README.md

metadata

title: Multimodal Affect Screening
emoji: 🙂
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
license: mit

Multimodal Affect & Well-being Screening

Facial + speech emotion recognition (TensorFlow) with a PHQ-9 questionnaire, served with Flask. Capture runs in the browser (webcam / microphone) and is classified server-side.

Emotion signals are a demo cue, not a clinical diagnosis.

Source & full write-up: https://github.com/parthhh-a/Detection-of-Anxiety-and-Depression