Update README.md

README.md

@@ -24,9 +24,11 @@ The training recipe was based on wsj recipe in [espnet](https://github.com/espne
 
 This model is Hybrid CTC/Attention model with pre-trained HuBERT encoder.
 
-The model pre-trained on Thai-central, Khummuang, Korat, and Pattani and fine-tuned on Khummuang, Korat, and Pattani.
+The model was pre-trained on Thai-central, Khummuang, Korat, and Pattani and fine-tuned on Khummuang, Korat, and Pattani. (Experiment 3 in the paper)
 
-you can demo on colab with [this link](https://colab.research.google.com/drive/1stltGdpG9OV-sCl9QgkvEXZV7fGB2Ixe?usp=sharing). (Please note that you cannot inference >4 seconds of audio with free Google colab)
+We provide some demo code to do inference with this model architecture on colab [here](https://colab.research.google.com/drive/1stltGdpG9OV-sCl9QgkvEXZV7fGB2Ixe?usp=sharing). 
+(Please note that you cannot inference >4 seconds of audio with free Google colab)
+(Code is for Thai-Central. Please select the correct model accordingly.)