readme

README.md

@@ -26,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 Icefall conformer-ctc3 based recipe (https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/conformer_ctc3) trained Estonian ASR model using ERR2020 dataset
 - WER on ERR2020: 12.1
-- WER on mozilla commonvoice_11: 24.5
+- WER on mozilla commonvoice_11: 23.2
 
  
 For usage:
@@ -39,7 +39,7 @@ For usage:
 
 ## Model description
 
-ASR model for Estonian, uses Estonian Public Broadcasting data ERR2020 data (around 230 hours of audio)
+ASR model for Estonian, uses Estonian Public Broadcasting data ERR2020 data (around 340 hours of audio)
 
 ## Intended uses & limitations