Update app.py

app.py

@@ -1,15 +1,28 @@
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+from datasets import load_dataset
+import torch
+import soundfile as sf
+from datasets import load_dataset
 from transformers import pipeline
 import gradio as gr
 
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+# code from the Model card
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+
+
 speech = pipeline("text-to-speech", model="microsoft/speecht5_tts")     
 def summarize_text_and_speak(prompt):
     summary = summarizer(prompt, max_length=150, min_length=30, do_sample=False)
     summary_text = summary[0]['summary_text']
-    audio = speech(summary_text)
+    #inputs = processor(text="Hello, my dog is cute.", return_tensors="pt")
+    inputs = processor(text=summary_text, return_tensors="pt")
+    #speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
+    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
     return summary_text, audio["audio"]
-
-
+    
 interface = gr.Interface(
     fn=summarize_text_and_speak,
     inputs=gr.Textbox(lines=10, label="Input text"),