Update README.md

README.md

@@ -33,9 +33,9 @@ model-index:
 ---
 
 
-# Wav2Vec2-Large-XLSR-53-Spanish
+# Wav2Vec2-Large-XLSR-53-Portuguese
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Spanish using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset.
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Portuguese using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset.
 
 ## Usage
 
@@ -58,14 +58,14 @@ resampler = torchaudio.transforms.Resample(48_000, 16_000)
 # 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
+\\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)
 
@@ -93,30 +93,30 @@ processor = Wav2Vec2Processor.from_pretrained("joorock12/wav2vec2-large-xlsr-53-
 model = Wav2Vec2ForCTC.from_pretrained("joorock12/wav2vec2-large-xlsr-53-portuguese")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“]'  # TODO: adapt this list to include all special characters you removed from the data
+chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“]'  # TODO: adapt this list to include all special characters you removed from the data
 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):
-\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\tbatch["speech"] = resampler(speech_array).squeeze().numpy()
-\treturn batch
+\\tbatch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+\\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)
 
 # Preprocessing the datasets.
 # We need to read the aduio files as arrays
 def evaluate(batch):
-\\\\\\\\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+\tinputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
 
-\\\\\\\\twith torch.no_grad():
-\\\\\\\\t\\\\\\\\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+\twith torch.no_grad():
+\t\tlogits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
 
   pred_ids = torch.argmax(logits, dim=-1)
-\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\\\\\\\treturn batch
+\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)
 
@@ -130,4 +130,4 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
 
 The Common Voice `train`, `validation` datasets were used for training.
 
-The script used for training can be found at: https://github.com/joaoalvarenga/wav2vec2-large-xlsr-53-spanish/blob/main/fine-tuning.py
+The script used for training can be found at: https://github.com/joaoalvarenga/wav2vec2-large-xlsr-53-portuguese/blob/main/fine-tuning.py