Automatic correction of README.md metadata. Contact website@huggingface.co for any question

README.md

@@ -9,11 +9,11 @@ tags:
 - audio
 - automatic-speech-recognition
 - speech
-license: Attribution-ShareAlike 4.0 International
+license: cc-by-sa-4.0
 model-index:
 - name: XLSR Wav2Vec2 Bengali by Arijit
   results:
-  - task: 
+  - task:
       name: Speech Recognition
       type: automatic-speech-recognition
     dataset:
@@ -21,9 +21,9 @@ model-index:
       type: OpenSLR
       args: ben
     metrics:
-       - name: Test WER
-         type: wer
-         value: 32.45
+    - name: Test WER
+      type: wer
+      value: 32.45
 ---
 # Wav2Vec2-Large-XLSR-Bengali
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) Bengali using a subset of 40,000 utterances from [Bengali ASR training data set containing ~196K utterances](https://www.openslr.org/53/). Tested WER using ~4200 held out from training.