Update app.py

app.py

@@ -26,13 +26,12 @@ ui.theme = "peach"
 ui.article = """<h2>Pre-trained model Information</h2>
                 <h3>Automatic Speech Recognition</h3>
                 <p style='text-align: justify'>The model used for the ASR part of this space is from                
-                [https://huggingface.co/facebook/wav2vec2-base-960h] which is pretrained and fine-tuned on 
-                <b>960 hours of 
-                Librispeech</b> on 16kHz sampled speech audio. This model has a <b>word error rate (WER)</b> of <b>8.6 percent on 
-                noisy speech</b> and <b>5.2 percent on clean speech</b> on the standard LibriSpeech benchmark. More information can be 
-                found on its website at [https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio] 
-                and 
-                original model is under [https://github.com/pytorch/fairseq/tree/main/examples/wav2vec].</p>
+                [https://huggingface.co/facebook/hubert-large-ls960-ft] which is pretrained and fine-tuned on <b>960 hours of 
+                Librispeech</b> on 16kHz sampled speech audio. This model has a self-reported <b>word error rate (WER)</b> of <b>1.9 
+                percent</b> and ranks first in <i>paperswithcode</i> for ASR on Librispeech. More information can be 
+                found on its website at [https://ai.facebook.com/blog/hubert-self-supervised-representation-learning-for-speech-recognition-
+                generation-and-compression] and 
+                original model is under [https://github.com/pytorch/fairseq/tree/main/examples/hubert].</p>
                 <h3>Text Translator</h3>
                 <p style='text-align: justify'>The English to Spanish text translator pre-trained model is from 
                 [https://huggingface.co/Helsinki-NLP/opus-mt-en-es] which is part of the <b>The Tatoeba Translation Challenge