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

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the mozilla-foundation/common_voice_3_0 - IT dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3899
-- Wer: 0.0770
+- Per: 0.0770
 
 ## Model description