Update README.md

README.md

@@ -24,10 +24,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 19.74
+         value: 17.57
        - name: Test CER
          type: cer
-         value: 2.89
+         value: 3.86
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -43,7 +43,6 @@ model-index:
          type: cer
          value: 
 ---
-
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
@@ -56,7 +55,7 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+Note: another version of this model is available with a KenLM 3gram model. This model performs better than this model. See https://huggingface.co/RuudVelo/wav2vec2-large-xls-r-1b-cv8-mt-lm
 
 ## Intended uses & limitations
 
@@ -114,6 +113,7 @@ training_args = TrainingArguments(
 | 0.7931        | 26.66 | 800  | 0.2377          | 0.2298 |
 | 0.5364        | 39.98 | 1200 | 0.2210          | 0.1974 |
 
+Note that the test WER of 19.74 is different than the above reported 17.57. This was due to a bug which was found while processing files with an older version of the datasets library. The right library is listed below.
 
 ### Framework versions