https://github.com/palwisha-18/interview_prep_buddy
AI-powered interview preparation tool providing real-time feedback using local AI models (Ollama, Whisper) for speech analysis and response evaluation 🎯
https://github.com/palwisha-18/interview_prep_buddy
generative-ai openai speech-to-text streamlit text-to-speech whisper-ai
Last synced: 2 months ago
JSON representation
AI-powered interview preparation tool providing real-time feedback using local AI models (Ollama, Whisper) for speech analysis and response evaluation 🎯
- Host: GitHub
- URL: https://github.com/palwisha-18/interview_prep_buddy
- Owner: Palwisha-18
- Created: 2025-01-29T02:57:56.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-06T04:31:37.000Z (over 1 year ago)
- Last Synced: 2025-03-29T05:17:52.392Z (about 1 year ago)
- Topics: generative-ai, openai, speech-to-text, streamlit, text-to-speech, whisper-ai
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Interview Prep Buddy 🎯
Interview Prep Buddy is an AI-powered interview preparation tool that helps candidates practice and improve their interview skills through real-time feedback on their responses. It uses local AI models for processing, making it free to use and privacy-focused.
## Current Features ✨
- **Speech-to-Text Conversion**: Transcribes your responses using Whisper for detailed analysis
- **AI-Powered Feedback**: Provides comprehensive feedback using Ollama on:
- Response content and relevance
- Answer structure
- Overall delivery
- **Text-to-Speech Feedback**: Delivers feedback in audio format using gTTS
- **Role-based Questions**: Generates relevant interview questions based on your target role
- **Interactive UI**: User-friendly interface built with Streamlit
- **Local Processing**: All AI operations run locally on your machine
## Prerequisites 🔧
Before running the application, ensure you have:
- Python 3.7 or higher installed
- Ollama installed on your system
- A microphone for audio recording
- Sufficient system resources to run local AI models
## Installation 📦
1. Clone the repository:
```bash
git clone https://github.com/Palwisha-18/interview_prep_buddy.git
cd interview_prep_buddy
```
2. Create and activate a virtual environment:
```bash
python -m venv interview_env
# On Windows
interview_env\Scripts\activate
# On macOS/Linux
source interview_env/bin/activate
```
3. Install Ollama:
```bash
# For macOS or Linux
curl -fsSL https://ollama.com/install.sh | sh
# For Windows
# Download from https://ollama.com/download
```
4. Pull the required Ollama model:
```bash
ollama pull mistral
```
5. Install the required Python dependencies:
```bash
pip install --upgrade pip
pip install -r requirements.txt
```
## Usage 🚀
1. Start Ollama service (should be running in background)
2. Start the application:
```bash
streamlit run main.py
```
3. Use the application:
- Enter the role you're preparing for
- Wait for the question to be generated
- Click the microphone icon to record your response
- Stop the recording when finished
- Review your transcribed response
- Read and listen to the AI-generated feedback
- Optionally download the feedback audio