README.md

metadata

title: EvalBot - Interview Analysis System
emoji: 🤖
colorFrom: blue
colorTo: green
sdk: docker
app_file: app.py
pinned: false

🎤 EvalBot: Automated Interview Analysis System

Welcome to EvalBot, your AI-powered solution for comprehensive interview analysis!

EvalBot helps assess candidate performance in interviews by analyzing:

• Voice Metrics: Speaking rate, filler words, anxiety, confidence, and fluency.
• Content Analysis: Key themes, strengths, and areas for development in responses.
• Speaker Identification: Differentiating between interviewer and interviewee.
• Acceptance Probability: An estimated likelihood of acceptance based on key performance indicators.

Features:

• Audio Analysis: Upload audio files (WAV, MP3, M4A, FLAC) or provide URLs.
• Detailed PDF Reports: Get professional, structured reports with key insights and actionable recommendations.
• API Access: Integrate EvalBot's analysis capabilities into your own applications.

How to Use the API:

You can interact with EvalBot's API using the gradio_client library in Python.

1. Install the client:

   pip install gradio_client
   

2. Use the API to analyze audio (accepts multiple URLs):

   from gradio_client import Client, handle_file
   import os
   
   # Replace with your actual Space URL (e.g., [https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME](https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME))
   SPACE_URL = "[https://huggingface.co/spaces/norhan12/YOUR_NEW_SPACE_NAME](https://huggingface.co/spaces/norhan12/YOUR_NEW_SPACE_NAME)" # REMEMBER TO UPDATE THIS
   
   # Ensure your Hugging Face Access Token is set as an environment variable (for private spaces)
   # HF_ACCESS_TOKEN = os.getenv("HF_TOKEN") 
   
   client = Client(SPACE_URL) # , hf_token=HF_ACCESS_TOKEN # Uncomment if your space is private
   
   # List of audio URLs to analyze
   audio_interview_urls = [
       "[https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3](https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3)",
       "[https://www.soundhelix.com/examples/mp3/SoundHelix-Song-2.mp3](https://www.soundhelix.com/examples/mp3/SoundHelix-Song-2.mp3)",
       # Add more URLs as needed
   ]
   
   try:
       result = client.predict(
           file=handle_file(audio_interview_urls),
           api_name="/analyze_multiple_audios" # Ensure this matches your function name in app.py
       )
   
       print("Combined Analysis Summary:", result[0])
       print("Detailed Analysis (JSON Array):", result[1])
       print("Downloadable PDF Paths:", result[2])
   
   except Exception as e:
       print(f"An error occurred while calling the API: {e}")
   

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference