Update app.py

app.py

@@ -1,33 +1,30 @@
-import os
-from gtts import gTTS
-from pdfminer.high_level import extract_text
 import gradio as gr
-import os
+from transformers import ImageClassificationPipeline, PerceiverForImageClassificationConvProcessing, PerceiverFeatureExtractor
+import torch
 
+torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+torch.hub.download_url_to_file('https://storage.googleapis.com/perceiver_io/dalmation.jpg', 'dog.jpg')
+ 
+feature_extractor = PerceiverFeatureExtractor.from_pretrained("deepmind/vision-perceiver-conv")
+model = PerceiverForImageClassificationConvProcessing.from_pretrained("deepmind/vision-perceiver-conv")
 
-def pdf_to_text(file_obj):
-    text = extract_text(file_obj.name)
-    myobj = gTTS(text=text, lang='en', slow=False) 
-    myobj.save("test.wav") 
-    return 'test.wav'
+image_pipe = ImageClassificationPipeline(model=model, feature_extractor=feature_extractor)
 
+def classify_image(image):
+  results = image_pipe(image)
+  # convert to format Gradio expects
+  output = {}
+  for prediction in results:
+    predicted_label = prediction['label']
+    score = prediction['score']
+    output[predicted_label] = score
+  return output
 
-examples = [
-    [os.path.abspath("short-pdf.pdf")],
-    [os.path.abspath("long-pdf.pdf")]
-]
+image = gr.inputs.Image(type="pil")
+label = gr.outputs.Label(num_top_classes=5)
+examples = [["cats.jpg"], ["dog.jpg"]]
+title = "Interactive demo: Perceiver for image classification"
+description = "Demo for classifying images with Perceiver IO. To use it, simply upload an image or use the example images below and click 'submit' to let the model predict the 5 most probable ImageNet classes. Results will show up in a few seconds."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2107.14795'>Perceiver IO: A General Architecture for Structured Inputs & Outputs</a> | <a href='https://deepmind.com/blog/article/building-architectures-that-can-handle-the-worlds-data/'>Official blog</a></p>"
 
-
-iface = gr.Interface(fn = pdf_to_text,
-                     inputs = 'file',
-                     outputs = 'audio', 
-                     title = 'PDF to Audio Application',
-                     description = 'A simple application to convert PDF files in audio speech. Upload your own file, or click one of the examples to load them.',
-                     article = 
-                        '''<div>
-                            <p style="text-align: center"> All you need to do is to upload the pdf file and hit submit, then wait for compiling. After that click on Play/Pause for listing to the audio. The audio is saved in a wav format.</p>
-                        </div>''',
-                     examples=examples
-                    )
-
-iface.launch()
+gr.Interface(fn=classify_image, inputs=image, outputs=label, title=title, description=description, examples=examples, enable_queue=True).launch(debug=True)