Update README.md

README.md

@@ -59,7 +59,7 @@ Transformer-based Large Language Model (LLM) integrated with specialized acousti
 
 ## Results
 
-The model achieves satisfactory performance on short-sentence benchmarks, despite not being specifically optimized for short sentences.
+The model achieves satisfactory performance on short-sentence benchmarks, while the model is more focused on long‑form speech generation.
 
 ### Zero-shot TTS performance on LibriSpeech test-clean set