Update README.md

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 44.92
+         value: 45.28
 ---
 
 # Wav2Vec2-Large-XLSR-53-Georgian
@@ -53,15 +53,15 @@ resampler = lambda sampling_rate, y: librosa.resample(y.numpy().squeeze(), sampl
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
-\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\tbatch["speech"] = resampler(sampling_rate, speech_array).squeeze()
-\\treturn batch
+\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\\\\tbatch["speech"] = resampler(sampling_rate, speech_array).squeeze()
+\\\\treturn batch
 
 test_dataset = test_dataset.map(speech_file_to_array_fn)
 inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
 
 with torch.no_grad():
-\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+\\\\tlogits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
@@ -90,7 +90,7 @@ processor = Wav2Vec2Processor.from_pretrained("xsway/wav2vec2-large-xlsr-georgia
 model = Wav2Vec2ForCTC.from_pretrained("xsway/wav2vec2-large-xlsr-georgian") 
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]' 
+chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“]' 
 resampler = lambda sampling_rate, y: librosa.resample(y.numpy().squeeze(), sampling_rate, 16_000)
 
 # Preprocessing the datasets.
@@ -120,7 +120,7 @@ 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**: 44.92 %  
+**Test Result**: 45.28 %  
 
 
 ## Training