Update README.md

fix chars_to_ignore_regex

README.md

@@ -86,8 +86,7 @@ processor = Wav2Vec2Processor.from_pretrained("ceyda/wav2vec2-large-xlsr-53-turk
 model = Wav2Vec2ForCTC.from_pretrained("ceyda/wav2vec2-large-xlsr-53-turkish")
 model.to("cuda")
 
-# chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\'\\\\`]'
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'\`…\]\[\&\’»«]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -106,7 +105,7 @@ 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
+        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)