Update app.py

app.py

@@ -59,6 +59,35 @@ def predict(text, speaker):
 
 title = "SpeechT5: Speech Synthesis"
 
+description = """
+The <b>SpeechT5</b> model is pre-trained on text as well as speech inputs, with targets that are also a mix of text and speech.
+By pre-training on text and speech at the same time, it learns unified representations for both, resulting in improved modeling capabilities.
+SpeechT5 can be fine-tuned for different speech tasks. This space demonstrates the <b>text-to-speech</b> (TTS) checkpoint for the English language.
+See also the <a href="https://huggingface.co/spaces/Matthijs/speecht5-asr-demo">speech recognition (ASR) demo</a>
+and the <a href="https://huggingface.co/spaces/Matthijs/speecht5-vc-demo">voice conversion demo</a>.
+<b>How to use:</b> Enter some English text and choose a speaker. The output is a mel spectrogram, which is converted to a mono 16 kHz waveform by the
+HiFi-GAN vocoder. Because the model always applies random dropout, each attempt will give slightly different results.
+The <em>Surprise Me!</em> option creates a completely randomized speaker.
+"""
+
+article = """
+<div style='margin:20px auto;'>
+<p>References: <a href="https://arxiv.org/abs/2110.07205">SpeechT5 paper</a> |
+<a href="https://github.com/microsoft/SpeechT5/">original GitHub</a> |
+<a href="https://huggingface.co/mechanicalsea/speecht5-tts">original weights</a></p>
+<pre>
+@article{Ao2021SpeechT5,
+  title   = {SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing},
+  author  = {Junyi Ao and Rui Wang and Long Zhou and Chengyi Wang and Shuo Ren and Yu Wu and Shujie Liu and Tom Ko and Qing Li and Yu Zhang and Zhihua Wei and Yao Qian and Jinyu Li and Furu Wei},
+  eprint={2110.07205},
+  archivePrefix={arXiv},
+  primaryClass={eess.AS},
+  year={2021}
+}
+</pre>
+<p>Speaker embeddings were generated from <a href="http://www.festvox.org/cmu_arctic/">CMU ARCTIC</a> using <a href="https://huggingface.co/mechanicalsea/speecht5-vc/blob/main/manifest/utils/prep_cmu_arctic_spkemb.py">this script</a>.</p>
+</div>
+"""
 
 examples = [
     ["It is not in the stars to hold our destiny but in ourselves.", "BDL (male)"],
@@ -90,4 +119,4 @@ gr.Interface(
     description=description,
     article=article,
     examples=examples,
-).launch()
+).launch()