Update README.md

README.md

@@ -18,14 +18,11 @@ model-index:
 
       args: vi
     metrics:
-       - name: Test WER
+       - name: Test WER (with Language model)
          type: wer
          value: 56.57
 ---
 
-<!-- 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. -->
-
 # xls-asr-vi-40h
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common voice 7.0 vi & private dataset.
@@ -33,17 +30,12 @@ It achieves the following results on the evaluation set (Without Language Model)
 - Loss: 1.1177
 - Wer: 60.58
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
+## Evaluation
+Please run the eval.py file
 
-More information needed
+```bash
+!python eval_custom.py --model_id geninhu/xls-asr-vi-40h --dataset mozilla-foundation/common_voice_7_0 --config vi --split test
+```
 
 ## Training procedure