the wrong speaker’s mouth. I think paying someone to go through this and fix typos or having it done by a person originally (I’d guess this is machine-transcribed) would’ve been worth it, I would’ve chipped in $10 for that and I’m sure many others would’ve.
Thanks for the feedback! I wasn’t sure how much effort to put into this producing this transcript (this entire podcast thing is pretty experimental); good to know you were trying to read along.
It was machine transcribed via Descript but then I did put in another ~90min cleaning it up a bit, removing filler words and correcting egregious mistranscriptions. I could have spent another hour or so to really clean it up, and perhaps will do so next time (or find some scaleable way to handle it eg outsource or LLM). I think that put it in an uncanny valley of “almost readable, but quite a bad experience”.
Yeah, sadly AFAICT it just takes hours of human time to produce good transcripts.
+1 here, I’ve found this to be a major pain, and just didn’t do it in my last one with Eli Lifland.
+1 that the transcript is rough. Unfortunately it’s just pretty expensive to create one that’s decent to read—for $1.50/min (so like $95 for this episode) you can get an OK transcript from rev.com within 24 hours, and then if you want to actually eliminate typos, you just have to go over it yourself.
I’d also encourage you to not use the descript feature that cuts out all ums and ahs—it just makes it sound super disjointed (especially when watching the video).
Ah interesting, thanks for the tips.
I use filler a lot so thought the um/ah removal was helpful (it actually cut down the recording by something like 10 minutes overall). It’s especially good for making the transcript readable, though perhaps I could just edit the transcript without changing the audio/video.
I think I care about the video being easier to watch more than I care about missing the ums and ahs? But maybe I’m not appreciating how much umming you do.