-
Notifications
You must be signed in to change notification settings - Fork 316
求助 No module named 'tts' #40
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Comments
@Baiken1412 请设置您的PYTHONPATH环境变量到当前目录 |
(megatts3-env) D:\study\语音\MegaTTS3>python tts/infer_cli.py --input_wav "assets/Chinese_prompt.wav" --input_text "另一边的桌上,一位读书人嗤之以鼻道,'佛子三藏,神子燕小鱼是什么样的人物,李家的那个李子夜如何与他们相提并论?'" --output_dir ./gen 你好现在报这个错请问怎么解决? |
@Baiken1412 想问下你有下载预训练模型参数吗?你那边,./checkpoints目录中都有哪些文件和文件夹。 需要在docker build之前先下载好才行。 |
@Baiken1412 是否有在docker build之前先下载好这些? |
嗯是的 |
@Baiken1412 ok,windows docker目前还在测试中,所以暂时还不知道原因。我们会马上找更多的人来帮助解决一下,如果您后续找到解决方案也希望您可以发送给我们。 暂时认为问题是没有找到对应的checkpoint文件,但不清楚原因。 |
好的谢谢 |
拷贝的时候没有成功把tts目录拷贝进去,你可以docker进到/app目录看下是否有tts目录。或者先用这个试试是否可以:https://github.com/leeyeel/MegaTTS3 |
export PYTHONPATH="path to MegaTTS3:$PYTHONPATH" 这步没操作吧。 |
直接用 |
_pickle.UnpicklingError: invalid load key, 'v'. |
@Coder-Wjt 您使用的是docker还是物理机? |
@jiang-ziyue docker和物理机都会 |
2025-04-15 13:58:06,852 WETEXT INFO skip building fst for en_normalizer ... |
Traceback (most recent call last):
File "D:\study\语音\MegaTTS3\tts\infer_cli.py", line 28, in
from tts.modules.ar_dur.commons.nar_tts_modules import LengthRegulator
ModuleNotFoundError: No module named 'tts'
The text was updated successfully, but these errors were encountered: