Update app.py

app.py

@@ -9,6 +9,7 @@ import easyocr
 import torch
 import tempfile
 import gradio as gr
+import numpy as np
 
 app = FastAPI()
 
@@ -19,8 +20,8 @@ vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetune
 # Load image captioning model
 captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
 
-# Load EasyOCR reader
-reader = easyocr.Reader(['en', 'fr'])
+# Load EasyOCR reader with English, French, Arabic
+reader = easyocr.Reader(['en', 'fr', 'ar'])
 
 def classify_question(question: str):
     question_lower = question.lower()
@@ -39,7 +40,7 @@ def answer_question_from_image(image, question):
 
     if mode == "ocr":
         try:
-            result = reader.readtext(image)
+            result = reader.readtext(np.array(image))
             text = " ".join([entry[1] for entry in result])
             answer = text.strip() or "No readable text found."
         except Exception as e:
@@ -85,7 +86,7 @@ gui = gr.Interface(
         gr.Textbox(label="Answer", lines=5),
         gr.Audio(label="Answer (Audio)", type="filepath")
     ],
-    title="🧠 Image QA with Voice",
+    title="🧐 Image QA with Voice",
     description="Upload an image and ask a question. Works for OCR, captioning, and VQA."
 )
 
@@ -93,4 +94,4 @@ app = gr.mount_gradio_app(app, gui, path="/")
 
 @app.get("/")
 def home():
-    return RedirectResponse(url="/")
+    return RedirectResponse(url="/")