Update README.md

README.md

@@ -66,14 +66,14 @@ wer = load_metric("wer")
 processor = Wav2Vec2Processor.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-rm-vallader")
 model = Wav2Vec2ForCTC.from_pretrained("anuragshas/wav2vec2-large-xlsr-53-rm-vallader")
 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 aduio files as arrays
 def speech_file_to_array_fn(batch):
     batch["sentence"] = re.sub('’ ',' ',batch["sentence"])
     batch["sentence"] = re.sub(' ‘',' ',batch["sentence"])
-    batch["sentence"] = re.sub('’|‘','\\'',batch["sentence"])
+    batch["sentence"] = re.sub('’|‘','\'',batch["sentence"])
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
     speech_array, sampling_rate = torchaudio.load(batch["path"])
     batch["speech"] = resampler(speech_array).squeeze().numpy()