ChatTTS基于python开发的本地部署简明步骤

风笑谷

于 2024-12-01 12:02:51 发布

阅读量425

点赞数 3

文章标签： python 人工智能深度学习

本文链接：https://blog.youkuaiyun.com/weixin_40101756/article/details/144167604

版权

1.配置python环境（不用gpu可以省略2和3）

2.配置cuda+cudnn

3.安装torch

pip install torch==2.2.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cu118

pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

4.安装ChatTTS

   pip install ChatTTS

5.运行demo

import ChatTTS
import torch
import torchaudio

chat = ChatTTS.Chat()
chat.load(compile=False) # Set to True for better performance

texts = ["PUT YOUR 1st TEXT HERE", "PUT YOUR 2nd TEXT HERE"]

wavs = chat.infer(texts)

torchaudio.save("output1.wav", torch.from_numpy(wavs[0]), 24000)