Upload 2 files

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load models
+model_paths = {
+    "BERT": "models/bert_model",
+    "XLNet": "models/xlnet_model",
+    "GPT-2": "models/gpt2_model"
+}
+
+models = {}
+tokenizers = {}
+
+for name, path in model_paths.items():
+    tokenizers[name] = AutoTokenizer.from_pretrained(path)
+    models[name] = AutoModelForSequenceClassification.from_pretrained(path)
+    models[name].eval()
+
+# Emotion labels (adjust based on your dataset!)
+labels = ["anger", "joy", "sadness", "fear", "love", "surprise"]
+
+def classify(text, model_choice):
+    tokenizer = tokenizers[model_choice]
+    model = models[model_choice]
+
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+        top_prob, top_idx = torch.max(probs, dim=1)
+
+    return f"Predicted: {labels[top_idx.item()]} ({top_prob.item():.2f})"
+
+iface = gr.Interface(
+    fn=classify,
+    inputs=[
+        gr.Textbox(lines=3, placeholder="Enter text here...", label="Text"),
+        gr.Radio(choices=["BERT", "XLNet", "GPT-2"], label="Choose Model")
+    ],
+    outputs="text",
+    title="Emotion Classifier (BERT / XLNet / GPT-2)"
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+torch
+gradio