initial config

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+dummy.pdf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import requests
+import json
+from jiwer import cer, wer
+
+pdf_file_path = 'dummy.pdf'
+
+with open("page_transcriptions.json", encoding="utf-8") as f:
+    
+    data = json.load(f)
+
+def send_request(url):
+    
+    try:
+        
+        with open(pdf_file_path, 'rb') as pdf_file:
+            
+            files = {
+                'file': (
+                    'dummy.pdf',
+                    pdf_file,
+                    'application/pdf'
+                )
+            }
+        
+            response = requests.post(url, files=files)
+    
+    except Exception as e:
+        
+        return {"Error message: "f"Error occurred while sending request. Error message: {e}"}
+    
+    try:
+        
+        response_json = response.json()
+        
+    except Exception as e:
+        
+        return {
+            "Error message": e,
+            "Response": response.content
+            }
+    
+    if isinstance(response_json, list):
+        
+        for page in response_json:
+            
+            if isinstance(page, dict):
+            
+                if "page_number" not in page.keys() or "MD_text" not in page.keys():
+                    
+                    return {
+                        "Error message": "Response is not in desired structure. Desired structure: [{'page_number': 1, 'MD_text': 'Extracted text'}]",
+                        "Response": response_json
+                    }
+                    
+                if isinstance(page["page_number"], int) and isinstance(page["MD_text"], str):
+                    
+                    continue
+                
+                else:
+                    
+                    return {
+                        "Error message": "'page_number' should be integer and 'MD_text' should be string.",
+                        "Response": response_json
+                    }
+            
+            else:
+                
+                return {
+                    "Error message": "List should include only dictionaries.",
+                    "Response": response_json
+                }
+            
+        if len(response_json) != len(data):
+            
+            return {
+                "Error message": "The number of pages are not equal between transcription and ground truth.",
+                "Response": response_json
+            }
+            
+        final_metrics = []
+        total_reference = ""
+        total_hypothesis = ""
+        
+        for page in response_json:
+            
+            for transcription in data:
+                
+                if page["page_number"] == transcription["page_number"]:
+                    
+                    reference = transcription['MD_text'].strip()
+                    hypothesis = page['MD_text'].strip()
+                    
+                    total_reference += reference
+                    total_reference += "\n"
+                    total_hypothesis += hypothesis
+                    total_hypothesis += "\n"
+                    
+                    cer_value = cer(reference, hypothesis)
+                    wer_value = wer(reference, hypothesis)
+                    
+                    final_metrics.append({"page_number": page["page_number"], "Character Error Rate (CER)": round(cer_value, 4), "Word Error Rate (WER)": round(wer_value, 4), "MD_text": page['MD_text']})
+            
+        global_cer = cer(total_reference.strip(), total_hypothesis.strip())
+        global_wer = wer(total_reference.strip(), total_hypothesis.strip())
+        
+        final_metrics.append({"Global CER": global_cer, "Global WER": global_wer})
+        
+        return final_metrics
+
+    else:
+        
+        return {
+            "Error message": "Response should be list of dictionaries.",
+            "Response": response_json
+        }
+
+with gr.Blocks() as demo:
+    
+    # Output window (top)
+    # output = gr.Textbox(
+    #     label="Output",
+    #     lines=45,
+    #     interactive=False
+    # )
+
+    output = gr.JSON(
+        label="Output"
+    )
+
+    # Input window (bottom)
+    input_box = gr.Textbox(
+        label="Input",
+        lines=1,
+        placeholder="Type your text here..."
+    )
+
+    send_btn = gr.Button("Send")
+
+    # Click handler
+    send_btn.click(
+        fn=send_request,
+        inputs=input_box,
+        outputs=output
+    )
+
+    # Allow pressing Enter to submit
+    input_box.submit(
+        fn=send_request,
+        inputs=input_box,
+        outputs=output
+    )
+
+demo.launch()

dummy.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5b733d0e21c53a9e40fa6eb9df01bb6898b842f5f13bd42db5624c2a97dd0
+size 49672

page_transcriptions.json

@@ -0,0 +1,18 @@
+[
+    {
+        "page_number": 1,
+        "MD_text": "Paragraph 1"
+    },
+    {
+        "page_number": 2,
+        "MD_text": "Paragraph 2"
+    },
+    {
+        "page_number": 3,
+        "MD_text": "Paragraph 3"
+    },
+    {
+        "page_number": 4,
+        "MD_text": "Paragraph 4"
+    }
+]

requirements.txt

@@ -0,0 +1 @@
+jiwer