| import gradio as gr | |
| # from TTS.api import TTS | |
| # tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False) | |
| # def predict(text): | |
| # file_path = "output.wav" | |
| # tts.tts_to_file(text, speaker=tts.speakers[0], language="en", file_path=file_path) | |
| # return file_path | |
| # demo = gr.Interface( | |
| # fn=predict, | |
| # inputs='text', | |
| # outputs='audio' | |
| # ) | |
| # demo.launch() | |
| import librosa | |
| import numpy as np | |
| import torch | |
| from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan | |
| checkpoint = "microsoft/speecht5_tts" | |
| processor = SpeechT5Processor.from_pretrained(checkpoint) | |
| model = SpeechT5ForTextToSpeech.from_pretrained(checkpoint) | |
| vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan") |