Update app.py

app.py

@@ -2,39 +2,27 @@ import gradio as gr
 from transformers import BertForSequenceClassification, BertTokenizer
 import torch
 
-# Load the model and tokenizer outside the prediction function, this ensures they are loaded once and used during inference
 model_name = "ArunNyp7/sentimentclassifier-finetuned-bert"
 model = BertForSequenceClassification.from_pretrained(model_name)
 tokenizer = BertTokenizer.from_pretrained(model_name)
 
-# Define the prediction function
 def classify_sentiment(text):
-    # Tokenize the input text
     inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=256)
     
-    # Perform inference
     with torch.no_grad():
         outputs = model(**inputs)
         logits = outputs.logits
         prediction = torch.argmax(logits, dim=-1).item()
 
-    # Map the prediction index to the corresponding sentiment label
     labels = {0: "Negative", 1: "Neutral", 2: "Positive"}
     return labels[prediction]
 
-# Define Gradio Interface using Blocks (this ensures everything is inside a correct Gradio context)
 with gr.Blocks() as demo:
     gr.Markdown("### Sentiment Classification using Fine-Tuned BERT Model")
     
-    # Input box for the text
     text_input = gr.Textbox(label="Enter Text", placeholder="Type here...", lines=2)
-    
-    # Output label for the prediction
     sentiment_output = gr.Label()
-
-    # Define the Button and its action
     submit_btn = gr.Button("Classify Sentiment")
     submit_btn.click(fn=classify_sentiment, inputs=text_input, outputs=sentiment_output)
 
-# Launch the interface
 demo.launch(share=False)