Update README.md

README.md

@@ -50,10 +50,10 @@ We measure the inference speed with four different Japanese speech audio on MacB
 
 | audio file | audio duration (min)| inference time (sec) |
 |--|---------------------|-------------|
-|audio 1 | 50.3 | 581       |
-|audio 2 | 5.6  | 41       |
-|audio 3 | 4.9  | 30       |
-|audio 4 | 5.6  | 35       |
+|audio 1 | 50.3 | 2601       |
+|audio 2 | 5.6  | 73       |
+|audio 3 | 4.9  | 141       |
+|audio 4 | 5.6  | 126       |
 
 
 ### Quantized Model