artitsu commited on
Commit
1b46209
1 Parent(s): cf7539e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -22,12 +22,12 @@ The training recipe was based on wsj recipe in [espnet](https://github.com/espne
22
 
23
  <!-- Provide a longer summary of what this model is. -->
24
 
25
- This model is Hybrid CTC/Attention model with pre-trained HuBERT as the encoder.
26
 
27
- The model pre-trained on Thai-central, Khummuang, Korat, and Pattani and fine-tuned on Khummuang, Korat, and Pattani.
28
-
29
- 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.)
30
 
 
 
31
 
32
  ## Evaluation
33
 
 
22
 
23
  <!-- Provide a longer summary of what this model is. -->
24
 
25
+ This model is a Hybrid CTC/Attention model with pre-trained HuBERT encoder.
26
 
27
+ 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)
 
 
28
 
29
+ 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).
30
+ (Code is for Thai-Central. Please select the correct model accordingly.)
31
 
32
  ## Evaluation
33