Update README.md

README.md

@@ -36,7 +36,6 @@ A lightweight, multilingual DistilBERT model fine-tuned for End-of-Utterance (EO
 - **F1 Score**: 0.9150
 - **Precision**: 0.9796
 - **Recall**: 0.8584
-- **Optimal Threshold**: 0.86
 
 ## Model Variants
 
@@ -112,7 +111,7 @@ text = "Thanks for your help!"
 inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=128)
 outputs = model(**inputs)
 probs = torch.softmax(outputs.logits, dim=-1)
-is_eou = probs[0][1] > 0.86  # Using optimal threshold
+is_eou = probs[0][1] > 0.5  # Using optimal threshold
 
 print(f"EOU Probability: {probs[0][1]:.3f}")
 print(f"Is EOU: {is_eou}")
@@ -147,7 +146,7 @@ logits = outputs[0][0]
 
 # Calculate probability
 probs = np.exp(logits) / np.sum(np.exp(logits))
-is_eou = probs[1] > 0.86  # Using optimal threshold
+is_eou = probs[1] > 0.5 # Using optimal threshold
 
 print(f"EOU Probability: {probs[1]:.3f}")
 print(f"Is EOU: {is_eou}")
@@ -169,10 +168,10 @@ This model is designed for:
 
 The model was trained using knowledge distillation on a multilingual dataset:
 
-- **English**: 16,258 samples
-- **Hindi**: 12,103 samples  
-- **Spanish**: 7,963 samples
-- **Total**: ~36K samples
+- **English**: 76,258 samples
+- **Hindi**: 75,103 samples  
+- **Spanish**: 75,963 samples
+- **Total**: ~211K samples
 
 ### Training Configuration
 
@@ -202,9 +201,8 @@ The model was evaluated on:
 ### Inference Speed
 
 Approximate inference times (CPU, single sample):
-- PyTorch: ~15-20ms
-- ONNX Optimized: ~8-12ms
-- ONNX Quantized INT8: ~5-8ms
+- ONNX Optimized: ~70-120ms
+- ONNX Quantized INT8: ~40-50ms
 
 *Note: Actual speeds vary by hardware*