Update app.py

app.py

@@ -275,5 +275,35 @@ print(summarized_text)
    # number_of_sentences-=1
     #print(summarized_text_list_list)
     #print(number_of_sentences)
+#text to speech
+#!pip install git+https://github.com/huggingface/transformers.git
+#!pip install datasets sentencepiece
+import torch
+import soundfile as sf
+from IPython.display import Audio
+from datasets import load_dataset
+from transformers import pipeline
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech
+processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+text = "The future belongs to those who believe in the beauty of their dreams."
+#text = (summarized_text_list_list)
+
+#inputs = processor(text=summarized_text_list_list, return_tensors="pt")
+inputs = processor(text, return_tensors="pt")
+from datasets import load_dataset
+embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
+
+import torch
+speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
+spectrogram = model.generate_speech(inputs["input_ids"], speaker_embeddings)
+from transformers import SpeechT5HifiGan
+vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+with torch.no_grad():
+    speech = vocoder(spectrogram)
+speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
+Audio(speech, rate=16000)
+
+