Update README.md

README.md

@@ -273,24 +273,23 @@ These are greedy WER numbers without external LM. More details on evaluation can
 
 ## Model Fairness Evaluation
 
-As presented in paper "Towards Measuring Fairness in AI: the Casual Conversations Dataset" for Fairness evaluation of Models, we evaluated parakeet-tdt-1.1b on the CausalConversations-v1
-dataset and results are reported as follows: 
+As outlined in the paper "Towards Measuring Fairness in AI: the Casual Conversations Dataset", we assessed the parakeet-tdt-1.1b model for fairness. The model was evaluated on the CausalConversations-v1 dataset, and the results are reported as follows:
 
 ### Gender Bias:
 
 | Gender | Male | Female | N/A | Other |
 | :--- | :--- | :--- | :--- | :--- |
 | Num utterances | 19325 | 24532 | 926 | 33 |
-| % WER | 19.56 | 16.87 | 21.45 | 38.88 |
+| % WER | 17.18 | 14.61 | 19.06 | 37.57 |
 
 ### Age Bias:
 
 | Age Group | $(18-30)$ | $(31-45)$ | $(46-85)$ | $(1-100)$ |
 | :--- | :--- | :--- | :--- | :--- |
 | Num utterances | 15956 | 14585 | 13349 | 43890 |
-| % WER | 17.95 | 18.28 | 17.95 | 18.06 |
-
+| % WER | 15.83 | 15.89 | 15.46 | 15.74 |
 
+(Error rates for fairness evaluation are determined by normalizing both the reference and predicted text, similar to the methods used in the evaluations found at https://github.com/huggingface/open_asr_leaderboard.)
 
 ## NVIDIA Riva: Deployment