Update README.md

README.md

@@ -1,4 +1,5 @@
 language: fon
+
 datasets:
 - [Fon Dataset](https://github.com/laleye/pyFongbe/tree/master/data)
 metrics:
@@ -130,7 +131,7 @@ for root, dirs, files in os.walk(test_path):
   test_dataset= load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
 
 #Remove unnecessary chars
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
 def remove_special_characters(batch):
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
     return batch
@@ -146,15 +147,15 @@ model = Wav2Vec2ForCTC.from_pretrained("chrisjay/wav2vec2-large-xlsr-53-fon")
 # Preprocessing the datasets.
 # We need to read the audio files as arrays
 def speech_file_to_array_fn(batch):
-	speech_array, sampling_rate = torchaudio.load(batch["path"])
-	batch["speech"]=speech_array.squeeze().numpy()
-	return batch
+\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
+\tbatch["speech"]=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():
-	logits = 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)
 
@@ -177,7 +178,7 @@ import re
 for root, dirs, files in os.walk(test_path):
   test_dataset = load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�]'
 def remove_special_characters(batch):
     batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
     return batch