Update app.py

app.py

@@ -6,7 +6,7 @@ from PIL import Image
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-# English to Persian model
+# English to Persian Translation model
 fa_en_translation_tokenizer = MT5Tokenizer.from_pretrained("SeyedAli/Persian-to-English-Translation-mT5-V1")
 fa_en_translation_model = MT5ForConditionalGeneration.from_pretrained("SeyedAli/Persian-to-English-Translation-mT5-V1").to(device)
 
@@ -16,7 +16,7 @@ def run_fa_en_transaltion_model(input_string, **generator_args):
     output = fa_en_translation_tokenizer.batch_decode(res, skip_special_tokens=True)
     return output
 
-# Persian to English model
+# Persian to English Translation model
 en_fa_translation_tokenizer = MT5Tokenizer.from_pretrained("SeyedAli/English-to-Persian-Translation-mT5-V1")
 en_fa_translation_model = MT5ForConditionalGeneration.from_pretrained("SeyedAli/English-to-Persian-Translation-mT5-V1").to(device)
 
@@ -38,13 +38,13 @@ def VQA(image,text):
         # Load the image file using Pillow
         image = Image.open(temp_image_file.name)
         # prepare inputs
-        encoding = processor(image, run_fa_en_transaltion_model(text), return_tensors="pt")
+        encoding = VQA_processor(image, run_fa_en_transaltion_model(text), return_tensors="pt")
         # forward pass
-        outputs = model(**encoding)
+        outputs = VQA_model(**encoding)
         logits = outputs.logits
         idx = logits.argmax(-1).item()
         output=[]
-        for item in model.config.id2label[idx]:
+        for item in VQA_model.config.id2label[idx]:
             output.append(run_en_fa_transaltion_model(item))
         return output