Without GPU

app.py

@@ -11,7 +11,7 @@ nltk.download('stopwords')
 
 # load the model and tokenizer
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to("cuda")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
 tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 reader = easyocr.Reader(['en'])
@@ -24,7 +24,7 @@ def generate_hashtags(image_file):
     image = Image.open(image_file).convert('RGB')
 
     # extract image features
-    inputs = processor(image, return_tensors="pt").to("cuda")
+    inputs = processor(image, return_tensors="pt")
 
     output_ids = model.generate(**inputs)
     # out_text = processor.decode(out[0], skip_special_tokens=True)