Python and ChatGPT : My Quest to Develop a YouTube Video Transcriber
Every line of code in this video has been generated by ChatGPT & in this video I'll show you how you can use OpenAI's Whisper to automatically generate YouTube Transcription. OpenAI is a research organization that focuses on developing and promoting friendly artificial intelligence. They have developed a number of different machine learning models and techniques, including natural language processing models like GPT (Generative Pre-trained Transformer) and GPT-2, and reinforcement learning algorithms like DQN and DDPG. Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language. Moreover, it enables transcription in multiple languages, as well as translation from those languages into English. We are open-sourcing models and inference code to serve as a foundation for building useful applications and for further research on robust speech processing.
▶ Link to the notebook : https://github.com/bhattbhavesh91/whi...
The Whisper architecture is a simple end-to-end approach, implemented as an encoder-decoder Transformer. Input audio is split into 30-second chunks, converted into a log-Mel spectrogram, and then passed into an encoder. A decoder is trained to predict the corresponding text caption, intermixed with special tokens that direct the single model to perform tasks such as language identification, phrase-level timestamps, multilingual speech transcription, and to-English speech translation. Other existing approaches frequently use smaller, more closely paired audio-text training datasets, or use broad but unsupervised audio pretraining. Because Whisper was trained on a large and diverse dataset and was not fine-tuned to any specific one, it does not beat models that specialize in LibriSpeech performance, a famously competitive benchmark in speech recognition. However, when we measure Whisper’s zero-shot performance across many diverse datasets we find it is much more robust and makes 50% fewer errors than those models.
▶ Sponsor me on GitHub : https://github.com/sponsors/bhattbhav...
▶ Join this channel to get access to perks: https://bit.ly/BhaveshBhattJoin
▶ Join the Telegram channel for regular updates: https://t.me/bhattbhavesh91
▶ If you like my work, you can buy me a coffee : https://bit.ly/BuyBhaveshCoffee
*I use affiliate links on the products that I recommend. These give me a small portion of the sales price at no cost to you. I appreciate the proceeds and they help me to improve my channel!
▶ Best Book for Python : https://amzn.to/3qYThqu
▶ Best Book for PyTorch & Machine Learning : https://amzn.to/3PyUkdy
▶ Best Book for Statistics : https://amzn.to/3vzvHEn
▶ Best Book for BERT: https://amzn.to/3lpX0fz
▶ Best Book for Machine Learning : https://amzn.to/2P6aZuT
▶ Best Book for Deep Learning : https://amzn.to/30UMTGl
▶ Best Intro Book for MLOps : https://amzn.to/3AoPZmM
Equipments I use for recording the videos:
▶ 1st Laptop I use : https://amzn.to/3AqI8Fp
▶ 2nd Laptop I use : https://amzn.to/3KAiYsB
▶ Microphone : https://amzn.to/3qUPxtz
▶ Camera : https://amzn.to/3rKQsM2
▶ Mobile Phone : https://amzn.to/3nRHP1f
▶ Ring Light : https://amzn.to/33LedM5
▶ RGB Light : https://amzn.to/3KzLgmS
▶ Bag I use : https://amzn.to/3AsM3RZ
If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.
If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think would find them useful.
Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.
You can find me on:
▶ Blog - https://bhattbhavesh91.github.io
▶ Twitter - / _bhaveshbhatt
▶ GitHub - https://github.com/bhattbhavesh91
▶ Medium - / bhattbhavesh91
▶ About.me - https://about.me/bhattbhavesh91
▶ Linktree - https://linktr.ee/bhattbhavesh91
▶ DEV Community - https://dev.to/bhattbhavesh91
▶ Telegram - https://t.me/bhattbhavesh91
#chatgpt #python