SpeechT5 TTS
This is a re-upload of the Microsoft/SpeechT5_TTS model.
Model description
SpeechT5 is a unified-modal speech and text model developed by Microsoft. This specific model is fine-tuned for text-to-speech tasks.
Usage
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import soundfile as sf
processor = SpeechT5Processor.from_pretrained("YOUR_USERNAME/YOUR_REPO_NAME")
model = SpeechT5ForTextToSpeech.from_pretrained("YOUR_USERNAME/YOUR_REPO_NAME")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
inputs = processor(text="Hello, how are you?", return_tensors="pt")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
sf.write("speech.wav", speech.numpy(), samplerate=16000)