Update app.py

app.py

@@ -14,10 +14,10 @@ vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
 
 speaker_embeddings = {
     "BDL": "spkemb/triniFemale.npy",
-    #"CLB": "spkemb/triniFemale.npy",
-    #"KSP": "spkemb/triniFemale.npy",
-    #"RMS": "spkemb/triniFemale.npy",
-    #"SLT": "spkemb/triniFemale.npy",
+    "CLB": "spkemb/triniFemale.npy",
+    "KSP": "spkemb/triniFemale.npy",
+    "RMS": "spkemb/triniFemale.npy",
+    "SLT": "spkemb/triniFemale.npy",
 }
 
 
@@ -59,16 +59,16 @@ 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.
+#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.
+#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>.
+#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>.
 
-Refer to <a href="https://colab.research.google.com/drive/1i7I5pzBcU3WDFarDnzweIj4-sVVoIUFJ">this Colab notebook</a> to learn how to fine-tune the SpeechT5 TTS model on your own dataset or language.
+#Refer to <a href="https://colab.research.google.com/drive/1i7I5pzBcU3WDFarDnzweIj4-sVVoIUFJ">this Colab notebook</a> to learn how to fine-tune the SpeechT5 TTS model on your own dataset or language.
 
 <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.
@@ -91,14 +91,14 @@ article = """
   primaryClass={eess.AS},
   year={2021}
 }
-</pre>
+#</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>
+#<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 = [ \
+#examples = [ 
     #["It is not in the stars to hold our destiny but in ourselves.", "BDL (male)"],
     #["The octopus and Oliver went to the opera in October.", "CLB (female)"],
     #["She sells seashells by the seashore. I saw a kitten eating chicken in the kitchen.", "RMS (male)"],