Update README.md

README.md

@@ -14,7 +14,11 @@ license: cc-by-4.0
 
 ## WavLabLM-MS 40k
 
-This model was trained by [William Chen] using ESPNet2's SSL recipe in [espnet](https://github.com/espnet/espnet/).
+[Paper](https://arxiv.org/abs/2309.15317)
+
+This model was trained by [William Chen](https://wanchichen.github.io/) using ESPNet2's SSL recipe in [espnet](https://github.com/espnet/espnet/).
+WavLabLM is an self-supervised audio encoder pre-trained on 40,000 hours of multilingual data across 136 languages. This specific variant, WavLabLM-MS, went through a second stage of pre-training on a balanced subset of the data to improve performance on lower-resource languages.
+It achieves comparable performance to XLS-R 128 on the [ML-SUPERB Benchmark](https://arxiv.org/abs/2305.10615) with only 10% of the pre-training data.