# Following pip packages need to be installed:
!pip install git+https://github.com/huggingface/transformers sentencepiece datasets

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
from datasets import load_dataset

processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")

inputs = processor(text="Hello, all this is a text to speech converter. Just change the embeddings_dataset number to try out different voices.", return_tensors="pt")

# load xvector containing speaker's voice characteristics from a dataset
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[5000]["xvector"]).unsqueeze(0)

speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)

sf.write("speech.wav", speech.numpy(), samplerate=16000)

from IPython.display import Audio

Audio(speech, rate=16000)