Update model card with detailed information

README.md

@@ -55,19 +55,18 @@ print(transcription)
 
 ## Training Details
 
-- **Training Data**: openslr37
+- **Training Data**: private dataset
 - **Language**: Bengali (bn)
 - **Training Steps**: 5000
 - **Batch Size**: 4
 - **Learning Rate**: 1e-05
 - **Optimizer**: AdamW
-- **eval_wer**: 0.3080158337456705
+- **eval_wer**: 0.687061
 
 ## Limitations
 
 - Optimized for Bengali speech only
 - Works best with clear audio at 16kHz sampling rate
-- May not perform well on heavily accented or noisy audio
 
 
 ## Acknowledgments