Update README.md

README.md

@@ -2,14 +2,18 @@ language: fon
 
 datasets:
 - [Fon Dataset](https://github.com/laleye/pyFongbe/tree/master/data)
+
 metrics:
 - wer
+
 tags:
 - audio
 - automatic-speech-recognition
 - speech
 - xlsr-fine-tuning-week
+
 license: apache-2.0
+
 model-index:
 - name: Fon XLSR Wav2Vec2 Large 53
   results:
@@ -131,7 +135,7 @@ 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
@@ -147,15 +151,15 @@ 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):
-\tspeech_array, sampling_rate = torchaudio.load(batch["path"])
-\tbatch["speech"]=speech_array.squeeze().numpy()
-\treturn 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():
-\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)
 
@@ -178,7 +182,7 @@ 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