WEBVTT

00:00:00.000 --> 00:00:02.720
Thanks for making the time.

00:00:02.800 --> 00:00:06.240
I want to start with the part you said was
messy.

00:00:06.320 --> 00:00:09.690
Right, so the messy part is that the file

00:00:09.770 --> 00:00:12.720
never arrives the way you expect it.

00:00:12.800 --> 00:00:14.817
Someone records on a phone,

00:00:14.897 --> 00:00:19.400
someone else on a laptop, and the levels
are nothing alike.

00:00:19.480 --> 00:00:22.800
We stopped sending the audio anywhere.

00:00:22.880 --> 00:00:25.890
Once the whole thing ran on the machine
that

00:00:25.970 --> 00:00:29.120
recorded it, half the problems were just
gone.

00:00:29.200 --> 00:00:32.538
What surprised me was how much of the time
went

00:00:32.618 --> 00:00:35.520
into the download, not the transcription.

00:00:35.600 --> 00:00:41.400
The model is about 200 megabytes, and
after the first run it is cached.

00:00:41.480 --> 00:00:45.851
On the laptop an hour of audio takes about
three minutes.

00:00:45.931 --> 00:00:50.458
On the desktop with a proper graphics
card, well under one.

00:00:50.538 --> 00:00:54.440
That was the moment it stopped feeling
like a demo.

00:00:54.520 --> 00:00:56.177
Let me add a pause here.

00:00:56.257 --> 00:01:00.960
And then continue with a second paragraph
about subtitle formats.

00:01:01.163 --> 00:01:05.323
SRT works on every video platform.

00:01:05.403 --> 00:01:08.523
VTT is what browsers use.

00:01:08.603 --> 00:01:10.683
Plain text is for notes.