ChatTTS-ui icon indicating copy to clipboard operation
ChatTTS-ui copied to clipboard

为ChatTTS创建web界面和api接口

Results 141 ChatTTS-ui issues
Sort by recently updated
recently updated
newest added

安装启动都正常,但是在合成声音的时候提示“发生错误: INTERNAL SERVER ERROR” ![sp240531_154240](https://github.com/jianchang512/ChatTTS-ui/assets/130527457/82bf9029-c8fa-4344-b7b6-b2234101f8ce)

**环境: ARM 架构 Ubuntu 20.04 4G24核内存 刚刚重装的干净系统** 执行 `docker-compose -f docker-compose.cpu.yaml up -d` 的时候报错如图: ![1111](https://github.com/user-attachments/assets/a4158720-7f0d-477e-9082-c07ed0ea4260) 请问是不是ARM无法安装啊?

选择音色后,对于一次生成多段语音,多段语音音色不一致,这个怎么处理呢?

2024-06-06 17:25:06,816 - modelscope - INFO - PyTorch version 2.1.2+cu118 Found. 2024-06-06 17:25:06,817 - modelscope - INFO - Loading ast index from C:\Users\vusoo\.cache\modelscope\ast_indexer 2024-06-06 17:25:06,817 - modelscope - INFO -...

发生错误: INTERNAL SERVER ERROR

TypeError: LlamaModel.forward() got an unexpected keyword argument 'cache_position'

0.98版还正常,今天部署到云服务器上,发现这个问题,然后看本地版本是0.98,于是本地版本也更新到0.99,发现同样的问题

我想咨询一下,为什么cpu的使用率很大的,但是生成的时间需要很久,需要一百多秒才能制作完成

源码安装,跑在cuda上,请求tts接口,如下报错,请教是什么原因: Traceback (most recent call last): File "/root/miniconda3/lib/python3.10/site-packages/flask/app.py", line 1473, in wsgi_app response = self.full_dispatch_request() File "/root/miniconda3/lib/python3.10/site-packages/flask/app.py", line 882, in full_dispatch_request rv = self.handle_user_exception(e) File "/root/miniconda3/lib/python3.10/site-packages/flask/app.py", line 880, in full_dispatch_request...

windows 1.0版API接口返回的audio_duration问题-1