Added references for the ParlaSpeech-HR dataset

README.md

@@ -97,7 +97,7 @@ Full config can be found inside the `.nemo` files.
 
 ### Datasets
 
-All the models in this collection are trained on ParlaSpeech-HR v1.0 Croatian dataset, which contains around 1665 hours of training data, 2.2 hours of development and 2.3 hours of test data after data cleaning.
+All the models in this collection are trained on ParlaSpeech-HR v1.0 Croatian dataset [4,5], which contains around 1665 hours of training data, 2.2 hours of development and 2.3 hours of test data after data cleaning.
 
 ## Performance
 
@@ -130,4 +130,8 @@ Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 
 - [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
 
-- [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
+- [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
+
+- [4] [ParlaSpeech-HR dataset](http://hdl.handle.net/11356/1494)
+  
+- [5] [ParlaSpeech-HR - a Freely Available ASR Dataset for Croatian Bootstrapped from the ParlaMint Corpus](https://aclanthology.org/2022.parlaclarin-1.16/)