File size: 1,407 Bytes
b42b1aa 8434495 f2460f7 c920662 dec293d 9184993 dec293d e8ba698 8434495 dec293d e8ba698 3534c83 dec293d e8ba698 dec293d e8ba698 76581dc e8ba698 8434495 e8ba698 dec293d e8ba698 dec293d ce4c6de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
import torch
from transformers import AutoModel, AutoTokenizer
from PIL import Image
import gradio as gr
import tempfile
# Load the OCR model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True,
low_cpu_mem_usage=True,
pad_token_id=tokenizer.eos_token_id).eval()
# Check if GPU is available and use it, else use CPU
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)
# Function to perform OCR on the image
def perform_ocr(image):
# Save the image to a temporary file
with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as temp_file:
image.save(temp_file.name) # Save the image
temp_image_path = temp_file.name # Get the file path for the saved image
# Perform OCR using the model
result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
return result
# Create the Gradio interface using the new syntax
interface = gr.Interface(
fn=perform_ocr,
inputs=gr.Image(type="pil"), # Updated to gr.Image
outputs=gr.Textbox(), # Updated to gr.Textbox
title="OCR Web App",
description="Upload an image to extract text using the GOT-OCR2.0 model."
)
# Launch the app
interface.launch() |