![Andrew Mayne](/img/default-banner.jpg)
- 114
- 4 596 111
Andrew Mayne
เข้าร่วมเมื่อ 8 พ.ค. 2006
Videos from magician and illusionist Andrew Mayne. AndrewMayne.com
The GPT-4 with Vision Robot Simulator
The GPT-4 with Vision Robot Simulator uses the OpenAI Vision API to navigate a robot to butter.
มุมมอง: 83
วีดีโอ
The influence of Arthur C. Clarke
มุมมอง 858 หลายเดือนก่อน
In this conversation, Andrew Mayne discusses the life and legacy of Arthur C. Clarke, a renowned science fiction writer and futurist. Clarke's contributions to science fiction and his accurate predictions of future technologies are highlighted. The concept of geostationary satellites and their significance in communication is explained. The idea of a space elevator and its role in space travel ...
In conversation with Bram Adams
มุมมอง 1088 หลายเดือนก่อน
In this conversation, Andrew Mayne and Bram Adams discuss various topics related to prompt engineering and the power of AI. Bram shares his journey as a creative technologist and how he found his passion for expressive coding. They explore the concept of agents and the potential they hold in various domains. The importance of goal seeking and the evolution of prompt engineering are also discuss...
Using Google Maps to Help Write Night Owl
มุมมอง 3268 หลายเดือนก่อน
In this conversation, Andrew Mayne discusses how he uses Google Maps to enhance his storytelling. He explains how he blends real locations to create fictional cities and how Google Maps helps him add detail and realism to his stories. Mayne demonstrates how he explores different areas, examines topographical features, and estimates travel time using Google Maps. He also shows how Street View ca...
How to create amazing transcriptions for videos in a Google Drive folder with OpenAI's Whisper.
มุมมอง 2.9Kปีที่แล้ว
In this tutorial I show how to transcribe a folder of videos on Google Drive using OpenAI's Whisper automatic speech recognition model and Google Colab. GitHub link: github.com/AndrewMayneProjects/Whisper OpenAI's Whisper model: openai.com/blog/whisper/
Transcribe Audio Files in your Google Drive with OpenAI's Whisper
มุมมอง 12Kปีที่แล้ว
In this tutorial I show how to use OpenAI's Whisper automatic speech recognition model, Google Drive and Colab to transcribe all the audio files in a Google Drive folder for free. Python notebooks for OpenAI's Whisper: github.com/AndrewMayneProjects/Whisper More about OpenAI's Whisper ASR model: openai.com/blog/whisper/ OpenAI's Whisper GitHub: github.com/openai/whisper
Transcribe YouTube videos for free with OpenAI's Whisper
มุมมอง 3.7Kปีที่แล้ว
This tutorial shows you how to create high quality captions and transcripts using Whisper, OpenAI's open source automatic speech recognitionmodel and Google Colab.. GItHub link: github.com/AndrewMayneProjects/Whisper/blob/main/WhisperTH-cam.ipynb
OpenAI Codex used to explain how to code and create functions
มุมมอง 5923 ปีที่แล้ว
This is a simple application that uses OpenAI Codex for coding questions. To find the best prompt (the instruction that tells it how to answer) I use Semantic Search to determine what kind of coding question the user is asking. For more information on Codex, go to OpenAI.com
OpenAI Codex demo application
มุมมอง 8K3 ปีที่แล้ว
This is a demo application built in just one day using OpenAI Codex - a natural language to code platform. Find out more about Codex at OpenAI.com
Let's talk about writing, creativity and Kindle Vella
มุมมอง 2933 ปีที่แล้ว
I'm answering questions from my email list followers: creativityandwriting.substack.com
Let's talk about writing, creativity and Kindle Vella
มุมมอง 1963 ปีที่แล้ว
I'm answering questions from my email list followers: creativityandwriting.substack.com
The Cure for Writer's Block | Chapter 6: Choosing the Right Story
มุมมอง 1614 ปีที่แล้ว
How to audience test and idea.
The Cure for Writer's Block | Chapter 5: Writing Prompts
มุมมอง 384 ปีที่แล้ว
The Cure for Writer's Block | Chapter 5: Writing Prompts
The Cure for Writer's Block | Chapter 4: Finding Stories
มุมมอง 454 ปีที่แล้ว
The Cure for Writer's Block | Chapter 4: Finding Stories
The Cure for Writer's Block | Chapter 3: What it Means to Write What You Know
มุมมอง 394 ปีที่แล้ว
The Cure for Writer's Block | Chapter 3: What it Means to Write What You Know
The Cure for Writer's Block | Chapter 2: Storytelling is in your DNA
มุมมอง 364 ปีที่แล้ว
The Cure for Writer's Block | Chapter 2: Storytelling is in your DNA
The Cure for Writer's Block | Chapter 1: Opening Night
มุมมอง 1474 ปีที่แล้ว
The Cure for Writer's Block | Chapter 1: Opening Night
The 3 best pieces of writing advice I ever received
มุมมอง 8046 ปีที่แล้ว
The 3 best pieces of writing advice I ever received
My favorite creativity tricks Q&A | Periscope
มุมมอง 4417 ปีที่แล้ว
My favorite creativity tricks Q&A | Periscope
Talking to Peter J. Wacks and Steven L. Sears about writing
มุมมอง 2108 ปีที่แล้ว
Talking to Peter J. Wacks and Steven L. Sears about writing
Andrew Mayne on Writer's Block for Wattpad Block Party
มุมมอง 5948 ปีที่แล้ว
Andrew Mayne on Writer's Block for Wattpad Block Party
One-Minute Writing Advice: Staying Inspired
มุมมอง 6549 ปีที่แล้ว
One-Minute Writing Advice: Staying Inspired
How to Get Started in Writing and Publishing
มุมมอง 4779 ปีที่แล้ว
How to Get Started in Writing and Publishing
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?!?!?
I'm having the same issue
I found the solution. the video file type names have to be in lowercase eg .mov not .MOV
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.
Same here! I had a snippet from Jurassic Park as a test mp3 and its Whisper transcription output was outlandish and made no sense at all. I used Kevin Stratvert's method (th-cam.com/video/ABFqbY_rmEk/w-d-xo.htmlsi=MA9r3_xTwsjC_fhj) and it worked perfectly, but a shame because I prefer this method from Andrew with the file transfer.
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;
@@elvistejeda8661 you mean in the first step? the original lines have changed now a bit (!pip youtube_dl -> !pip install youtube_dl and so on). Your fix still seems to help (it's still processing but at least it found the video now), so thanks a bunch!
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
either me with this function
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