benkhelifamohamedtaher/speech-emotion-recognition

Deep learning system for emotion recognition from speech, achieving 50.5% accuracy on 8-class classification using transformer architecture and real-time analysis

43
/ 100
Emerging

This project helps systems understand human emotions by analyzing spoken words. It takes audio input, like a live conversation or a recording, and identifies one of eight emotions (e.g., anger, happiness, sadness). This is useful for anyone building or managing virtual assistants, mental health support tools, or customer service platforms that need to respond appropriately to user feelings.

Use this if you need to automatically detect and categorize emotions from speech in real-time or from audio recordings.

Not ideal if you require extremely high accuracy (above 50.5%) for critical emotion classification or need to identify emotions from text rather than speech.

virtual-assistants mental-health-monitoring customer-service-analysis human-computer-interaction
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benkhelifamohamedtaher/speech-emotion-recognition"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.