| import streamlit as st |
| from transformers import TrOCRProcessor, VisionEncoderDecoderModel |
| from PIL import Image |
|
|
| |
| processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten") |
| model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten") |
|
|
| st.title("OCR Application") |
| uploaded_file = st.file_uploader("Upload an image", type=["png", "jpg", "jpeg"]) |
|
|
| if uploaded_file: |
| |
| image = Image.open(uploaded_file).convert("RGB") |
| st.image(image, caption="Uploaded Image", use_column_width=True) |
|
|
| |
| 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] |
|
|
| |
| st.text("Extracted Text:") |
| st.write(generated_text) |
|
|
