README.md

metadata

title: Echo
emoji: 🐢
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
license: apache-2.0
short_description: an emotional recognition model

Audio Emotion Analyzer with Gemma

This application uses Google's Gemma model to analyze emotions from audio files through acoustic feature analysis.

Features

• 🎵 Upload audio files or record directly
• 🎭 Emotion detection using acoustic features
• 🤖 Powered by Google's Gemma model
• 📊 Detailed analysis with confidence scores
• 🎨 Beautiful visual interface

How it works

1. Extracts acoustic features from audio (MFCC, spectral centroid, pitch, energy, etc.)
2. Converts features to descriptive text
3. Uses Gemma to analyze emotional content based on acoustic characteristics
4. Provides structured emotion analysis with reasoning

Supported emotions

• Happy, Sad, Angry, Fearful, Disgusted
• Surprised, Neutral, Excited, Calm, Anxious

Usage

1. Upload an audio file or record your voice
2. Wait for the AI analysis
3. View the emotional analysis with confidence scores and reasoning

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