Update README.md

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 24.944955
+         value: 23.736641
 ---
 
 # Wav2Vec2-Large-XLSR-53-Hindi-Marathi
@@ -103,7 +103,7 @@ import re
 test = Dataset.from_csv('test.csv')
 
 
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�\\\\\\\\।]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\।]'
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
@@ -145,7 +145,7 @@ import numpy as np
 import re
 from datasets import load_dataset
 
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�\\\\\\\\।]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\।]'
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
@@ -179,7 +179,7 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=test_data["pred_strings"
 
 Link to eval notebook : https://colab.research.google.com/drive/1nZRTgKfxCD9cvy90wikTHkg2il3zgcqW#scrollTo=cXWFbhb0d7DT
 
-WER :  24.944955% (OpenSLR Hindi+Marathi Test set : https://filebin.net/snrz6bt13usv8w2e/test_large.csv)
+WER :  23.736641% (OpenSLR Hindi+Marathi Test set : https://filebin.net/snrz6bt13usv8w2e/test_large.csv)
 
 
-WER: 49.303944% (Common Voice Hindi Test Split)
+WER: 44.083527% (Common Voice Hindi Test Split)