Update README.md

README.md

@@ -17,7 +17,7 @@ model-index:
     dataset:
       name: Common Voice ky
       type: common_voice
-      args: {lang_id}  
+      args: ky
     metrics:
        - name: Test WER
          type: wer
@@ -49,15 +49,15 @@ 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):
-\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\\treturn batch
+\\\\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\\\\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
+\\\\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)
 
@@ -85,7 +85,7 @@ processor = Wav2Vec2Processor.from_pretrained("iarfmoose/wav2vec2-large-xlsr-kyr
 model = Wav2Vec2ForCTC.from_pretrained("iarfmoose/wav2vec2-large-xlsr-kyrgyz")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�\\\\–\\\\—\\\\¬\\\\⅛]'
+chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�\\\\\\\\–\\\\\\\\—\\\\\\\\¬\\\\\\\\⅛]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def speech_file_to_array_fn(batch):