Update README.md

README.md

@@ -4,6 +4,8 @@ tags:
 - Czech
 - KKY
 - FAV
+datasets:
+- mozilla-foundation/common_voice_7_0
 license: "cc-by-nc-sa-4.0"
 ---
 
@@ -27,7 +29,7 @@ More than 80 thousand hours of unlabeled Czech speech:
 ## Usage
 Inputs must be 16kHz mono audio files.
 
-This model could be used e.g. to extract per-frame contextual embeddings from audio:
+This model can be used e.g. to extract per-frame contextual embeddings from audio:
 ```python
 from transformers import Wav2Vec2Model, Wav2Vec2FeatureExtractor
 import torchaudio
@@ -67,7 +69,7 @@ If you find this model useful, please cite our paper:
     Ale\v{s} Pra\v{z}\'ak and 
     Josef V. Psutka
   },
-  booktitle = {Interspeech 2022},
+  booktitle = {{I}nterspeech 2022},
   publisher = {{ISCA}},
   year = {2022},
   note = {(in press)},
@@ -75,5 +77,5 @@ If you find this model useful, please cite our paper:
 }
 ```
 
-## Other papers using this model:
+## Works using this model
 - [Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project](https://arxiv.org/abs/2206.07666)