File size: 1,305 Bytes
b01b23a
7732ecc
b01b23a
 
 
7732ecc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b01b23a
 
7732ecc
b01b23a
 
 
7732ecc
 
b01b23a
 
7732ecc
 
b01b23a
 
 
 
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
39
40
41
42
43
44
45
46
import gradio as gr
from transformers import AutoModel, AutoTokenizer
from PIL import Image
import torch

# Load 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,
    device_map='cuda' if torch.cuda.is_available() else 'cpu',
    use_safetensors=True,
    pad_token_id=tokenizer.eos_token_id
)
model = model.eval()
if torch.cuda.is_available():
    model = model.cuda()

# OCR function
def ocr_from_image(image, ocr_type):
    if image is None:
        return "Please upload an image."
    image_path = "uploaded_image.jpg"
    image.save(image_path)
    res = model.chat(tokenizer, image_path, ocr_type=ocr_type)
    return res

# OCR types to choose from
ocr_types = ["ocr", "format"]

# Gradio interface
iface = gr.Interface(
    fn=ocr_from_image,
    inputs=[
        gr.File(label="Upload Image", file_types=[".jpg", ".jpeg", ".png"]),
        gr.Radio(ocr_types, label="OCR Type", value="ocr")
    ],
    outputs="text",
    title="🧠 GOT-OCR2.0 Transformer OCR",
    description="Upload an image file and select the OCR type: plain text (`ocr`) or formatted (`format`)."
)

if __name__ == "__main__":
    iface.launch()