https://github.com/topdev0215/AudioMultifunctionChatbot

This app enabling users to either record or upload audio files. Then utilizing OpenAI API (Whisper, GPT4) generates transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Users can also intelligently chat about their transcriptions with a GPT4 chatbot. Data is stored relationally in SQLite and also vectorized in Pinecone.
https://github.com/topdev0215/AudioMultifunctionChatbot

gpt4 langcha nltk openai python3 sqlite3 streamlit strean whisper

Last synced: 2 months ago
JSON representation

This app enabling users to either record or upload audio files. Then utilizing OpenAI API (Whisper, GPT4) generates transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Users can also intelligently chat about their transcriptions with a GPT4 chatbot. Data is stored relationally in SQLite and also vectorized in Pinecone.

• Host: GitHub
• URL: https://github.com/topdev0215/AudioMultifunctionChatbot
• Owner: topdev0215
• Created: 2024-02-18T16:55:58.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2024-02-18T16:57:29.000Z (10 months ago)
• Last Synced: 2024-07-30T21:03:17.949Z (5 months ago)
• Topics: gpt4, langcha, nltk, openai, python3, sqlite3, streamlit, strean, whisper
• Language: Python
• Homepage:
• Size: 43.9 KB
• Stars: 1
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# 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)

5. LLM: OpenAI API (GPT-4), LangChain

6. Text Analysis: NLTK

7. Vector DB: Pinecone

8. Relational DB and User Auth: SQLite

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

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/5c822c4f-1763-4be7-ac90-03927e2bbfb2)

### 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

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/1511331a-ab38-4f3f-a6c7-ea2b6d016fa2)

### App V8 Screenshot

#### Implement option for user to record their own audio

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/a2c56da0-9f98-4175-88fc-361c9f4e9909)

### App V7 Screenshot

#### Implement GPT-4 Sentiment Reports of Transcriptions

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/3c3ae66f-e38b-4026-86b4-b920e131ea2b)

### App V6 Screenshot

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/f719c5b2-88f7-4594-b6fb-20254082801b)

### App V5 Screenshot

#### Implemented GPT-4 ChatBot Functionality

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot/assets/87671757/388abd0a-07f0-42ed-87e1-1b9196678e83)

### App V4 Screenshots

#### App V4 Login Page

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-App/assets/87671757/22335942-5277-4f0a-8c8c-9eb54a465d37)

#### App V4 AI Response Screenshot

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-And-Summarization-App/assets/87671757/e90eb4f8-9bbd-4a4d-9be2-d5fc47925fab)

### App V3 Screenshots

#### App V3 Transcript and Summary Generation

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-Streamlit-App/assets/87671757/808b13e6-bebf-42be-97d8-3e09c9987415)

#### App V3 Transcript ans Summary Retrieval 

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-Streamlit-App/assets/87671757/80edcc2c-b7e9-4ff0-9b99-2145a4b8cec4)

### App V2 Screenshots

#### App V2 Transcript Generation

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-Streamlit-App/assets/87671757/3855e9b3-4acd-42b4-97e4-51386bbc5d12)

#### App V2 SQLite Transcript Retrieval

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-Streamlit-App/assets/87671757/cb59aecf-e8c9-439e-9708-40f0cadddc6c)

### App V1 Screenshot

![image](https://github.com/petermartens98/OpenAI-Whisper-Audio-Transcription-Streamlit-App/assets/87671757/27424c2f-530e-4076-8cb8-2d369a7ea89b)