Update README.md

README.md

@@ -36,6 +36,7 @@ The easiest way to test differing audio context is to use whisper.cpp with the `
 
 ## Metrics
 Speed was evaluated using TensorRT-LLM using In-flight Batching
+Dynamic context was padded with additional 128 context for stability
 
 | Model Name                                                       | WER on Earnings22    | Relative Speed |
 |------------------------------------------------------------------|--------|----------------|