Update README.md

README.md

@@ -64,18 +64,22 @@ wer = load_metric("wer")
 processor = Wav2Vec2Processor.from_pretrained("ayameRushia/wav2vec2-large-xlsr-indonesia-demo")
 model = Wav2Vec2ForCTC.from_pretrained("ayameRushia/wav2vec2-large-xlsr-indonesia-demo")
 model.to("cuda")
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
+
 def speech_file_to_array_fn(batch):
   batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
   speech_array, sampling_rate = torchaudio.load(batch["path"])
+  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
   batch["speech"] = resampler(speech_array).squeeze().numpy()
   return batch
+  
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 # Preprocessing the datasets.
 # 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():
@@ -87,6 +91,6 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 **Test Result**: 
-WER = 21.079620 %
+WER = 20.072720 %
 ## Training
 Training using common voice dataset