วีดีโอ

What good is this with keeping the audio files private? Does it get sent to google and the AI? Got it to work on Chrome. However, didn't work on FireFox

This is brilliant, thank you. Not going to lie, I didn't realise I should open the Python Notebook link and then open in Colaborate as this is a very new world to me, but once I finally figured it out and let the system do it's thing, it has been a game changer. I record audio notes on my watch (Samsung Classic Watch 6), share them to my Google Drive into the WhisperAudio folder, and your magic code does the rest. You rock!

Hi. I have an error in Step 2: MessageError: Error: credential propagation was unsuccessful

😊🙂🙃

😊🙂🙃

Hi, thanks for that. Very handy guide. What about generating srt files? Is it possible to write srt or vtt with time codes? Maybe in a new dir called captions? It would be nice to have this as well... But I don't know if it would be hard to create this feature... Anyway, thank you for a great job here.

I want to translate Spanish audio file in English can you send me Code

A year later this still works! Thanks Andrew, you just saved me SO MUCH TIME!

Enjoyed watching this after the reading the first Trasker book, the location tie-ins were great, can't wait for Bangkok! Thanks sharing with the writing community, appreciate it!

What was the twitch address again? bram... something.. Thanks!

I do most of reading on my iPad. So…. I follow the action on my map app and when something is mentioned.. a food or weapon…I google it to see what it is. I really like when “real” locations are used and mildly annoyed with made up locations.

Great stuff! Thanks!

I thoroughly enjoyed this and really hope you continue. Thanks!

Excellent!

<> Top work

Fascinating. More of this please Andrew.

I love this! I started reading Night Owl and immediately went to google maps to see where the story was taking place!💕💕💕

Thanks for sharing this part of your process, Andrew. And thanks for introducing us to Trasker. I am really enjoying Night Owl.

Good idea! And a GREAT book!

This is a fantastic idea! Thank you so much for sharing this process. Great video!

Thanks for the shout out! This video is great but it made me miss our walks. Let’s chat soon!

Very cool! Thanks again!

Hi! I must say your explanation was clear, but I did not understand the part about language. My transcriptions are in Spanish, and, in this case, Which model do I have to use? Should the code be the following: model = whisper.load _model ("medium.sp")?

Thanks for your useful tutorial. The hardware accelerator list only includes CPU, T4, TPU, A100 GPU, and V100 GPU. How can I make use of M1 Max? Thank you.

So glad to see you live again talking about writing and creative processes etc. Have truly missed the days of your lives on Periscope! Hope you keep on doing them! And was glad you emailed out on your mailing list to let people know because TH-cam can be glitchy with their notifications. Still amazing as always!! 😊🙂🙃

Do you do an outline for every idea ?

👋

This is great! Many thanks!

When I get to the last step, it just runs in 2 seconds and says "Mounted at /content/drive" . . . the .mov file is in there, and I tried a few versions but nothing changes this . . . any help?!?!?

Great video! Works so bad with spanish :(

Is it possible to modify the code for detecting multiple speakers and as a result line breaks where speakers start and stop in the textfile folder output? Thanks Brian

The last step is not working. The code executes but the transcript is not generated. Could you please help me out?

For some reason it does not work for me. the transcripts resulting from this method do not make sense at all. My guess is that the 16 Khz mono setting is too low quality.

Is it possible to choose a specific language?

Thank you Andrew, however at step 3 there is an error even using your example youtube link: th-cam.com/video/CnT-Na1IeVI/w-d-xo.html ERROR: Unable to extract uploader id;

where do i get the vedio file in my drive

This is amazing!

What a great video! Thank you for all of your hard work. I was wondering if it is possible to set up some kind of trigger, maybe a time trigger, to run this script periodically, let's say every couple of hours.

Hi, Would be it possible to make this app a bit more idtiot proof. Like playing around usage limits of Google and other things like: - dividing audio/video into 30 minute chunks - being able to come back after google 90 minute back stop (starting at last "save point") Cheers

Thanks so much for this! Running my first file now.

Why am i getting librosa error

❤Great video! So many similar videos everywhere these days, but you were the one of the fists and easiest to follow. Thank you! I was looking for this! By the way, I'm trying to add "Summarize" function after this transcribing step. I'd appreciate it if you could give me (us viewers) some idea?💙

Great tutorial; i did try to change language from "en" to "da" when install, but the installation failed? Without this change, it translates the audio txt to english. How do i?

When I take my videos from C: Drive and put them in a Drive folder - I can't drag them out of that file to Colob - What am I missing?

Thank you Andrew. I have been looking for this super simple solution

Andrew, thanks for this awesome video. I need to add time code per line to use as subtitles, how would I do that. With your instruction I was able to transcribe a video to text, all I am missing is the time code that is needed for subtitle burner App. Thanks

Thank you Andrew, a life saver!

Thanks for this great tutorial. I am looking for a way to make SRT files for mp4 video files that I'm going to upload to TH-cam. I love the way you structured the colaboratory, which makes it nice and easy for me to click play on each cell. However, the method that you use only create a big .txt file instead of a time stamped .srt file. Could you make a version of your guide that makes that as well? Much love from Norway

Man this guy used to be so famous for his magic tricks