🗓️ This will be a week of hacking and fun from 24 February to 3 March
💻 Create innovative new apps with OpenAI's latest AI tools
💡 Learn from top AI professionals
⚒️ Combine GPT-3, Codex, Dalle-2, and Whisper to build your AI app
🐱‍💻 Now is the time to register and let's get started!

OpenAI Stack Hack

No-rank

Apprentice

Jinu Nyachhyon

Tetranator

mridul3301

Watching the right content and understanding and drawing conclusions from them is very important on this content-populated internet. It is a time-consuming process to go through lengthy tiring lecture videos and research papers. 

In this project, we take input in 3 different formats: youtube video link, pdf link, and pdf uploaded by the user. From the youtube video link, we first download the video and then extract its audio. The audio is then transcribed using WhiperAPI. Finally, we save the transcribed text from the audio and it is summarized using GPT-3. 

As for the pdf link and pdf uploaded from the local device, the text is extracted from the pdf and again with the use of GPT-3, we summarize the pdf. 

The summary LearnIt provides gives an overview of what those lengthy tiring videos and research papers were about. This gives the user an idea of what they can expect from the video and paper. Also based on the summary, they can save time to understand the video and papers quickly and sort them based on their interest. 

Break this hectic process of going through lengthy videos and papers with LearnIt as it not only saves time but also helps users to discard any papers/videos without having to waste time on them, that are less important based on their field of interest. 

LearnIt

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Whisper

DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language.

DALL-E-2

GPT-3 stands for Generative Pre-trained Transformer 3 and it is an autoregressive language model that uses deep learning to produce human-like text. It is the third-generation language prediction model in the GPT-n series created by OpenAI. GPT-3 is currently in open beta.

GPT-3

ChatGPT is a large language model trained by OpenAI to generate human-like text in a conversational style. It is a variant of the GPT-3 model, which was specifically designed to be used to generate text in response to user input. The ChatGPT model has been trained on a vast amount of text data, including conversations and other types of human-generated text, which allows it to generate text that is similar in style and content to human conversation. ChatGPT can be used to generate responses to questions, code, make suggestions, or provide information in a conversational manner, and it is able to do so in a way that is often indistinguishable from human-generated text. The initial model has been trained using Reinforcement Learning from Human Feedback (RLHF), using methods similar to InstructGPT, but with slight differences in the data collection setup. The model is trained using supervised fine-tuning, where human AI trainers provided conversations in which they played both sides—the user and an AI assistant. The trainers would have had access to model-written suggestions to help them compose their responses.

ChatGPT

OpenAI Codex is an artificial intelligence platform that enables developers to translate natural language into code. 

Jinu Nyachhyon@jinu_nyachhyon315

Events attended

Submissions made

I built with

Socials

🤝 Top Collabolators

Mridul Sharma

🤓 Submissions

LearnIt

👌 Attended Hackathons

OpenAI Stack Hack

📝 Certificates

OpenAI Stack Hack | Certificate