Update README.md

README.md

@@ -150,8 +150,8 @@ This is a "large" versions of Conformer-CTC (around 120M parameters) trained on
 
 This model can be efficiently deployed with [NVIDIA Riva](https://developer.nvidia.com/riva) on premises or with cloud providers.
 Additionally with RIVA you get:
-* streaming speech recognition mode
-* ability to boost specific words (e.g. brand and product names)
+* Streaming speech recognition mode
+* Boost specific words (e.g. brand and product names)
 * Conformer checkpoints trained on proprietary data
 
 ## NVIDIA NeMo