| import torch | |
| from transformers import SpeechT5ForTextToSpeech, SpeechT5Processor | |
| MODEL_ID = "microsoft/speecht5_tts" | |
| processor = SpeechT5Processor.from_pretrained(MODEL_ID) | |
| model = SpeechT5ForTextToSpeech.from_pretrained(MODEL_ID) | |
| def synthesize_speech(text): | |
| inputs = processor(text, return_tensors="pt") | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| model.to(device) | |
| inputs = inputs.to(device) | |
| with torch.no_grad(): | |
| speech = model.generate(**inputs) | |
| return processor.decode(speech, skip_special_tokens=True) | |