Update README.md

README.md

@@ -82,11 +82,11 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def speech_file_to_array_fn(batch):
 
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+  speech_array, sampling_rate = torchaudio.load(batch["path"])
 
-\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+  batch["speech"] = resampler(speech_array).squeeze().numpy()
 
-\treturn batch
+  return batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 
@@ -94,7 +94,7 @@ inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tens
 
 with torch.no_grad():
 
-\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+  logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -130,7 +130,7 @@ model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xls
 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'
+chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'
 
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
@@ -140,13 +140,13 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 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)
 
@@ -156,17 +156,17 @@ test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 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():
+with torch.no_grad():
 
-\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+  logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
-    pred_ids = torch.argmax(logits, dim=-1)
+pred_ids = torch.argmax(logits, dim=-1)
 
-\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+batch["pred_strings"] = processor.batch_decode(pred_ids)
 
-\treturn batch
+return batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)