Create README.md

README.md

@@ -0,0 +1,57 @@
+Accuracy: 0.9098119858989424
+precision recall f1-score support
+
+       0     0.9058    0.9148    0.9103      1702
+       1     0.9139    0.9048    0.9094      1702
+
+accuracy                         0.9098      3404
+
+
+macro avg 0.9099 0.9098 0.9098 3404
+weighted avg 0.9099 0.9098 0.9098 3404
+
+
+**Test Set**
+
+
+
+Accuracy: 0.8763517649459294
+precision recall f1-score support
+
+       0     0.7650    0.8786    0.8179      3097
+       1     0.9398    0.8753    0.9064      6705
+
+accuracy                         0.8764      9802
+
+
+macro avg 0.8524 0.8770 0.8621 9802
+weighted avg 0.8846 0.8764 0.8784 9802
+
+
+</details>
+
+---
+
+## 🧪 How to Use
+
+### **Python (PyTorch)**
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_name = "nihad-ask/Arabert-EOU-detection-model"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+text = "تمام و بعدين؟"
+
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model(**inputs)
+prediction = torch.argmax(outputs.logits, dim=1).item()
+
+if prediction == 1:
+    print("End of turn")
+else:
+    print("Speaker will continue")