Update README.md

README.md

@@ -77,14 +77,14 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "es", split="test")
+test_dataset = load_dataset("common_voice", "uk", split="test")
 wer = load_metric("wer")
 
 processor = Wav2Vec2Processor.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-ukrainian")
 model = Wav2Vec2ForCTC.from_pretrained("mrm8488/wav2vec2-large-xlsr-53-ukrainian")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“]'
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 # Preprocessing the datasets.
@@ -104,7 +104,7 @@ def evaluate(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)
+  pred_ids = torch.argmax(logits, dim=-1)
   batch["pred_strings"] = processor.batch_decode(pred_ids)
   return batch