Update README.md

README.md

@@ -76,6 +76,10 @@ Because the GPU has limited power, we used a lightweight model architecture for
 In general, this makes it faster for inference but might show less overall performance.\
 In addition, if the speech includes technical terms or dialect words the model hasn't learned, it may not work as well.
 
+## Demonstration
+
+For quicker inference, you can test the model on Space here: https://huggingface.co/spaces/transiteration/nemo_stt_kz_quartznet15x5
+
 ## References
 
 [1] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
@@ -84,6 +88,3 @@ In addition, if the speech includes technical terms or dialect words the model h
 
 [3] [Kazakh Speech Corpus 2](https://issai.nu.edu.kz/kz-speech-corpus/?version=1.1)
 
-## Demonstration
-
-For quicker inference, you can test the model on Space here: https://huggingface.co/spaces/transiteration/nemo_stt_kz_quartznet15x5