Update app.py

app.py

@@ -1,6 +1,5 @@
 #From 
 import torch 
-import re 
 import gradio as gr
 from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
 
@@ -12,34 +11,34 @@ feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
+def predict(image, max_length=64, num_beams=4):
+    image = image.convert('RGB')
+    image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
+    clean_text = lambda x: x.replace('','').split('\n')[0]
+    caption_ids = model.generate(image, max_length=max_length, num_beams=num_beams)[0]
+    caption_text = clean_text(tokenizer.decode(caption_ids, skip_special_tokens=True))
+    return caption_text
 
-def predict(image,max_length=64, num_beams=4):
-  image = image.convert('RGB')
-  image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
-  clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
-  caption_ids = model.generate(image, max_length = max_length)[0]
-  caption_text = clean_text(tokenizer.decode(caption_ids))
-  return caption_text 
+input_image = gr.inputs.Image(label="Upload your Image", type='pil', optional=True)
+output_text = gr.outputs.Textbox(type="text", label="Captions")
 
+examples = [f"example{i}.jpg" for i in range(1, 7)]
 
-
-input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
-output = gr.outputs.Textbox(type="auto",label="Captions")
-examples = [f"example{i}.jpg" for i in range(1,7)]
-
-description= "Image captioning application made using transformers"
+description = "Image captioning application made using transformers"
 title = "Image Captioning 🖼️"
+article = "Created By : Shreyas Dixit"
 
-article = "Created By : Shreyas Dixit "
-
+# Create the Gradio interface
 interface = gr.Interface(
-        fn=predict,
-        inputs = input,
-        theme="grass",
-        outputs=output,
-        examples = examples,
-        title=title,
-        description=description,
-        article = article,
-    )
-interface.launch(debug=True)
+    fn=predict,
+    inputs=input_image,
+    outputs=output_text,
+    examples=examples,
+    title=title,
+    description=description,
+    article=article,
+    theme="grass"
+)
+
+# Launch the interface
+    interface.launch(debug=True,share=True)