Update README.md

README.md

@@ -27,7 +27,7 @@ model-index:
 
 # Wav2Vec2-Large-XLSR-53-German
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on German using 3% of the [Common Voice](https://huggingface.co/datasets/common_voice) dataset. #TODO: replace {language} with your language, *e.g.* French and eventually add more datasets that were used and eventually remove common voice if model was not trained on common voice
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on German using 3% of the [Common Voice](https://huggingface.co/datasets/common_voice) dataset. 
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Usage
@@ -40,7 +40,7 @@ import torchaudio
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 
-test_dataset = load_dataset("common_voice", "de", split="test[:2%]") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.
+test_dataset = load_dataset("common_voice", "de", split="test[:2%]") 
 
 processor = Wav2Vec2Processor.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
 model = Wav2Vec2ForCTC.from_pretrained("marcel/wav2vec2-large-xlsr-german-demo/") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
@@ -94,11 +94,11 @@ 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()
-\\\\tbatch["sentence"] = re.sub('\\ß', 'ss', batch["sentence"])
-\\\\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()
+\\tbatch["sentence"] = re.sub('\\\\ß', 'ss', batch["sentence"])
+\\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)