Update README.md

README.md

@@ -34,7 +34,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 5.53
+      value: 5.66
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -48,7 +48,7 @@ model-index:
     metrics:
     - name: Test WER P&C
       type: wer
-      value: 6.92
+      value: 8.06
 ---
 
 # NVIDIA FastConformer-Hybrid Large (ua)
@@ -148,13 +148,13 @@ The following tables summarizes the performance of the available models in this
 a) On data without Punctuation and Capitalization with Transducer decoder
 | **Version** |     **Tokenizer**     | **Vocabulary Size** | **MCV12 TEST** |
 |:-----------:|:---------------------:|:-------------------:|:-------------:|
-|    1.0.0    | SentencePiece Unigram |         512         |      5.53     |
+|    1.0.2    | SentencePiece Unigram |         512         |      5.66     |
 
 
 b) On data with Punctuation and Capitalization with Transducer decoder
 | **Version** |     **Tokenizer**     | **Vocabulary Size** | **MCV12 TEST** |
 |:-----------:|:---------------------:|:-------------------:|:-------------:|
-|    1.0.0    | SentencePiece Unigram |         512         |      6.92     |
+|    1.0.2    | SentencePiece Unigram |         512         |      8.06     |
 
 
 ## Limitations