Update README.md

Add an example of prediction.

README.md

@@ -26,8 +26,39 @@ model-index:
 # Wav2Vec2-Large-XLSR-53-Breton
 The model can be used directly (without a language model) as follows:
 ```python
-TODO
+import torch
+import torchaudio
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+lang = "br"
+test_dataset = load_dataset("common_voice", lang, split="test[:2%]") 
+
+processor = Wav2Vec2Processor.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton") 
+model = Wav2Vec2ForCTC.from_pretrained("Marxav/wav2vec2-large-xlsr-53-breton")
+
+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):
+   speech_array, sampling_rate = torchaudio.load(batch["path"])
+   batch["speech"] = resampler(speech_array).squeeze().numpy()
+   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)
+
+with torch.no_grad():
+   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])
 ```
+The above code leads to the following prediction for the first two samples:
+* Prediction: ["nel ler ket dont abenn eus netra la vez ser mirc'hid evel sij", 'an eil hag egile']
+* Reference: ['"N\'haller ket dont a-benn eus netra pa vezer nec\'het evel-se."', 'An eil hag egile.']
 
 The model can be evaluated as follows on the {language} test data of Common Voice.
 ```python
@@ -45,7 +76,7 @@ model = Wav2Vec2ForCTC.from_pretrained('Marxav/wav2vec2-large-xlsr-53-breton')
 model.to("cuda")
 
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'\(\)\/\«\»\½\…]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\'\\(\\)\\/\\«\\»\\½\\…]'
 
 def remove_special_characters(batch):
      sentence = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "