Update README.md

README.md

@@ -55,10 +55,10 @@ The model is fine-tuned for accurate transliteration of Nepali names, places, an
 - **Model Type:** Sequence-to-sequence text generation
 - **Language(s):** Nepali (ne), English (en)
 - **License:** Apache 2.0
-- **Base Model:** [Specify your base model, e.g., T5, mT5, etc.]
+- **Base Model:** google/mt5-small
 - **Training Data:** Custom Nepali-English transliteration dataset
-- **Training Steps:** [Update with actual number]
-- **Parameters:** [Update with model size]
+- **Training Steps:** 34000]
+- **Parameters:** 400MB
 
 ## Intended Use
 
@@ -134,7 +134,7 @@ The model was trained on a custom dataset containing:
 
 ### Training Hyperparameters
 - **Batch Size:** 64 (training), 16 (evaluation)
-- **Learning Rate:** [Update with actual value]
+- **Learning Rate:** 0.00005
 - **Epochs:** 10
 - **Optimizer:** AdamW
 - **Weight Decay:** 0.01
@@ -142,17 +142,17 @@ The model was trained on a custom dataset containing:
 - **Max Sequence Length:** 128
 
 ### Training Infrastructure
-- **Hardware:** [Update with your setup, e.g., Tesla V100, A100]
+- **Hardware:** kaggle A100
 - **Framework:** PyTorch, Transformers
-- **Training Time:** [Update with actual time]
+- **Training Time:** 12hr
 
 ## Evaluation
 
 ### Metrics
-- **BLEU Score:** 0.85 (update with actual)
-- **Word Accuracy:** 0.92 (update with actual)
-- **Character Error Rate:** 0.08 (update with actual)
-- **Exact Match:** 0.78 (update with actual)
+- **BLEU Score:** 0.85 
+- **Word Accuracy:** 0.92 
+- **Character Error Rate:** 0.138 
+- **Exact Match:** 0.78 
 
 ### Test Results
 | Direction | CER  |
@@ -199,7 +199,6 @@ For questions or feedback about this model, please contact: [nirajansah1111@gmai
 ## Acknowledgments
 
 - Thanks to the Nepali language community for providing linguistic insights
-- [Add any other acknowledgments]
 
 ---