Update README.md

README.md

@@ -10,7 +10,21 @@ datasets:
 - common_voice
 model-index:
 - name: ''
-  results: []
+  results:
+  - task: 
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition 
+    dataset:
+      name: Common Voice Corpus 8.0
+      type: mozilla-foundation/common_voice_8_0
+      args: mr
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 38.27
+       - name: Test CER
+         type: cer
+         value: 8.91
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,9 +33,15 @@ should probably proofread and complete it, then remove this comment. -->
 # 
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - MR dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5951
-- Wer: 0.5435
+It achieves the following results on the mozilla-foundation/common_voice_8_0 mr test set:
+
+- Without LM
+  + WER: 48.53
+  + CER: 10.63
+   
+- With LM
+  + WER: 38.27
+  + CER: 8.91
 
 ## Model description