Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-language: fy-NL
+language: hsb
 datasets:
 - common_voice
 tags:
@@ -9,13 +9,13 @@ tags:
 - xlsr-fine-tuning-week
 license: apache-2.0
 model-index:
-- name: XLSR Wav2Vec2 Frisian by Adam Montgomerie
+- name: XLSR Wav2Vec2 Sorbian by Adam Montgomerie
   results:
   - task: 
       name: Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice fy-NL
+      name: Common Voice hsb
       type: common_voice
       args: {lang_id}  
     metrics:
@@ -24,9 +24,9 @@ model-index:
          value: 43.48
 ---
 
-# Wav2Vec2-Large-XLSR-53-Frisian
+# Wav2Vec2-Large-XLSR-53-Sorbian
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Frisian using the [Common Voice](https://huggingface.co/datasets/common_voice)
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Sorbian using the [Common Voice](https://huggingface.co/datasets/common_voice)
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Usage
@@ -67,7 +67,7 @@ print("Reference:", test_dataset["sentence"][:2])
 
 ## Evaluation
 
-The model can be evaluated as follows on the Frisian test data of Common Voice.
+The model can be evaluated as follows on the Sorbian test data of Common Voice.
 
 
 ```python
@@ -84,7 +84,7 @@ processor = Wav2Vec2Processor.from_pretrained("iarfmoose/wav2vec2-large-xlsr-sor
 model = Wav2Vec2ForCTC.from_pretrained("iarfmoose/wav2vec2-large-xlsr-sorbian")
 model.to("cuda")
 
-chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\–\—\¬\⅛]'
+chars_to_ignore_regex = '[\\,\\?\\.\\!\\-\\;\\:\\"\\“\\%\\‘\\”\\�\\–\\—\\¬\\⅛]'
 resampler = torchaudio.transforms.Resample(48_000, 16_000)
 
 def speech_file_to_array_fn(batch):