Update app.py

app.py

@@ -1,20 +1,23 @@
 import streamlit as st
-from transformers import pipeline
-from PIL import Image
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+# Load pre-trained model and tokenizer
+model_name = "username/my_spam_detector"  # replace 'username' with your Hugging Face account name
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
-st.title("Hot Dog? Or Not?")
+st.title("Spam Detector")
 
-file_name = st.file_uploader("Upload a hot dog candidate image")
+text = st.text_input("Enter a text")
 
-if file_name is not None:
-    col1, col2 = st.columns(2)
+if st.button('Predict'):
+    # Tokenize the input text
+    inputs = tokenizer(text, return_tensors='pt')
 
-    image = Image.open(file_name)
-    col1.image(image, use_column_width=True)
-    predictions = pipeline(image)
+    # Get model's prediction
+    outputs = model(**inputs)
+    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
 
-    col2.header("Probabilities")
-    for p in predictions:
-        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+    # Show prediction
+    st.write(f"The probability of the text being spam is {probs[0][1].item() * 100:.2f}%.")