Update README.md

README.md

@@ -17,7 +17,7 @@ model-index:
     dataset:
       name: Common Voice hsb
       type: common_voice
-      args: {lang_id}  
+      args: hsb 
     metrics:
        - name: Test WER
          type: wer
@@ -77,7 +77,7 @@ wer = load_metric("wer")
 processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
 model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-upper-sorbian-mixed")
 model.to("cuda")
-chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�„«»–]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�„«»–]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the audio files as arrays