| Feature | Spec |
|---|---|
| 🧠 Base Model | Florence-2-base |
| 📦 Size | 232M params (~500MB) |
| ⚡ Speed | <200ms on CPU |
| 🌍 Languages | English, Indonesian |
| 🔊 Output | Text + Voice (TTS) |
| Mode | Use Case | Example Output |
|---|---|---|
| 👁️ Scene | Describe surroundings | "Kitchen with wooden table. Stove on left." |
| 😊 Emotion | Read facial expressions | "Happy. They seem in good spirits!" |
| 💊 Medicine | Read medicine labels | "Dosage: 500mg. Take as prescribed." |
| 💵 Currency | Identify money | "Rp 50,000. Blue-colored note." |
| 📖 Text | OCR for signs/labels | "EXIT sign detected." |
1from dara import DARA
2
3# Initialize
4dara = DARA()
5
6# Use any mode
7result = dara.detect(
8 image_path="photo.jpg",
9 mode="scene", # scene | emotion | medicine | currency | text
10 language="en" # en | id
11)
12
13print(result["result"]) # Text description
14# Audio saved to result["audio"]1pip install torch transformers pillow gtts
2git clone https://github.com/ardelyo/dara.git🏥 Medical Disclaimer: Medicine mode is for reference only. Always consult healthcare professionals.
🔒 Privacy: All processing runs locally. No images are uploaded.
| Device | Latency |
|---|---|
| CPU (i7) | ~180ms |
| GPU (RTX 3060) | ~45ms |
| Mobile | ~320ms |
1@misc{dara2024,
2 title={DARA: Detect & Assist Recognition AI},
3 author={Ardelyo},
4 year={2024},
5 url={https://github.com/ardelyo/dara}
6}