2noise / ChatTTS

A generative speech model for daily dialogue.
https://2noise.com
GNU Affero General Public License v3.0
31.21k stars 3.39k forks source link

只能用GPU吗?CPU不能跑是吗? #18

Closed guoqingcun closed 2 months ago

guoqingcun commented 4 months ago

只能用GPU吗?CPU不能跑是吗?

guoqingcun commented 4 months ago

image这是什么原因

iwanglei1 commented 4 months ago

模型下载中~

guoqingcun commented 4 months ago

模型下载中~

未下载完,直接退出了

wa008 commented 4 months ago

模型下载中~

未下载完,直接退出了

最终的进度条是在推理,是正常结束了。 可以用以下代码保存音频文件,再单独打开音频文件听内容。

import scipy
scipy.io.wavfile.write(filename = "./chattts_download_0.wav", rate = 24_000, data = wavs[0].T)
guoqingcun commented 4 months ago

@wa008 你说的没错,成功。怎么换语音模式,切换男女的声音之类的呢

Bill-XU commented 4 months ago

image这是什么原因

我这边运行示例代码报下面的错。。。为啥没有下载模型的过程? 能不能分享一下你的代码?谢谢! WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead INFO:ChatTTS.core:use cpu WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:dvae not initialized. WARNING:ChatTTS.core:vocos not initialized. WARNING:ChatTTS.core:gpt not initialized. WARNING:ChatTTS.core:tokenizer not initialized. WARNING:ChatTTS.core:dvae not initialized. Traceback (most recent call last): File "C:\Workstations\python\chattts\chattts.py", line 22, in wavs = chat.infer(texts) ^^^^^^^^^^^^^^^^^ File "C:\Users\xxxxxx.conda\envs\chattts\Lib\site-packages\ChatTTS\core.py", line 95, in infer assert self.check_model(use_decoder=use_decoder) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AssertionError

github-actions[bot] commented 2 months ago

This issue was closed because it has been inactive for 15 days since being marked as stale.