chrisjay commited on
Commit
da95346
1 Parent(s): 6e75ca4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -52,7 +52,7 @@ for root, dirs, files in os.walk(test/):
52
  test_dataset= load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
53
 
54
  #Remove unnecessary chars
55
- chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”]'
56
  def remove_special_characters(batch):
57
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
58
  return batch
@@ -99,7 +99,7 @@ import re
99
  for root, dirs, files in os.walk(test/):
100
  test_dataset = load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
101
 
102
- chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”]'
103
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
104
  return batch
105
 
@@ -149,7 +149,7 @@ The script used for training can be found [here](https://colab.research.google.c
149
 
150
  # Collaborators on this project
151
 
152
- - Chris C. Emezue ([Twitter](https://twitter.com/ChrisEmezue))([email protected])
153
- - Bonaventure F.P. Dossou ([Twitter](https://twitter.com/bonadossou))([email protected])
154
 
155
  ## This is a joint project continuing our research on [OkwuGbé: End-to-End Speech Recognition for Fon and Igbo](https://arxiv.org/abs/2103.07762)
 
52
  test_dataset= load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
53
 
54
  #Remove unnecessary chars
55
+ chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”]'
56
  def remove_special_characters(batch):
57
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
58
  return batch
 
99
  for root, dirs, files in os.walk(test/):
100
  test_dataset = load_dataset("json", data_files=[os.path.join(root,i) for i in files],split="train")
101
 
102
+ chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”]'
103
  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower() + " "
104
  return batch
105
 
 
149
 
150
  # Collaborators on this project
151
 
152
+ - Chris C. Emezue ([Twitter](https://twitter.com/ChrisEmezue))|([email protected])
153
+ - Bonaventure F.P. Dossou (HuggingFace Username: [bonadossou](https://huggingface.co/bonadossou))|([Twitter](https://twitter.com/bonadossou))|([email protected])
154
 
155
  ## This is a joint project continuing our research on [OkwuGbé: End-to-End Speech Recognition for Fon and Igbo](https://arxiv.org/abs/2103.07762)