Update README.md

README.md

@@ -270,6 +270,28 @@ The following tables summarizes the performance of the available models in this
 
 These are greedy WER numbers without external LM. More details on evaluation can be found at [HuggingFace ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard)
 
+
+## 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: 
+
+### Gender Bias:
+
+| Gender | Male | Female | N/A | Other |
+| :--- | :--- | :--- | :--- | :--- |
+| Num utterances | 19325 | 24532 | 926 | 33 |
+| % WER | 19.56 | 16.87 | 21.45 | 38.88 |
+
+### 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 |
+
+
+
 ## NVIDIA Riva: Deployment
 
 [NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. 
@@ -295,6 +317,8 @@ Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 
 [6] [HuggingFace ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard)
 
+[7] [Towards Measuring Fairness in AI: the Casual Conversations Dataset](https://arxiv.org/abs/2104.02821)
+
 
 ## Licence