required files for OCR tool

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,14 @@
----
-title: OCR For Hindi English
-emoji: 🐠
-colorFrom: indigo
-colorTo: gray
-sdk: gradio
-sdk_version: 4.44.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Ocr Gradio(Developed by Tirtha Debnath, Bangladesh)
+emoji: 🐢
+colorFrom: blue
+colorTo: red
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+license: mit
+short_description: IIT Roorkee   
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,111 @@
+# import all required libraries after doing research
+import gradio as gr
+from PIL import Image
+from surya.ocr import run_ocr  # dedicated GOT_OCR_2.0 for hindi languages
+from surya.model.detection.model import load_model as load_det_model, load_processor as load_det_processor
+from surya.model.recognition.model import load_model as load_rec_model
+from surya.model.recognition.processor import load_processor as load_rec_processor
+import re  # recognized hindi encoded pattern
+from transformers import AutoModel, AutoTokenizer
+import torch
+import tempfile
+import os
+
+# device = "cuda"
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+print(device)
+# load_desirable_model
+got_model_name = 'tdnathmlenthusiast/got-ocr-2.0-modified-hindi-version'
+
+det_processor, det_model = load_det_processor(), load_det_model()
+det_model.to(device)
+rec_model, rec_processor = load_rec_model(), load_rec_processor()
+rec_model.to(device)
+
+# tokenized to extract individual character
+tokenizer = AutoTokenizer.from_pretrained(
+    got_model_name, trust_remote_code=True, device_map=device)
+got_model = AutoModel.from_pretrained(
+    got_model_name, trust_remote_code=True, low_cpu_mem_usage=True, device_map=device, use_safetensors=True)
+got_model = got_model.eval().to(device)
+
+
+# function to extract hindi & english
+def extract_hindi(text):
+    # Unicode range for Devanagari script
+    hindi_pattern = re.compile(r'[\u0900-\u097F]+')
+    hindi_words = hindi_pattern.findall(text)
+    return ' '.join(hindi_words)
+
+
+def process_image(image):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as temp_file:
+        image.save(temp_file.name)
+        temp_file_path = temp_file.name
+
+    image = Image.open(temp_file_path)
+    image = image.convert("RGB")
+
+    langs = ["hi"]
+    surya_predictions = run_ocr(
+        [image], [langs], det_model, det_processor, rec_model, rec_processor)
+
+    surya_text_list = re.findall(r"text='(.*?)'", str(surya_predictions[0]))
+    surya_text = '\n'.join(surya_text_list)
+    surya_text = extract_hindi(surya_text)
+
+    got_res = got_model.chat(tokenizer, temp_file_path, ocr_type='ocr')
+
+    combined_text = f"<h2> Hindi Text (Surya OCR) </h2> <br>{surya_text}<br> <br> <h2> English Text (GOT OCR) </h2> <br> {got_res}"
+
+    if os.path.exists(temp_file_path):
+        os.remove(temp_file_path)
+
+    return combined_text
+
+# code to search words like documents
+
+
+def highlight_search(text, query):
+    if query:
+        pattern = re.compile(re.escape(query), re.IGNORECASE)
+        highlighted_text = pattern.sub(
+            lambda m: f"<span style='background-color: limegreen;'>{m.group(0)}</span>", text)
+        return highlighted_text
+    return text
+
+
+with gr.Blocks() as ocr_interface:
+    gr.Markdown("# OCR Application for Hindi & English")
+    gr.Markdown(
+        "Upload an image for OCR processing.(Takes a little bit time or sometimes a lot due to the limitation of the resources)")
+
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(
+                type="pil", label="Upload an Image(Hindi/English/Hindi+English)")
+            run_ocr_button = gr.Button("Run OCR")
+
+        with gr.Column():
+            output_text = gr.HTML(label="Extracted Text in Hindi & English")
+            query_input = gr.Textbox(
+                label="Search in extracted text", placeholder="Type to search...")
+            search_button = gr.Button("Search")
+
+    def process_and_display(image):
+        combined_text = process_image(image)
+        return combined_text
+
+    def search_text(combined_text, query):
+        highlighted = highlight_search(combined_text, query)
+        return highlighted
+
+    run_ocr_button.click(fn=process_and_display,
+                         inputs=image_input, outputs=output_text)
+
+    search_button.click(fn=search_text, inputs=[
+                        output_text, query_input], outputs=output_text)
+
+ocr_interface.launch()
+
+# Developed by Tirtha Debnath.

requirements.txt

@@ -0,0 +1,11 @@
+streamlit
+Pillow
+surya-ocr
+torch
+transformers
+tiktoken
+torchvision
+verovio
+accelerate
+rapidfuzz
+gradio