feat(generator): bundle as function and generate on button click

app.py

@@ -10,16 +10,21 @@ text = st.text_input(
 	value = "Hi, Welcome to theserverfault.com"
 )
 
-processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
-model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
-vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+def generate_speech():
+    processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+    model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+    vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+    inputs = processor(text=text, return_tensors="pt")
 
+    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+    speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
 
-inputs = processor(text=text, return_tensors="pt")
+    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
 
-embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
-speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+    sf.write("speech.wav", speech.numpy(), samplerate=16000)
 
-speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
-
-sf.write("speech.wav", speech.numpy(), samplerate=16000)
+if st.button("Generate"):
+      generate_speech()
+      audio_file = open("speech.wav", 'rb')
+      audio_bytes = audio_file.read()
+      st.audio(audio_bytes, format="audio/wav")