Create app.py

app.py

@@ -0,0 +1,36 @@
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import string
+import easyocr
+
+# Initialize OCR Reader once
+ocr_reader = easyocr.Reader(['en'])
+
+def extract_text_from_image(image_path):
+    result = ocr_reader.readtext(image_path, detail=0)
+    # Join OCR lines into one string
+    ocr_text = " ".join(result)
+    return ocr_text
+
+def preprocess(text):
+    return text.lower().translate(str.maketrans('', '', string.punctuation)).strip()
+
+def detect_sarcasm(combined_text):
+    MODEL_NAME = "helinivan/english-sarcasm-detector"
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+
+    inputs = tokenizer([preprocess(combined_text)], padding=True, truncation=True, max_length=256, return_tensors="pt")
+    outputs = model(**inputs)
+    probs = outputs.logits.softmax(dim=-1).tolist()[0]
+    sarcasm_pred = probs.index(max(probs))
+    confidence = max(probs)
+
+    return {"sarcasm": bool(sarcasm_pred), "confidence": confidence}
+
+# Example usage:
+ocr_text = extract_text_from_image('path_to_image.jpg')
+typed_text = "Your favorite sarcastic phrase here"
+
+combined = ocr_text + " " + typed_text
+result = detect_sarcasm(combined)
+print(result)