fix

README.md

@@ -40,7 +40,7 @@ processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-iris
 model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-irish-basic")
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
-# We need to read the aduio files as arrays
+# We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
 	speech_array, sampling_rate = torchaudio.load(batch["path"])
 	batch["speech"] = resampler(speech_array).squeeze().numpy()
@@ -90,15 +90,15 @@ def remove_special_characters(batch):
 	return batch
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
-# We need to read the aduio files as arrays
+# We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
-	batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+	batch["sentence"] = remove_special_characters(batch)
 	speech_array, sampling_rate = torchaudio.load(batch["path"])
 	batch["speech"] = resampler(speech_array).squeeze().numpy()
 	return batch
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 # Preprocessing the datasets.
-# We need to read the aduio files as arrays
+# We need to read the audio files as arrays
 def evaluate(batch):
 	inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 	with torch.no_grad():