Is there any transcripts for the videos available anywhere?

[cedric (Cedric Chee)]

A written text transcript of each lesson would be much appreciated. They don’t need to be time-coded at all.

Benefits of this:

• we can refer back to the transcripts without having to play the videos all the time.
• this will save us a ton of time and helping us learn more effectively.
  • the transcript files are extremely helpful for searching up contents quickly.

The importance of transcripts:

Full notes and transcripts now available

To quote from the announcement: We’ve been so excited to watch the thousands of people working their way through part 1 of Practical Deep Learning For Coders, and the buzzing community that have formed around the course’s Deep Learning Discussion Forums. But we have heard from those for whom English is not their first language that a major impediment to understanding the content is the lack of written transcript or course notes. As a student of Chinese I very much empathize - I find it far eas…

In the previous course, @lin.crampton was kind enough to manually (old-fashioned) transcribe the full set of videos.

Lesson 8 wiki

made a text file transcript of lesson 8 (otherwise known as part2 lesson1). file is lesson8.txt and it resides at https://drive.google.com/open?id=0BxXRvbqKucuNVUFBU3NIT1dtb3M let me know if you see things i should change lin

I think, some kind of crowd-sourced approach would be cool.

Thanks to everyone who are thinking on how to help your fellow students.

[hiromi (Hiromi Suenaga)]

I don’t have “transcripts” but I did take fairly detailed notes if it helps:

Deep Learning 2: Part 2 Lesson 8 – Hiromi Suenaga – Medium

Still working on lesson 10, 13, and 14, but the rest should be there.

[jeremy (Jeremy Howard)]

There are auto-generated transcripts on youtube that are searchable. Click the 3 dots at the bottom right of the video to get to it. But yes, a proper transcript would be even better, since there’s plenty of errors in the automatic one.

BTW one idea would be to use Lin’s transcripts to train a better voice recognition model for my voice, and then auto-generate the transcripts for the new videos. You could even learn a language model to make it more accurate… It would be quite a big project, but it would be pretty amazing to let anyone create a speech recognizer from their own youtube captions!

[hiromi (Hiromi Suenaga)]

That sounds like a fantastic project!! I usually have the youtube’s transcripts open next to the video, but it could use some improvements. I was quite impressed when it spelled “Leslie Smith” correctly, but other terms like “ReLU”, not so much.

[jeremy (Jeremy Howard)]

BTW I’ve just gone through and added @hiromi’s excellent notes to all the wiki posts.

[hiromi (Hiromi Suenaga)]

Thank you I will update the last 3 as soon as I get them done!

[cedric (Cedric Chee)]

I am aware of your awesome set of notes on all the new lessons including Machine Learning. Really helpful. I have been reading some of those DL Part 2 2018 notes before the official launch. I noticed the notes are pretty much in sync with the video. Easy to follow. So, yeah, in some way, almost like “transcripts” Thank you very much.

[beecoder (Nikhil)]

Yes, there’s a wealth of content in each lecture. Especially in part 2 where we end up implementing recent SOTA papers/techniques in each lecture. Taking notes and reviewing multiple times is the way to go!

[cedric (Cedric Chee)]

@jeremy

There are auto-generated transcripts on youtube that are searchable. Click the 3 dots at the bottom right of the video to get to it. But yes, a proper transcript would be even better, since there’s plenty of errors in the automatic one.

Right. A previous participant have also created a simple Python script to grab the auto-generated transcripts on all fast.ai YouTube videos but the transcription quality is so low that it’s even hard to manually correct the mistakes. But with the part 2 2018 edition, the video quality is so much better, so the auto-gen YouTube subtitles are better: GitHub - mingrui/youtube_caption_search: Make youtube video timestamp searchable by caption/subtitle

@jeremy

BTW one idea would be to use Lin’s transcripts to train a better voice recognition model for my voice, and then auto-generate the transcripts for the new videos. You could even learn a language model to make it more accurate… It would be quite a big project, but it would be pretty amazing to let anyone create a speech recognizer from their own youtube captions!

Thanks for giving me the idea. Yeah, it’s an interesting idea to turn into a project with great potentials.