Update README.md

README.md

@@ -18,14 +18,14 @@ In this release the entire encoder was frozen. Subsequent releases will not do t
 generalization to other types of data (i.e not parliamentary speeches) is kept when not freezing
 the encoder.
 
-## Evaluation
+## Evaluation (test)
 
-* RixVox test WER: `22.59`
-* RixVox test WER (normalized*): `19.33`
-* Common Voice test 11 WER: `18.03`
-* Common Voice test 11 WER (normalized*): `13.23`
-* Fleurs WER: test `14.26`
-* Fleurs WER test (normalized*): `8.99`
+* RixVox WER: `22.59`
+* RixVox WER (normalized*): `19.33`
+* Common Voice 11 WER: `18.03`
+* Common Voice 11 WER (normalized*): `13.23`
+* Fleurs WER: `14.26`
+* Fleurs WER (normalized*): `8.99`
 
 *) Normalization is done by applying the following to source and generated texts:
 
@@ -34,7 +34,7 @@ def normalize(s):
     return ' '.join([ x for x in sub('[^0-9a-zåäöA-ZÅÄÖ ]', ' ', s.lower().replace('é', 'e')).split() ])
 ```
 
-In comparison the original Whisper large gets `30.57`/`25.59`, `18.76`/`15.00`, and `14.53`/`9.19` respectively.
+In comparison the original Whisper large gets `30.56`/`25.58`, `18.76`/`15.00`, and `14.53`/`9.19` respectively.
 
 ## Training