Update README.md

README.md

@@ -23,10 +23,24 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: []
+         value: 0.49378259125551544
        - name: Test CER
          type: cer
-         value: []
+         value: 0.12470799640610962
+  - task: 
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Robust Speech Event - Dev Data
+      type: speech-recognition-community-v2/dev_data
+      args: mr
+    metrics:
+       - name: Test WER
+         type: wer
+         value: NA
+       - name: Test CER
+         type: cer
+         value: NA
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -39,19 +53,17 @@ It achieves the following results on the evaluation set:
 - Loss: 0.8729
 - Wer: 0.4942
 
-## Model description
-
-More information needed
+### Evaluation Commands
 
-## Intended uses & limitations
+1. To evaluate on mozilla-foundation/common_voice_8_0 with test split
 
-More information needed
+python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-mr-v2 --dataset mozilla-foundation/common_voice_8_0 --config mr --split test --log_outputs
 
-## Training and evaluation data
+2. To evaluate on speech-recognition-community-v2/dev_data
 
-More information needed
+python eval.py --model_id DrishtiSharma/wav2vec2-large-xls-r-300m-mr-v2 --dataset speech-recognition-community-v2/dev_data --config mr --split validation --chunk_length_s 10 --stride_length_s 1
 
-## Training procedure
+Note: Marathi language not found in speech-recognition-community-v2/dev_data!
 
 ### Training hyperparameters