Update README.md

README.md

@@ -27,7 +27,7 @@ model-index:
          value: 59.46
 ---
 
-# Wav2Vec2-Large-XLSR-53-{language} Vietnamese
+# Wav2Vec2-Large-XLSR-53-Vietnamese
 
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Vietnamese using the [Common Voice](https://huggingface.co/datasets/common_voice), and [FOSD](https://data.mendeley.com/datasets/k9sxg2twv4/4).
 When using this model, make sure that your speech input is sampled at 16kHz.
@@ -51,15 +51,15 @@ 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)
 
@@ -70,7 +70,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
+The model can be evaluated as follows on the Vietnamese test data of Common Voice.
 
 
 ```python
@@ -87,30 +87,30 @@ processor = Wav2Vec2Processor.from_pretrained("Nhut/wav2vec2-large-xlsr-vietname
 model = Wav2Vec2ForCTC.from_pretrained("Nhut/wav2vec2-large-xlsr-vietnamese")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\\\+\\@\\ǀ\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�0123456789]'
+chars_to_ignore_regex = '[\\\\\\\\\\\\+\\\\@\\\\ǀ\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�0123456789]'
 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
 
-\tpred_ids = torch.argmax(logits, dim=-1)
-\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\treturn batch
+\\tpred_ids = torch.argmax(logits, dim=-1)
+\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\\treturn batch
 
 result = test_dataset.map(evaluate, batched=True, batch_size=8)