[2noise/ChatTTS]未知错误

2024-06-05 788 views
2
image image

成功跑在本地了,但是点击generate显示错误

回答

7
 ChatTTS-main /usr/local/bin/python3 /Users/wangkewen/Downloads/ChatTTS-main/ChatTTS/1.py
INFO:ChatTTS.core:Load from cache: /Users/wangkewen/.cache/huggingface/hub/models--2Noise--ChatTTS/snapshots/ce5913842aebd78e4a01a02d47244b8d62ac4ee3
WARNING:ChatTTS.utils.gpu_utils:No GPU found, use CPU instead
INFO:ChatTTS.core:use cpu
INFO:ChatTTS.core:vocos loaded.
INFO:ChatTTS.core:dvae loaded.
INFO:ChatTTS.core:gpt loaded.
INFO:ChatTTS.core:decoder loaded.
INFO:ChatTTS.core:tokenizer loaded.
INFO:ChatTTS.core:All initialized.
INFO:ChatTTS.core:All initialized.
WARNING:ChatTTS.core:Package WeTextProcessing not found!                         Run: conda install -c conda-forge pynini=2.1.5 && pip install WeTextProcessing
Traceback (most recent call last):
  File "/Users/wangkewen/Downloads/ChatTTS-main/ChatTTS/1.py", line 13, in <module>
    wavs = chat.infer(texts, use_decoder=True)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/wangkewen/Downloads/ChatTTS-main/ChatTTS/ChatTTS/core.py", line 146, in infer
    self.init_normalizer(_lang)
  File "/Users/wangkewen/Downloads/ChatTTS-main/ChatTTS/ChatTTS/core.py", line 192, in init_normalizer
    self.normalizer[lang] = Normalizer().normalize
                            ^^^^^^^^^^
UnboundLocalError: cannot access local variable 'Normalizer' where it is not associated with a value
3
164 #168 MacOS下也可以照此解决
0
164 #168 MacOS下也可以照此解决

谢谢,我在研究您的项目CHATTTS-UI

9
164 #168 MacOS下也可以照此解决
image

大佬想请问下这是什么错误呢,我执行了python3 app.py后显示 2024-06-02 10:41:08,296 - modelscope - WARNING - Downloading: GPT.pt failed, reason: HTTPSConnectionPool(host='www.modelscope.cn', port=443): Max retries exceeded with url: /api/v1/models/pzc163/chatTTS/repo?Revision=master&FilePath=asset%2FGPT.pt (Caused by SSLError(SSLEOFError(8, '[SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violation of protocol (_ssl.c:1000)'))) will retry

2

modelscope.cn 只允许国内ip下载,关闭代理就行了

4

modelscope.cn 只允许国内ip下载,关闭代理就行了

image

谢谢老哥,you do such a wonderful job!😺