Update README.md

README.md

@@ -51,30 +51,30 @@ processor = Wav2Vec2Processor.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mo
 model = Wav2Vec2ForCTC.from_pretrained("bayartsogt/wav2vec2-large-xlsr-mongolian-v1")
 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 aduio 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
 
-\tpred_ids = torch.argmax(logits, dim=-
-\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\treturn batch
+     pred_ids = torch.argmax(logits, dim=-
+     batch["pred_strings"] = processor.batch_decode(pred_ids)
+     return batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)