Update README.md

README.md

@@ -25,7 +25,7 @@ for the french language that was fine-tuned on the
 The model is a CTC-based model on top of
 [wav2vec2](https://huggingface.co/LeBenchmark/wav2vec2-FR-7K-large) embeddings,
 trained on data from the [CommonVoice](https://commonvoice.mozilla.org),
-[PxCorpus](https://zenodo.org/records/6482587) and Simsmu datasets. The CTC
+[PxCorpus](https://zenodo.org/records/6482587) and Simsamu datasets. The CTC
 layers were trained from scratch and the wav2vec2 layers were fine-tuned.
 
 The model can be used in [medkit](https://github.com/medkit-lib/medkit/) the