Update README.md

README.md

@@ -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)
 
@@ -156,17 +156,17 @@ test_dataset = test_dataset.map(speech_file_to_array_fn)
 
 def evaluate(batch):
 
-inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
-
-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)
-
-batch["pred_strings"] = processor.batch_decode(pred_ids)
-
-return batch
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    
+    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)
+    
+    batch["pred_strings"] = processor.batch_decode(pred_ids)
+    
+    return batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)