OpenAI Whisper Audio Transcription and Summarization Chatbot

Description

Web app enabling users to record or upload audio files, utilizing OpenAI API (Whisper, GPT-4) and custom agents/ tools with LangChain to generate transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Additionally, users can interact with a GPT4 chatbot about their transcriptions. Data is stored in an SQLite DB for user authentication and later retrieval. Data is also embedded into a Pinecone vector DB, for LLM purposes.

Technologies Utilized

1. Programming Languages: Python, HTML, CSS
2. Web Framework: Streamlit
3. Audio Transcription: OpenAI API (Whisper)
4. LLM: OpenAI API (GPT-4), LangChain
5. Text Analysis: NLTK
6. Vector DB: Pinecone
7. Relational DB and User Auth: SQLite

App V12: Implemented Sidebar for LLM Temperature and Model Selection & Much Improved Code Modularity

App V11: Improved Code Logic, Faster Response Times, Improved Rendering

App V10: Implemented a Pinecone DB utilizing OpenAI Embedding, and and implemented as optional reference tool for LangChain Zero Shot React Description agent.

App V9 Screenshot

Implemented Transcription Fact Checking

From JRE - Neil DeGrasse Tyson - https://www.youtube.com/shorts/y9RowvoU43Q

App V8 Screenshot

Implement option for user to record their own audio

App V7 Screenshot

Implement GPT-4 Sentiment Reports of Transcriptions

App V6 Screenshot

App V5 Screenshot

Implemented GPT-4 ChatBot Functionality

App V4 Screenshots

App V4 Login Page

App V4 AI Response Screenshot

App V3 Screenshots

App V3 Transcript and Summary Generation

App V3 Transcript ans Summary Retrieval

App V2 Screenshots

App V2 Transcript Generation

App V2 SQLite Transcript Retrieval

App V1 Screenshot