Update README.md

README.md

@@ -18,7 +18,7 @@ model-index:
       type: automatic-speech-recognition
     dataset:
       name: MGB5 from ELDA and https://arabicspeech.org/
-      type: ELDA and https://arabicspeech.org/
+      type: ELDA/mgb5_moroccan
       args: ary
     metrics:
        - name: Test WER
@@ -151,7 +151,8 @@ processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-morocc
 model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-moroccan")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\'\\�]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\\"\\\'\\�]'
+
 
 def remove_special_characters(batch):
     batch["text"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).lower() + " "