File size: 603 Bytes
993fe8a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 |
from transformers import pipeline
from datasets import load_dataset
import soundfile as sf
import torch
synthesiser = pipeline(task="text-to-speech", model="microsoft/speecht5_tts")
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
sf.write("speech.wav", speech["audio"], samplerate=speech["sampling_rate"])
|