- 91
- 76 010
Coding Together
Germany
เข้าร่วมเมื่อ 31 ก.ค. 2023
Hello, Pythoneers! 🐍 Coding Together is all about learning, experimenting, and growing our programming skills as a community. My goal is to guide you through Python tutorials, projects, and tips while learning from you too! Together, we'll build apps, solve problems, and discover the endless possibilities of coding. Let’s embark on this journey together and turn those coding dreams into reality. Join the Coding Together community today!
Impressum
Alexander Reute
Untere Muehle 12A
86470 Thannhausen
cod1ing.together@gmail.com
Impressum
Alexander Reute
Untere Muehle 12A
86470 Thannhausen
cod1ing.together@gmail.com
Automate Voice to Text & SRT Subtitles with OpenAI Whisper in Python (Step-by-Step Tutorial)
Hello Pythoneer!
Do you want to learn how to harness the power of OpenAI’s Whisper library to transcribe audio files into text or generate SRT subtitles for your videos-perfect for TH-camrs, content creators, and developers! 🚀 In this step-by-step tutorial, you’ll discover:
✅ Quick Setup: Install Whisper, set up a Python virtual environment, and choose the right model (like "tiny" for speed).
✅ Text Transcription: Convert audio to clean text files, fix formatting issues (like leading spaces), and save results.
✅ SRT File Creation: Format segments with precise timestamps (HH:MM:SS ,MS) for TH-cam-ready subtitles.
✅ Pro Tips: Handle Whisper’s output segments, optimize accuracy, and avoid common pitfalls.
Follow along with the script to build your own transcription tool, whether for podcasts, videos, or apps.
✨ Why Whisper? It’s fast, open-source, and supports multiple languages-ideal for automating subtitles or analyzing audio data.
💡 Need more features? Check out my video on the Whisper CLI version (linked below) for advanced options like max characters per line and output formats!
th-cam.com/video/ZRCzwZRZVng/w-d-xo.html
Got questions? Let me know in the comments: How will you use Whisper? Drop a comment below!
👍 Enjoyed this? Smash the Like button, Subscribe for more Python tutorials, and hit the bell to stay updated!
Happy coding! 💻
🔗 Resources:
🔗 Code
github.com/Tonkyboy/transcribe_with_whisper/blob/master/whisper.py
🔗 OpenAI Whisper
github.com/openai/whisper?tab=readme-ov-file
🔗 Install FFMP
th-cam.com/users/results?search_query=install+ffmpeg
⏰ Content
00:00 Intro
00:20 OpenAI Whisper GitHub
02:41 Coding Voice to .txt
06:09 Coding Voice to .srt
#openai #whisper #pythontutorial #subtitles #voicetotext #srt
Do you want to learn how to harness the power of OpenAI’s Whisper library to transcribe audio files into text or generate SRT subtitles for your videos-perfect for TH-camrs, content creators, and developers! 🚀 In this step-by-step tutorial, you’ll discover:
✅ Quick Setup: Install Whisper, set up a Python virtual environment, and choose the right model (like "tiny" for speed).
✅ Text Transcription: Convert audio to clean text files, fix formatting issues (like leading spaces), and save results.
✅ SRT File Creation: Format segments with precise timestamps (HH:MM:SS ,MS) for TH-cam-ready subtitles.
✅ Pro Tips: Handle Whisper’s output segments, optimize accuracy, and avoid common pitfalls.
Follow along with the script to build your own transcription tool, whether for podcasts, videos, or apps.
✨ Why Whisper? It’s fast, open-source, and supports multiple languages-ideal for automating subtitles or analyzing audio data.
💡 Need more features? Check out my video on the Whisper CLI version (linked below) for advanced options like max characters per line and output formats!
th-cam.com/video/ZRCzwZRZVng/w-d-xo.html
Got questions? Let me know in the comments: How will you use Whisper? Drop a comment below!
👍 Enjoyed this? Smash the Like button, Subscribe for more Python tutorials, and hit the bell to stay updated!
Happy coding! 💻
🔗 Resources:
🔗 Code
github.com/Tonkyboy/transcribe_with_whisper/blob/master/whisper.py
🔗 OpenAI Whisper
github.com/openai/whisper?tab=readme-ov-file
🔗 Install FFMP
th-cam.com/users/results?search_query=install+ffmpeg
⏰ Content
00:00 Intro
00:20 OpenAI Whisper GitHub
02:41 Coding Voice to .txt
06:09 Coding Voice to .srt
#openai #whisper #pythontutorial #subtitles #voicetotext #srt
มุมมอง: 739
วีดีโอ
How to Transcribe Voice with OpenAI Whisper-CLI in Python
มุมมอง 72414 วันที่ผ่านมา
Hello Pythoneer! Struggling with manual subtitles for your videos? Let Python do the heavy lifting! In this tutorial, I’ll show you two powerful ways to transcribe voice to text using OpenAI’s Whisper: 1️⃣ Terminal Magic: Create a lightning-fast CLI workflow for batch processing audio files. Perfect for TH-camrs and content creators! 2️⃣ Python Scripting: Build a reusable script in VS Code for ...
13 Python List Tricks Every Programmer Should Know
มุมมอง 1.2K28 วันที่ผ่านมา
Hello, Pythoneer! Welcome to 13 Things You Need to Know About Python Lists. In this video, we'll explore five groups of essential list techniques, from basic operations to advanced list comprehensions. You'll learn powerful methods like custom sorting with lambda functions, list unpacking, and efficient ways to manipulate data. By the end of it, you'll have practical tools and knowledge to leve...
How to use Grok xAI API in Python - Getting Started
มุมมอง 1.2Kหลายเดือนก่อน
How to use Grok xAI API in Python - Getting Started
How to use OpenAI o1 Model API in Python?
มุมมอง 8292 หลายเดือนก่อน
How to use OpenAI o1 Model API in Python?
Logging Errors Like a PRO in Python Made Easy
มุมมอง 1.2K2 หลายเดือนก่อน
Logging Errors Like a PRO in Python Made Easy
How to use Python’s Map Function: A Quick Guide!
มุมมอง 3732 หลายเดือนก่อน
How to use Python’s Map Function: A Quick Guide!
How to use Google Gemini API in Python: A Quick Guide!
มุมมอง 9622 หลายเดือนก่อน
How to use Google Gemini API in Python: A Quick Guide!
How to use Python's Help Function: A Quick Guide!
มุมมอง 4492 หลายเดือนก่อน
How to use Python's Help Function: A Quick Guide!
How to Process Large Log Files in Python using Generator?
มุมมอง 4363 หลายเดือนก่อน
How to Process Large Log Files in Python using Generator?
How to generate a Fibonacci Sequence in Python using Generators?
มุมมอง 3373 หลายเดือนก่อน
How to generate a Fibonacci Sequence in Python using Generators?
How to use Python Generators: Save Time & Boost Memory Efficiency
มุมมอง 5K3 หลายเดือนก่อน
How to use Python Generators: Save Time & Boost Memory Efficiency
5 Python DATETIME Use Cases Every Developer Should Know
มุมมอง 1863 หลายเดือนก่อน
5 Python DATETIME Use Cases Every Developer Should Know
2 Python Progress Bars You Should Know: TQDM & alive_progress
มุมมอง 1.7K3 หลายเดือนก่อน
2 Python Progress Bars You Should Know: TQDM & alive_progress
How to use Open AI API in Python - Image to Text with GPT4o
มุมมอง 1.5K4 หลายเดือนก่อน
How to use Open AI API in Python - Image to Text with GPT4o
How to Manage Environment Variable in Python
มุมมอง 2224 หลายเดือนก่อน
How to Manage Environment Variable in Python
9 Tricks to Master Python PRINT Function!
มุมมอง 3654 หลายเดือนก่อน
9 Tricks to Master Python PRINT Function!
Master Python *args and **kwargs Like a Pro in Minutes!
มุมมอง 785 หลายเดือนก่อน
Master Python *args and kwargs Like a Pro in Minutes!
How to Use the Gemini API in Python - Image-2-Text & Chat
มุมมอง 5437 หลายเดือนก่อน
How to Use the Gemini API in Python - Image-2-Text & Chat
Python for Beginners - How to use LIST COMPREHENSION
มุมมอง 12310 หลายเดือนก่อน
Python for Beginners - How to use LIST COMPREHENSION
React MUI for Beginners - How to create a Collapse Menu
มุมมอง 410ปีที่แล้ว
React MUI for Beginners - How to create a Collapse Menu
Hey i just need a help integrating grok ai on my python project , i am a newbie and dont have much knowledge about it..Can you help me if possible ?
Hey Buddy for sure! What issue are you facing? Or where do you need help. Feel free to ask. 😄
For some reason I keep getting a FileNotFound error when trying to create the text file. How do I fix this? I'm a windows user if that tells you anything
My god, can't believe you put a "/" there without telling us at 5:32
@BhaiLazer oh sorry buddy! I really missed this one. 😳 thank you for pointing out. And I am glad that you where able to fix it.
@ Thanks for the tutorial though. It was very helpful to include the playlist on the ffmpeg.
@BhaiLazer thanks for your feedback. Did you also face an ffmpeg issue?
@@Cod1ngTogether Nope, surprisingly not. Worked fine for me. However, I did need to use the playlist as I use a windows computer, and not a Mac, where the process is different for the Mac setup.
Sorry! This one has to be fast due the 3min limitations on TH-cam. If you are interested in the slower version i can give sou the link to to slower TikTok version.
By magic , come one
😂 wait what?
Ah, I found the part right now you were talking about 2:10. PCs are at some point like magic! I really don't know why it worked then. :D
NOTE: At 5:32 i added a / infront of the output path. 🔗 Install FFMPEG th-cam.com/users/results?search_query=install+ffmpeg
Why don’t check the length of the set vs list ?
Good point, thats another great way to achieve the same result. 😄
Thank you for this. I didn't get the .env to work because it didn't find "Source" but I didn't really spend much time on looking into it. But the rest was useful!
Ty buddy. Is it running now or should we try to fix it?
Tbh i don't know how to code at all but i will learn im taking IT for grade 10, 11 and 12
Python is good for beginners but awful for pros.
Even if you never want to get a dev job its worth to understand coding purposes if you go in ways like PM or Application Manager. So go Buddy! 😄
I would like to know why you think like this? Dont you think Python is already a common pro Language? 😄
@@Cod1ngTogether No, python has terrible speed.
@llortaton2834 well this can be a downside. But its getting better and better for every release. If you need speed in python you can use cpython. But for development speed and prototyping it’s unbeatable fast. And to mention: if your application isn’t speed critical its also not a downside. So it always depends on your usecase in my opinion ! 😄
Should I purchase the API to work with it ?
I am not sure if they have a free tier as well. But it will be very limited. But you could test it here: platform.openai.com/playground/chat
If you want to use it regularly its worth to add some cash to it. The most requests are verry cheap. But a honest suggestion is to limit the usage. 😄
can you make another video on how to run grok bot on python?
Hey buddy, as a chatbot? Or what are you looking for?
As a meme coin trading bot crawling off twitter.i sent directions to your Instagram dm yesterday
Scraping x isnt this easy anymore cause x did alot to prevent it. When you sou check here, most scraping is agains the TOS and will lead to a IP ban very fast. I have an perma banned account due this 😂 x.com/robots.txt Using the API is easy when you have x premium. If not its very limited. U habe to enter a code you get back from the API in the Web evey time you want to access it… painful
Did you know all of them? If not you should smash that like button. 😆
So many Dislikes? Please tell my why.
How about that? 😅
Funny, but what to use for?
@tonkyboy8920 its more to showcase listslicing and errorhandling than a real usecase.
Is Gemini pro-vision free?
Yeah, it has a free tier as well with limited access atm 50 requests per day: ai.google.dev/pricing#1_5pro
Thanks bro, very objective. I will be using those codes from now on. It is basic and effective
Hey Buddy, thank you for your feedback. You are welcome! 😄 Check out my other videos, I have a lot of helpful tips waiting for you.
Thank you! Awesome and helpful.
You are welcome 😄🤗
Why not use a real library for this? 😄That's why we cool devs have them!
I would. Check out my other shorts, i already did a video about it.
@ ty buddy
I sometimes give google AI a chance, and I am often disappointed by the answers... Maybe OpenAI doesn't deliver the best results, but they know how to handle Users.
Yeah the gemini responses suck sometimes.
X has just a crazy data power due to its platform. Interested to see where this will go.
Yeah. Thats why i was excited to try it out. In the x app there is a free tier available atm.
That's some pretty nasty code right there.
What do you think is nasty about? The regex part or in general?
And you are the reason it is like that in the first place.
Its hard to work with this criticism if i dont know what exactly. Can’t improve it if i dont know whats the reason for this comment.
@@Cod1ngTogether oh I wasn’t criticizing you, I was talking to the guy that opened that comment.
Oh sorry and thank for your clarification 🤩 i hope he will answer why he thinks so.
Just starting out. This was helpful and added to what I have learned. Thanks.
You are welcome buddy. I wish you success on your further journey! Keep going. 😄
NOTE: you don’t need the if return True else return False Part. But it doesn’t hurt for readability to use it.
This is a bad regret for a phone number my guy. Add optional dashes, and add optional opening parenthesis after the country code, and an optional closing parenthesis after the area code as well. Your regex is too rigid and not useful for most applications.
Yeah thats a very specific usecase. But like said in the video if you need more robust check out the phonenumbers library provided by google. 😄 like shown here: th-cam.com/users/shortscXVj7961HmI?si=wqC5MBts0ndqVzSf Should have linked it 😄
World doesn’t end on American phone numbers and formats. What about spaces? Parentheses? Dashes?
You are right! Thats why i called it basic validation and said at the end: for a more robust validaten check out the phonenumbers library provided by google. 😄
Validate a Phone Number in Python #python #programming #coding #codingtogether th-cam.com/users/shortscXVj7961HmI?feature=share Could check out my video about. Just forgot to link it 😄
Might be a good start of US phone numbers but the phone number industry standards are quite complex. Using the Google library for phone number validation is probably better since it would be updated as the phone number algorithms update because a new country code or a new area code is given. +COUNTRYCODE (NPA) NXX-STATION
Yeah I agree! That's why I earlier made a video about: th-cam.com/users/shortscXVj7961HmI But on TikTok i got a lot of feedback saying: You don't need all the time a full suit for simple basic validation, that's why I made this video with the comment for more robust use Googles Library.
Scared about regex? 🤣
@Cod1ngTogether I want to implement the save history and use that prompts in future prompts and voice chat in this flask python chatbot, can you suggest me the best suitable resource for this please
How to share the executable file or link to others to this service without the code share please
Please help me with this
Python isnt the best language to create compiled software. But if .ou want to, check out: 1. Compile your code with Cython to protect it. 2. Use PyInstaller to bundle the compiled files into an executable. Another way would be to pack the function into an API and offer the API protected to the ppl you want to give it to. Both ways are some work that have to be done.
@@Cod1ngTogether Ok, What alternative you would suggest please if not python
That's hard to answer, cause it's out of my expertise. But Java and C++ might be good for compiled software. Or something like flutter if you want to bring it to mobile.
Never hard code API Key
Yeah. Never ever! 😄
01:18 Update: Sorry Pythoneers, I made a mistake I just saw! If you want to use the API better go for the grok-2 models like shown here: console.x.ai/team/fa19e94e-7911-4433-9d02-e656ba0b796a/models?cluster=us-east-1 One of these: grok-2-vision-1212 grok-2-1212 grok-2 grok-2-latest They have access to the x real-time data. So my review at the end is outdated!
What will you use the grok API for? Let us know! 😄
thank you!
You are welcome 🤗
Could you show how to send a phone number in python (With SS7 or some other method, without API's?)
Hey buddy, unfortunately, this involves advanced telecom protocols like SS7, which require specialized knowledge and access to carrier-grade systems-it's outside my area of expertise.
@@Cod1ngTogether That's unfortunate, Let me know when you get SS7 access.
The phonenumbers library is a Python port of Google’s 2009 libphonenumber, designed to parse, validate, and manipulate phone numbers internationally.
Nice 👍👍
Tyty 😄👍🏻
Merry Christmas and Happy Holidays. 🎄🎁
your Screen is too small to read
Ty for your feedback. Good to know! 😄would you suggest zooming in in the current relevant stuff?
Is Grok on your AI radar cause of its x access possibilities? 😄
I think the o1 model is currently only available for Tier5 users. I am not talking about the o1-preview model
Yeah u might be right. 👍🏻 I personally dint like that they a are so expensive. And will stick to 4o or gemini flash 2.0. the can do the most stuff i do.
You might also want to validate the hostname of the email address in your is_valid_email function. An email string can be valid without being a valid email to send to.
Good addition, thank you! Might taggle this in a more extended video about this topic. 😄
Did you know these two ways? What do you use in your e.g. backend for email validation? 😅
I used this code in a while loop to check and document the uptime of a SaaS service we bought in the company. To see if they can hold their negotiated uptime. 😅
Could you use this in your projects? Lets us know. 😄
How to install Gemini models
U mean locally? Unfortunately you cant Google doesnt serve them open source. You just can use them trough the google API. 😅
Bro just use powershell ping command 💀
Yeah we could. But what if you want to automate it with python cause you are not into powershell or have a Mac/ Linux machine? For ppl like this is this video. 😄
Import speedtest😭😭
Whats up buddy? 😂 do you know a built in?
Is it worth to do in python? Or do you prefer simple web uis like google?
less majestic neofetch
Ah what? 😂
@Cod1ngTogether neofetch is a linux program which displays info about your computer, it has a windows port too
Bro I have a question Is python the best programming language? Isn't c++ or Java much much faster than python?😊❤
Great question! In my opinion Python isn’t the best but at least one of the top tier languages. And Python isn’t the fastest in terms of raw performance, but it’s often the best for beginners, rapid development, and data science. C++ and Java are indeed faster but more complex to learn due its compiling! 😄
yeah python is slower than both of those languages but C++ and Java are not beginner friendly so it means that Java and C++ are harder languages to learn
By far yeah. If you master C there is nothing on the world that can impress you anymore in Coding 😂😂