arslan911/qwen2-vl-ocr

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

title: Qwen2-VL-2B-OCR emoji: 🔍 colorFrom: blue colorTo: indigo sdk: docker pinned: false ---

Qwen2-VL-2B-OCR

OCR API using Qwen2-VL-2B model for text extraction.

API Endpoints

• —POST /ocr - Base64 image input
• —POST /upload - File upload
• —POST /structured - Structured contact extraction
• —GET /health - Health check

Usage

import requests
import base64

with open("image.png", "rb") as f:
    img_base64 = base64.b64encode(f.read()).decode()

response = requests.post(
    "https://YOUR_SPACE.hf.space/ocr",
    json={"image": img_base64}
)

print(response.json()["text"])