Update README.md

README.md

@@ -80,14 +80,15 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "el", split="test") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "el", split="test") 
 wer = load_metric("wer")
 
 processor = Wav2Vec2Processor.from_pretrained("PereLluis13/wav2vec2-large-xlsr-53-greek") 
 model = Wav2Vec2ForCTC.from_pretrained("PereLluis13/wav2vec2-large-xlsr-53-greek") 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\'\\\\\\\\�]'  
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�]'
+
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)