Update README.md

README.md

@@ -69,7 +69,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the {language} test data of Common Voice.  # TODO: replace #TODO: replace language with your {language}, *e.g.* French
+The model can be evaluated as follows on the {language} test data of Common Voice.
 
 
 ```python
@@ -79,24 +79,26 @@ from datasets import load_dataset, load_metric
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
 import re
 
-test_dataset = load_dataset("common_voice", "de", split="test") #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") [this](https://huggingface.co/languages) site.
 wer = load_metric("wer")
 
-processor = Wav2Vec2Processor.from_pretrained("de") #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("de") #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`
+processor = Wav2Vec2Processor.from_pretrained("de")
+`elgeish/wav2vec2-large-xlsr-53-arabic`
+model = Wav2Vec2ForCTC.from_pretrained("de") 
+`elgeish/wav2vec2-large-xlsr-53-arabic`
 model.to("cuda")
 
-chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'  # TODO: adapt this list to include all special characters you removed from the data
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“]'  
 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)