Update README.md

README.md

@@ -28,7 +28,7 @@ model-index:
 
 # Wav2Vec2-Large-XLSR-53-rw
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Kinyarwanda using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, using about 20% of the training data (limited to utterances without downvotes and shorter than 9.5 seconds), and validated on 2048 utterances from the validation set.
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Kinyarwanda using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, using about 20% of the training data (limited to utterances without downvotes and shorter than 9.5 seconds), and validated on 2048 utterances from the validation set. In contrast to the [lucio/wav2vec2-large-xlsr-kinyarwanda-apostrophied](https://huggingface.co/lucio/wav2vec2-large-xlsr-kinyarwanda-apostrophied) model, which predicts the apostrophes that mark contractions of pronouns with vowel-initial words, this model does not predict any punctuation.
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Usage