Update README.md

README.md

@@ -66,9 +66,9 @@ model-index:
       value: 14.23
 ---
 
-# XLS-R-1B-RUSSIAN
+# Fine-tuned XLS-R 1B model for speech recognition in Russian
 
-Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Russian using the [Common Voice 8](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0).
+Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Russian using the train split of [Common Voice 8.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0), [Golos](https://www.openslr.org/114/), and [Multilingual TEDx](http://www.openslr.org/100).
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool, and thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
@@ -139,12 +139,10 @@ python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-russian --dataset spe
 If you want to cite this model you can use this:
 
 ```bibtex
-@misc{grosman2022wav2vec2-xls-r-1b-russian,
-  title={XLS-R Wav2Vec2 Russian by Jonatas Grosman},
+@misc{grosman2021xlsr-1b-russian,
+  title={Fine-tuned {XLS-R} 1B model for speech recognition in {R}ussian},
   author={Grosman, Jonatas},
-  publisher={Hugging Face},
-  journal={Hugging Face Hub},
   howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-russian}},
-  year={2022}
+  year={2021}
 }
 ```