m

app.py

@@ -81,6 +81,7 @@ def llm(cleaned_sentence, vqa_answer):
 
 
 torch.hub.download_url_to_file('https://media.istockphoto.com/id/1174602891/photo/two-monkeys-mom-and-cub-eat-bananas.jpg?s=612x612&w=0&k=20&c=r7VXi9d1wHhyq3iAk9D2Z3yTZiOJMlLNtjdVRBEjG7g=', 'monkeys.jpg')
+torch.hub.download_url_to_file('https://img.freepik.com/premium-photo/man-holds-apple-his-hands_198067-740023.jpg', 'apple.jpg')
 
 vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
@@ -103,15 +104,23 @@ def main(image, text):
 image = gr.Image(type="pil")
 question = gr.Textbox(label="Question")
 answer = gr.Textbox(label="Predicted answer")
-examples = [["monkeys.jpg", "How many monkeys are there, in French?"]]
+examples = [
+    ["monkeys.jpg", "What are they doing in French?"],
+    ["apple.jpg", "Qu'est-ce que c'est dans ma main en anglais?"]
+    ]
 
 title = "Cross-lingual VQA"
-description = "Visual Question Answering (VQA) across langages"
+description = "Visual Question Answering (VQA) across Langages"
+article = """
+Supports questions regarding the following langages: 
+['afrikaans', 'albanian', 'amharic', 'arabic', 'armenian', 'azerbaijani', 'basque', 'belarusian', 'bengali', 'bosnian', 'bulgarian', 'catalan', 'cebuano', 'chichewa', 'chinese (simplified)', 'chinese (traditional)', 'corsican', 'croatian', 'czech', 'danish', 'dutch', 'english', 'esperanto', 'estonian', 'filipino', 'finnish', 'french', 'frisian', 'galician', 'georgian', 'german', 'greek', 'gujarati', 'haitian creole', 'hausa', 'hawaiian', 'hebrew', 'hebrew', 'hindi', 'hmong', 'hungarian', 'icelandic', 'igbo', 'indonesian', 'irish', 'italian', 'japanese', 'javanese', 'kannada', 'kazakh', 'khmer', 'korean', 'kurdish (kurmanji)', 'kyrgyz', 'lao', 'latin', 'latvian', 'lithuanian', 'luxembourgish', 'macedonian', 'malagasy', 'malay', 'malayalam', 'maltese', 'maori', 'marathi', 'mongolian', 'myanmar (burmese)', 'nepali', 'norwegian', 'odia', 'pashto', 'persian', 'polish', 'portuguese', 'punjabi', 'romanian', 'russian', 'samoan', 'scots gaelic', 'serbian', 'sesotho', 'shona', 'sindhi', 'sinhala', 'slovak', 'slovenian', 'somali', 'spanish', 'sundanese', 'swahili', 'swedish', 'tajik', 'tamil', 'telugu', 'thai', 'turkish', 'ukrainian', 'urdu', 'uyghur', 'uzbek', 'vietnamese', 'welsh', 'xhosa', 'yiddish', 'yoruba', 'zulu']
+"""
 
 interface = gr.Interface(fn=main, 
                          inputs=[image, question], 
                          outputs=answer, 
                          examples=examples, 
                          title=title,
-                         description=description)
+                         description=description,
+                         article=article)
 interface.launch(debug=True)