File size: 676 Bytes
df165b9 d195c23 df165b9 d195c23 03088e5 df165b9 d195c23 03088e5 d195c23 df165b9 d195c23 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
import torch
from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech
import soundfile as sf
# Initialize the model and processor from Hugging Face
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
def text_to_speech(text):
# Process the input text into tokens
inputs = processor(text, return_tensors="pt")
# Generate speech
with torch.no_grad():
speech = model.generate_speech(inputs.input_ids)
# Save the generated speech as a WAV file
sf.write('output.wav', speech.squeeze().cpu().numpy(), 16000)
return "output.wav"
|