Update README.md

README.md

@@ -85,7 +85,7 @@ processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr
 model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\–\…]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\–\\…]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -102,13 +102,12 @@ test_dataset = test_dataset.map(speech_file_to_array_fn)
 # We need to read the aduio files as arrays
 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
+    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)