Update app.py

app.py

@@ -3,24 +3,26 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
 # Load model and tokenizer from Hugging Face
-# model_name = "your-username/your-model-name"  # replace with your model path
-# tokenizer = AutoTokenizer.from_pretrained(model_name)
-# model = AutoModelForSequenceClassification.from_pretrained(model_name)
+model_name = "iro-malta07/distilbert-base-german-lang-level-class"  # replace with your model path
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
 # Use id2label from the config
-# id2label = model.config.id2label
+id2label = model.config.id2label
 
 # Inference function
 def classify_text(text):
-    # 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)
-       # pred_class = torch.argmax(probs, dim=1).item()
-        #confidence = probs[0, pred_class].item()
-   # label = id2label[pred_class]
-    # return f"Predicted Level: {label} (Confidence: {confidence:.2f})"
-    return f"Predicted Level: a2 (Confidence: 0.5)"
+    if not text.endswith("."):
+        text = text + "."
+    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)
+        pred_class = torch.argmax(probs, dim=1).item()
+        confidence = probs[0, pred_class].item()
+    label = id2label[pred_class]
+    return f"Predicted Level: {label} (Confidence: {confidence:.2f})"
+   
 
 # Gradio interface
 demo = gr.Interface(