chatTTS使用问题新生避雷

1.链接：git clone https://github.com/2noise/ChatTTS.git

2.遇到'nomalizer'问题，直接pip install nemo_text_processing，pynini,WeTextProcessing，这在linux无问题，windows有问题

解决办法：

在chatTTS里面的core.py：

143行到149行注释掉：

# if do_text_normalization:

        # for i, t in enumerate(text):

        # _lang = detect_language(t) if lang is None else lang

        # self.init_normalizer(_lang)

        # text[i] = self.normalizer[_lang](t)

        # if _lang == 'zh':

        # text[i] = apply_half2full_map(text[i])

3.huggingface连接问题，在Google colab无问题可连接，但本地出现梯子代理问题，尚未解决

替代解决：

使用以下代码

from modelscope import snapshot_download

model_dir = snapshot_download('mirror013/ChatTTS')

 

# # 加载模型

chat = ChatTTS.Chat()

chat.load_models(

    source="local",

    local_path=model_dir,

)

替代以下代码：

chat = ChatTTS.Chat()

# chat.load_models(compile=False) # Set to True for better performance

chatTTS使用问题
1.链接：git clone https://github.com/2noise/ChatTTS.git
2.遇到'nomalizer'问题，直接pip install nemo_text_processing，pynini,WeTextProcessing，这在linux无问题，windows有问题
解决办法：
在chatTTS里面的core.py：
143行到149行注释掉：
SQL
# if do_text_normalization:
        #     for i, t in enumerate(text):
        #         _lang = detect_language(t) if lang is None else lang
        #         self.init_normalizer(_lang)
        #         text[i] = self.normalizer[_lang](t)
        #         if _lang == 'zh':
        #             text[i] = apply_half2full_map(text[i])

3.huggingface连接问题，在Google colab无问题可连接，但本地出现梯子代理问题，尚未解决
替代解决：
使用以下代码
SQL
from modelscope import snapshot_download
model_dir = snapshot_download('mirror013/ChatTTS')

# # 加载模型
chat = ChatTTS.Chat()
chat.load_models(
    source="local",
    local_path=model_dir,
)

替代以下代码：
SQL
chat = ChatTTS.Chat()
# chat.load_models(compile=False) # Set to True for better performance

4.torchaudio出现问题
问题如下：
SQL
Traceback (most recent call last):

    torchaudio.save("output1.wav", torch.from_numpy(wavs[0]), 24000)
  File "D:\Python\Anaconda3_2024_2_1\file\envs\talk\lib\site-packages\torchaudio\_backend\utils.py", line 312, in save
    backend = dispatcher(uri, format, backend)
  File "D:\Python\Anaconda3_2024_2_1\file\envs\talk\lib\site-packages\torchaudio\_backend\utils.py", line 222, in dispatcher
    raise RuntimeError(f"Couldn't find appropriate backend to handle uri {uri} and format {format}.")
RuntimeError: Couldn't find appropriate backend to handle uri output1.wav and format None.

解决办法：
SQL
pip install soundfile

5.webui的使用gradio进行公网链接生成时
设置share=True即可
SQL
import gradio as gr

def greet(name):
    return f"Hello {name}!"

iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch(share=True)

如果生成公网链接报错如下：
SQL
INFO:httpx:HTTP Request: GET https://api.gradio.app/v2/tunnel-request "HTTP/1.1 200 OK"

Could not create share link. Missing file: D:\Python\Anaconda3_2024_2_1\file\envs\talk\lib\site-packages\gradio\frpc_windows_amd64_v0.2.

Please check your internet connection. This can happen if your antivirus software blocks the download of this file. You can install manually by following these steps:

1. Download this file: https://cdn-media.huggingface.co/frpc-gradio-0.2/frpc_windows_amd64.exe
2. Rename the downloaded file to: frpc_windows_amd64_v0.2
3. Move the file to this location: D:\Python\Anaconda3_2024_2_1\file\envs\talk\lib\site-packages\gradio

解决办法：
SQL
点开下载链接：https://cdn-media.huggingface.co/frpc-gradio-0.2/frpc_windows_amd64.exe
下载到自创anaconda的环境里的lib\site-packages\gradio下
改名成frpc_windows_amd64_v0.2（注意改名时连exe后缀名也去掉)