fixed the chars and tabs

README.md

@@ -87,31 +87,31 @@ processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-large-xls
 model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline") 
 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):
-\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\treturn batch
+    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()
+    return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def evaluate(batch):
-\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-\\twith torch.no_grad():
-\\t\\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+    with torch.no_grad():
+        logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
     pred_ids = torch.argmax(logits, dim=-1)
-\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\treturn batch
+    batch["pred_strings"] = processor.batch_decode(pred_ids)
+    return batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)