Add a cautionary note on input audio length

Signed-off-by: Fujimoto Seiji <[email protected]>

README.md

@@ -24,6 +24,8 @@ This model provides end-to-end Japanese speech recognition based on
 * The training recipe is available on
   [k2-fsa/icefall](https://github.com/k2-fsa/icefall/tree/master/egs/reazonspeech/ASR).
 
+Note that this model can process Japanese audio clips up to ~30 seconds.
+
 ## Usage
 
 We recommend to use this model through our