jianchang512 / ChatTTS-ui

一个简单的本地网页界面,使用ChatTTS将文字合成为语音,同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.
https://pyvideotrans.com
Other
5.78k stars 657 forks source link

源码安装,执行python3 app.py启动报错 #193

Open fuyuhnag168 opened 1 month ago

fuyuhnag168 commented 1 month ago

Starting... no GPU found, use CPU instead Traceback (most recent call last): File "/data/chat-tts-ui/app.py", line 69, in chat.load(source="custom",custom_path=CHATTTS_DIR, device=None if device=='default' else device,compile=True if os.getenv('compile','true').lower()!='false' else False) File "/data/chat-tts-ui/ChatTTS/core.py", line 126, in load return self._load( File "/data/chat-tts-ui/ChatTTS/core.py", line 244, in _load torch.load(vocos_ckpt_path, weights_only=True, mmap=True) File "/usr/local/python3/lib/python3.9/site-packages/torch/serialization.py", line 1032, in load raise RuntimeError("mmap can only be used with files saved with " RuntimeError: mmap can only be used with files saved with `torch.save(/data/chat-tts-ui/models/pzc163/chatTTS/asset/Vocos.pt, _use_new_zipfile_serialization=True), please torch.save your checkpoint with this option in order to use mmap.

jianchang512 commented 1 month ago

不要使用已有的音色pt,填写音色值,然后重试