adjust README

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 13.45
+         value: 13.48
 ---
 
 # Wav2Vec2-Large-XLSR-53-portuguese
@@ -54,23 +54,23 @@ model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
-  speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
-	batch["speech"] = resampler(speech_array).squeeze().numpy()
-	return batch
+    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    batch["sentence"] = batch["sentence"].upper()
+    return 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)
+inputs = processor(test_dataset[:2]["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
 with torch.no_grad():
-	logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
 
 predicted_ids = torch.argmax(logits, dim=-1)
 
 print("Prediction:", processor.batch_decode(predicted_ids))
-print("Reference:", test_dataset["sentence"][:2])
+print("Reference:", test_dataset[:2]["sentence"])
 ```
 
-
 ## Evaluation
 
 The model can be evaluated as follows on the Portuguese test data of Common Voice.
@@ -92,7 +92,7 @@ CHARS_TO_IGNORE = [",", "?", ".", "!", "-", ";", ":", '""', "%", "'", '"', "�"
 test_dataset = load_dataset("common_voice", LANG_ID, split="test")
 wer = load_metric("wer")
 
-chars_to_ignore_regex = f'[{re.escape("".join(CHARS_TO_IGNORE))}]'
+chars_to_ignore_regex = f"[{re.escape("".join(CHARS_TO_IGNORE))}]"
 
 processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
 model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
@@ -101,7 +101,7 @@ model.to(DEVICE)
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
-    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).upper()
+    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
     speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
     batch["speech"] = speech_array
     return batch
@@ -125,4 +125,4 @@ result = test_dataset.map(evaluate, batched=True, batch_size=32)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 
-**Test Result**: 13.45% 
+**Test Result**: 13.48%