Update README.md

README.md

@@ -50,7 +50,7 @@ Due to different precisions, there are minor differences in the values generated
 ![plots/metrics_timeseries.png](plots/metrics_timeseries.png)
 
 
-We see this when running the end to end pipeline with the Pytorch model versus the Core ML model (patched the Pyannote pipeline to run the Core ML model instead)
+We see this when running the end to end pipeline with the Pytorch model versus the Core ML model (patched the Pyannote pipeline to run the Core ML model instead). The DER and JER is ~1% compared to the Pytorch model as we're dropping the precision to fp32
 ![plots/pipeline_overview.png](plots/pipeline_overview.png)