Update README.md

README.md

@@ -22,27 +22,11 @@ datasets:
     metrics:
        - name: Test WER
          type: wer
-         value: 48.3
+         value: 48.5
        - name: Test CER
          type: cer
-         value: 18.5
-  - task:
-      name: Automatic Speech Recognition 
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 8
-      type: mozilla-foundation/common_voice_8_0
-      args: sr
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 48.3
-       - name: Test CER
-         type: cer
-         value: 18.5
+         value: 18.4
 ---
-<!-- 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. -->
 
 # Serbian wav2vec2-xls-r-300m-sr-cv8
 
@@ -52,24 +36,20 @@ It achieves the following results on the evaluation set:
 - Wer: 0.4825
 - Cer: 0.1847
 
+Evaluation on mozilla-foundation/common_voice_8_0 gave the following results:
+
+- WER: 0.48530097993467103
+- CER: 0.18413288165227845
+
 Evaluation on  speech-recognition-community-v2/dev_data gave the following results:
 
 - WER: 0.9718373107518604
 - CER: 0.8302740620263108
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
+The model can be evaluated using the attached `eval.py` script:
+```
+python eval.py --model_id comodoro/wav2vec2-xls-r-300m-sr-cv8 --dataset mozilla-foundation/common-voice_8_0 --split test --config sr
+```
 
 ### Training hyperparameters