File size: 1,835 Bytes
5e4488c 301a707 86d342d 443e319 86d342d e02beda 86d342d 9317cd1 86d342d 301a707 86d342d 9317cd1 86d342d 3dd9291 86d342d |
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 47 48 49 50 51 52 53 |
import gradio as gr
from PIL import Image
import requests
import torch
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
import logging
# Setup logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
# Load processor and model
model_name = "microsoft/trocr-large-handwritten"
processor = TrOCRProcessor.from_pretrained(model_name)
model = VisionEncoderDecoderModel.from_pretrained(model_name)
# Function to recognize handwriting
def recognize_handwriting(image):
try:
logger.info("Received an image for handwriting recognition.")
if isinstance(image, dict):
image = image.get("image")
if image is None:
logger.error("No image found in the input.")
return "No image found"
image = Image.fromarray(image).convert("RGB")
pixel_values = processor(images=image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
logger.info("Handwriting recognized successfully.")
return generated_text
except Exception as e:
logger.error(f"Error during handwriting recognition: {e}")
return f"Error: {str(e)}"
# Create Gradio interface
with gr.Blocks() as demo:
gr.Markdown("## Handwritten Text Recognition")
with gr.Row():
with gr.Column():
image_input = gr.Image(tool="editor", type="numpy", label="Draw or Upload an Image")
submit_button = gr.Button("Submit")
with gr.Column():
output_text = gr.Textbox(label="Recognized Text")
submit_button.click(fn=recognize_handwriting, inputs=image_input, outputs=output_text)
# Launch the app
if __name__ == "__main__":
demo.launch()
|