Model card contadicts information on Github.

GitHub repo says Phoneme error rate, not WER:
https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition#common-voice-ctc

README.md

@@ -17,7 +17,7 @@ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://hug
 It achieves the following results on the evaluation set:
 
 - Loss: 0.4879
-- Wer: 0.0997
+- Per: 0.0997
 
 ## Model description