---
title: Recipe Health Analyzer
emoji: 🥗
colorFrom: green
colorTo: green
sdk: gradio
sdk_version: "6.9.0"
app_file: app.py
pinned: false
license: mit
short_description: AI pipeline that classifies recipe health from text or audio
---

# 🥗 Recipe Health Analyzer

An end-to-end AI pipeline that analyzes spoken or written food recipes and classifies them as **Healthy**, **Moderately Healthy**, or **Unhealthy** — with full SHAP-based explainability.

## Pipeline stages

1. **Speech recognition** — OpenAI Whisper transcribes audio input
2. **NLP extraction** — spaCy dependency parsing extracts ingredients, quantities, and cooking methods
3. **Nutrition mapping** — USDA FoodData Central API maps each ingredient to its nutritional profile
4. **Health classification** — RandomForest / XGBoost trained on nutritional features
5. **Explainability** — SHAP values + natural language reasons + actionable suggestions

## Setup

Set your `USDA_API_KEY` in Space Secrets (Settings → Variables and secrets).  
Get a free key at [fdc.nal.usda.gov/api-key-signup.html](https://fdc.nal.usda.gov/api-key-signup.html).  
Without a key the app uses `DEMO_KEY` which is rate-limited to ~30 req/hour.

## Tech stack

`spaCy` · `openai-whisper` · `scikit-learn` · `xgboost` · `shap` · `gradio`